[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MGTHJ92M2H87BEFFGEP2KD":3,"skill-same:01M6MGTHJ92M2H87BEFFGEP2KD":100},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6MGTHJ92M2H87BEFFGEP2KD","playtest",null,"Playtest a studio's app against its owner's Codex needs, or its game the way Homie holds its own games to a bar — real browsers on a computer and a phone held both ways, the first ten seconds timed, the look measured (black or flat frames, contrast, detail), how much of the screen the UI covers, the game's real sound captured and measured, a round played with one person trying and one doing nothing, the owner control tests and two strangers finishing a round — then a blind review by a fresh reviewer that never saw the code, and a ranked list of what is weak. Use when someone asks to playtest, test, review, critique or judge a game, asks what is weak or what to fix next, before calling a game finished or publishing it, and after every change that should make it better.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fplaytest\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"never","when","studio","contrast","judge","screen","fresh","black","app","next","review","fix","list","reviewer","game","how","critique","ui","code","change","2026-11-10 10:12:30",false,"---\nname: playtest\ndescription: Playtest a studio's app against its owner's Codex needs, or its game the way Homie holds its own games to a bar — real browsers on a computer and a phone held both ways, the first ten seconds timed, the look measured (black or flat frames, contrast, detail), how much of the screen the UI covers, the game's real sound captured and measured, a round played with one person trying and one doing nothing, the owner control tests and two strangers finishing a round — then a blind review by a fresh reviewer that never saw the code, and a ranked list of what is weak. Use when someone asks to playtest, test, review, critique or judge a game, asks what is weak or what to fix next, before calling a game finished or publishing it, and after every change that should make it better.\n---\n\n## Apps: judge the place against its owner’s words\n\nFor an app, read `apps\u002F\u003Cid>\u002FCODEX.md` first. This is the app branch of the same playtest: no rounds, scores or invented entertainment. Run build and `check \u003Cid> --shots .checks` (including its Codex needs), then open the wall and phone in real Chrome. The game script below measures games; do not run a round instrument on an app.\n\nWalk in as the owner. Read **Their words** aloud to yourself, then inspect the wall capture: is the pictured place there, do recognisable things move\u002Ffill\u002Farrive\u002Flight up as requested, and can someone across the room understand the work? A generic board of boxes fails a living-scene request even if every label is correct. Check an empty and a busy state without passing invented records off as real customers. Inspect state before and after a real action, not only a pretty still.\n\nNow arrive as a new customer on a phone: find the offer and correct price, book\u002Fgive\u002Flog\u002Fsign up, understand success or failure, save the return link, reload and follow your own record. Use a second phone to check the link follows the same thing. As staff, sign in and perform the real work; as a public visitor, verify privileged writes are refused. Close all browsers and return: the work must remain. A simulated paid event is not a real charge; record payment connection gaps honestly.\n\nFor every need, write `met \u002F partly \u002F not`, the exact capture or flow that demonstrates it, and what remains. Check phone portrait\u002Flandscape, wall readability, kiosk reset if present, native controls, keyboard focus and reduced motion. Do not infer usability from a build or a shared counter. Inspect the saved captures yourself; automated selector assertions cannot judge the dreamed scene. Copy the verdict and evidence into the Codex and redraw its page. Keep unfinished needs visibly unfinished. No approval question is needed for local checks or your visual review.\n\nA local review is labelled local, not independent. If a fresh reviewer was requested, give that reviewer the owner's original request, the Codex and real captures\u002Fflow addresses; ask them to judge as owner and customer, need by need. When comparing several businesses, they must read as different places with different work, not a common template recoloured. If one fails, identify what the builder read or skipped, repair that making path, and build\u002Ftest again before saying done.\n\n# Playtest a game\n\nThe question is never \"does it run\". It is: **would a stranger who pressed Play stay for a whole\nround, and come back?** Instruments measure what can be measured; a fresh reviewer who never saw\nthe code answers the rest when the person asks for one.\n\nOne script: `scripts\u002Fplaytest.mjs` in this skill's folder (Claude Code:\n`node \"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fplaytest\u002Fscripts\u002Fplaytest.mjs\" \u003Ccommand>`), run from inside the\nstudio. It needs Node 22, Chrome and the studio's `@homie-rocks\u002Fstudio` (for puppeteer-core and its\nchecks). It opens at most two browsers at a time, all muted: nothing plays out loud.\n\nFor rules games, build first: the guard, strict types and deterministic play check must pass\nbefore Chrome opens. Both online browsers are replicas of a server host; killing the first\nbrowser tests continuity, not host election. Use the real predicted pose in the probe, never\nfake movement or scores. Test local movement with 150 ms delay and also verify hits, scores,\nturns and results agree after authority arrives. A turn game, quiz or live app needs its actual\nbuttons and workflow exercised: movement-only rows do not prove it works, and an app has no\nrequired game round. Use the app check for shared actions and reconnect. Report inapplicable\nrows honestly, and add a manual two-browser trial of the requested mechanic.\n\n## 1. Run the site and the instruments\n\nStart the site as a background task that outlives the command (Claude Code: the Bash tool's\n`run_in_background`), wait until the play page answers, then:\n\n```sh\nnpm run dev                                     # background: http:\u002F\u002F127.0.0.1:8787 (another port: npx --no-install homie-studio dev --port \u003Cn>)\nnode \u003Cplaytest.mjs> run \u003Cgame id> --url http:\u002F\u002F127.0.0.1:8787\n```\n\nIt takes five to ten minutes; poll its output, never end your turn while it runs, and do not rebuild\nwhile it runs (a rebuild under `npm run dev` can stop the dev server). `--only first,look,ui,sound`\nruns some rows; `--seconds 30` plays longer. The live site works too (`--url` the studio's address).\nStop the site afterwards with `npx --no-install homie-studio dev --stop`.\n\n| row | what it does | fails when |\n| --- | --- | --- |\n| `first \u003Cdevice>` | opens the play page like a stranger on a computer, a phone, a phone on its side, and times four separate things: a seat, the page's first paint (the loading card, not the game), the loading cover lifting, and the first picture of the game itself (cover gone, the game's own frames advancing); frames per second; the GPU | no seat, a cover that never lifts, or no picture of the game in 10 s |\n| `move \u003Cdevice>` | waits for a live round and a body that is the player's, then presses right and times the body moving; when nothing moves it presses left too and reports both, with the position, round phase and time left at each press | the body answers after 1.5 s, or neither way moves it in a live round. WARN when only the opposite way moved (a wall on that side looks like this). BLOCKED when no press fit inside a live round with a free body |\n| `look \u003Cdevice>` | plays like a person (holds a direction most of a second, sometimes the action, changes its mind) and shoots the screen: brightness, contrast, colour, visible detail, black or one-colour frames, holes where nothing drew, frames that did not change | a black or one-colour frame, pure-black holes; WARN for dark, flat, featureless or still frames |\n| `ui \u003Cphone>` | waits for active play, holds the thumb on the stick, hides the world, paints the page black then white, and counts what stays: the share of the screen the DOM UI covers and what is opaque in the middle third. Both frames are saved with the game's state at each | over 12% covered, or anything opaque in the middle, during active play. N\u002FA when the screen was the results card, a spectator view, the loading cover or a browser cut off from its room (measured, labelled, not judged by that bar). BLOCKED when the game changed state between the two frames. WARN when it would pass and a DOM HUD element sits under one of the play page's own controls (the room button, the server or chat pill, the banner): the row names the element and the control |\n| `sound` | copies what the game sends to its speaker while it is played (no autoplay flag: the real first-touch rule); loudness overall and through a phone speaker, true peak, clipping, gaps, whether each action press answers with a sound, whether music started | silence, clipping; WARN for quiet, gaps, actions without sound, what a phone loses |\n| `play` | a computer plays (direction holds and the game's primary action) and a phone does nothing, in the same public room, for a round that starts after both are in: places, scores, round length against `game.json`, lead changes, and which inputs the script really pressed | no round finishes; WARN when doing nothing scores as well as playing, everyone ties, or a bot is far ahead (a measured gap in one scripted round, never \"people cannot win\") |\n| `controls` | the owner tests from `homie-studio port check`: hold a direction 5 s (one straight line, the camera's yaw moves under 10°), alternate directions 10 s (every press goes the pressed way), real touch on Android Chrome (and iPhone WebKit when Playwright's WebKit is installed; otherwise that row says skip), the first browser closing (server continuity; host election only for older games), a late joiner, the big screen, audio unlock, errors | any of them (`port` skill: `references\u002FCHECKS.md` says what each failure usually means) |\n| `round` | `homie-studio check`: two fresh browsers press Play, meet in one room and both see a round finish with both of them in the results; reconnects are reported beside completion | they do not. WARN when the round finished and a browser reconnected on the way |\n| `errors` | uncaught errors and failed requests seen along the way | any uncaught error |\n\n**BLOCKED is never PASS.** A browser rendering at a few frames a second (a software renderer, a\nmachine under heavy load) makes any game look stuck: the rows say BLOCKED and judge nothing. Run\nagain on a quieter machine. \"Could not test\" and \"tested and fine\" must never sound the same.\nThe same goes for the instrument's own faults: a screenshot decoder that does not finish in 20 s\nis stopped, that device's rows say BLOCKED, the browser is closed and the run exits non-zero; a\nsite address this computer's Node.js cannot look up (a browser may still open it) stops the run as\nBLOCKED, \"network preflight failed, before any page or game was opened\" (the words `check`, `perf`\nand `port check` use for it too), and offers the local site. **N\u002FA** means the row did not apply to what\nwas on screen. One scripted run is one run: report a gap as measured once, and repeat before\nconcluding.\n\n### What the game tells the instruments\n\nEvery press and every picture is recorded with the game's state, read from its port probe\n(`exposePort`, the `port` skill) and the play page: round phase and time left, whether the body is\nthe player's to steer (`busy`), where it is. A game with no probe still runs, and its rows say the\nphase was unknown. Three optional things make the rows sharper; none is required:\n\n- In `exposePort(net, { extra: { ... } })`: `alive: () => boolean` (false: spectating until the\n  next round), `mode: () => string` (the control mode on screen), `loadout: () => string` (what\n  the player holds, when it changes which controls show), `touchHeld: () => boolean`, and\n  `drawCalls` \u002F `triangles` (`renderer.info.render.calls` \u002F `.triangles`: the look row then\n  reports measured runtime scene cost, which is not the asset inventory's estimate).\n- In `game.json`, the primary action, so a shooter is played by firing and not by the space bar:\n\n  ```json\n  \"playtest\": { \"primary\": { \"label\": \"fire\",\n    \"computer\": { \"mouse\": \"left\" },\n    \"phone\": { \"selector\": \"[data-action=fire]\" } } }\n  ```\n\n  `computer` is `{ \"key\": \"\u003CKeyboardEvent.code>\" }` or `{ \"mouse\": \"left|right|middle\", \"at\": [x, y] }`;\n  `phone` is `{ \"selector\": \"\u003Ccss, in the game's frame>\" }` or `{ \"region\": [x, y, w, h] }`\n  (fractions of the screen). Undeclared, the script presses the space bar and taps a fixed spot,\n  says that was a guess, and qualifies anything it concludes from the scores. It does not aim.\n- In `game.json`, `\"scoring\": \"together\"`: every result row carries the room's one shared total,\n  so the play row marks the active-against-idle comparison not applicable.\n\nThe UI row measures DOM coverage only. A HUD, labels or hints drawn inside the canvas are hidden\nwith the world and are not checked for coverage or overlap; REPORT.md says so beside the result.\n\nThe UI row also lays the game's visible DOM HUD against the play page's own controls, which the\npage draws over the game's frame and reports as `window.__shell.rects` (the game reads the same as\n`net.shell` \u002F `net.on('shell')`). A HUD element under a control that stays is a WARN with both\nnamed; under the \"N playing\" chip, which fades, it is a note. Fix it by laying the HUD out around\n`net.shell`'s rectangles, or by moving the page's controls (`game.json` `screen.share`,\n`screen.chat`). A page that reports no layout (an older studio) is said to be unchecked.\n\nA reading taken while the browser was not in its room is labelled, never judged as play: the\nhelper's link (`window.__homieNet.link`, and `window.__shell.link.state`) says `reconnecting`,\n`alone` (the room never answered; an older browser-hosted game may play locally), `offline` or `closed`, and a\npress, a picture or a UI frame sampled then is BLOCKED or N\u002FA with \"CUT OFF from its room\" in its\nstate. The round row says a browser \"was seen cut off\" beside completion.\n\nThe run writes `.playtest\u002F\u003Cgame>\u002F\u003Ctime>\u002F` in the studio (added to `.gitignore`): `REPORT.md`,\n`report.json`, contact sheets (`sheet-desk.png`, `sheet-phone.png`, `sheet-phone-landscape.png`),\nevery screenshot (the UI row's pair as `*-ui-on-black.png` and `*-ui-on-white.png`), `sound-capture.wav` and its spectrogram, and the owner-test receipts.\n**Open the contact sheets and look at every picture before believing any number.**\n\n## 2. The blind review\n\nFor a rules game with maxSpeed 0 on every player kind, the toolkit marks the\nmovement probe stationary. First-move rows say N\u002FA and directional owner tests\nsay not applicable, never PASS. Exercise its actual choices\u002Ftaps\u002Fturns in two\nbrowsers and measure local feedback separately from authoritative acceptance.\nDo not add movement, fake pose samples or a board-direction probe to silence a check.\nA hold entirely inside a hiding countdown, death or stun is blocked evidence.\nWait for an active, steerable phase and repeat the real controls in both browsers;\nrecord that directed result beside the generic row. Keep the mechanic and honest\nbusy\u002Falive probes; never remove a freeze or disguise it to turn a row green.\n\n```sh\nnode \u003Cplaytest.mjs> review .playtest\u002F\u003Cgame>\u002F\u003Ctime>\n```\n\nIt writes `REVIEW.md` in that folder: a brief for a FRESH reviewer, with the pictures, the numbers and\na rubric.\n\n**An outside review is optional, only when requested.** Finish local checks and your own visual review without an extra question. When an outside review is requested, it hands screenshots outside this session: use the authorization already given, or ask once if the destination was not specified.\nThe command prints `approval`: one self-contained question naming every file it sends (REVIEW.md,\nreport.json and the listed pictures), the report folder they come from, and the destination (name\nit with `--to \"\u003Cthe reviewer>\"`: a subagent in this session, or an external command such as a\nsecond coding agent). For a requested outside review without prior destination consent, ask that question once. One yes covers that report\nfolder and that reviewer; another folder or reviewer is a new question. `review-request.json` in\nthe folder keeps the same list. A host that reviews what an agent sends may still refuse the\ntransfer: that is the host's decision. Do not rephrase and retry it, and do not send the pictures\nanother way. Then one of:\n\n- `node \u003Cplaytest.mjs> review \u003Cfolder> --local` writes `REVIEW-LOCAL.md`: the same rubric for\n  this session to score the contact sheets itself. Nothing leaves the session. It is the builder\n  grading its own build, so it is labelled **not independent** everywhere, and you say so in the\n  first sentence when you report it.\n  Read that brief and every listed picture, follow its JSON rubric and write\n  `VERDICT.json` with `\"review\": \"local\"` in this exact run folder BEFORE calling\n  `reviewed --kind local`. The `reviewed` command records a verdict; it does not create one.\n  Rubric parts use 0–10; the overall JSON `score` and `--score` use **0–100**\n  (for example, an overall seven out of ten is `--score 70`, not `7`).\n- Record what happened, always: `node \u003Cplaytest.mjs> reviewed \u003Cfolder> --kind independent --by\n  \"\u003Cwho>\"`, `--kind local --reason \"\u003Cwhy>\"`, or `--kind none --reason \"\u003Cwhy>\"`. REPORT.md and\n  `report \u003Cfolder>` then say which review this run had. With no record, or `none`, the review line\n  is BLOCKED: a missing review never reads as a passed one. Hand its WHOLE TEXT, unchanged, to a reviewer that has not seen the code, the plan or your\nsummary (Claude Code: the Agent tool with the file's full contents as the prompt, never just its path\nor your summary of it; Codex: a new session). Add nothing about what you built or changed. It plays the game itself, scores it\n0-100 in eight parts, and returns gaps ranked by impact, each with evidence it saw and one concrete\nfix. Its verdict outranks yours. Put it in the run folder as `VERDICT.json`.\n\nComparing against other games (the person's references, the studio's last version, a game they\nadmire): give the reviewer frames of each under shuffled labels, scored before the labels are revealed.\nA reference is a bar (\"is it as good as that\"), never a template (\"make it look like that\").\n\nA game with models: give the reviewer the style board, the golden images and the lineup pictures\n(`homie-studio assets lineup \u003Cid>`, in `.studio\u002Fart\u002F\u003Cid>\u002F`) beside the frames, and add one question: \"does every\nframe look like ONE game?\" (1-10, naming outliers). Record it with `homie-studio assets review \u003Cid> --score \u003Cn>\n--outliers \u003Cids>`.\n\n## 3. Say what is weak\n\nLead with the numbers and the review, most important first: what fails, then what the reviewer would\nfix first. Group findings by cause before proposing work (five complaints about flat shapes are one\nmissing lighting model, not five jobs). Name the one change that would matter most. Then, if the\nperson wants, fix it and run the same instruments again; a change that does not measure better than\nthe version before it is a regression, not progress. When the weak thing is speed (a low frame rate in\n`first`, a slow first ten seconds, a phone that struggles), the `perf` skill measures it properly: frame\ntimes and CPU per frame for player browsers (server tick work is separate), alternating runs,\nand only changes that beat the noise.\nWhen the weak thing is how a move feels (a hit that does not land, a floaty jump), the `lab` skill compares the\nchange with the last commit frame by frame, with the person.\n\n`references\u002FMETHOD.md` has the method behind the rows: playing like a person, the five numbers a\nround owes you, the scenarios, seats with different strategies, the do-nothing test, the ten-second\ntest, and the traps that make an instrument lie.\n\n## Never\n\n- Never call a game good, fixed or finished from the code or a build that passed: play it first, and label your own look as local.\n- Never report a local review as a blind one, and never read a BLOCKED or N\u002FA row, or a missing review, as a pass.\n- Never turn one scripted round into a rule (\"people cannot win\", \"input does not matter\"): say what was measured, and run it again.\n- Never call the builder's local verdict an independent review: an independent reviewer is fresh every time.\n- Never script a player to make a number look good; the instruments play like a person on purpose.\n- Never leave a room open on a live site: the playtest's browsers leave when it ends; do not start\n  more than two browsers of your own beside it.\n","## Apps: judge the place against its owner’s words\n\nFor an app, read `apps\u002F\u003Cid>\u002FCODEX.md` first. This is the app branch of the same playtest: no rounds, scores or invented entertainment. Run build and `check \u003Cid> --shots .checks` (including its Codex needs), then open the wall and phone in real Chrome. The game script below measures games; do not run a round instrument on an app.\n\nWalk in as the owner. Read **Their words** aloud to yourself, then inspect the wall capture: is the pictured place there, do recognisable things move\u002Ffill\u002Farrive\u002Flight up as requested, and can someone across the room understand the work? A generic board of boxes fails a living-scene request even if every label is correct. Check an empty and a busy state without passing invented records off as real customers. Inspect state before and after a real action, not only a pretty still.\n\nNow arrive as a new customer on a phone: find the offer and correct price, book\u002Fgive\u002Flog\u002Fsign up, understand success or failure, save the return link, reload and follow your own record. Use a second phone to check the link follows the same thing. As staff, sign in and perform the real work; as a public visitor, verify privileged writes are refused. Close all browsers and return: the work must remain. A simulated paid event is not a real charge; record payment connection gaps honestly.\n\nFor every need, write `met \u002F partly \u002F not`, the exact capture or flow that demonstrates it, and what remains. Check phone portrait\u002Flandscape, wall readability, kiosk reset if present, native controls, keyboard focus and reduced motion. Do not infer usability from a build or a shared counter. Inspect the saved captures yourself; automated selector assertions cannot judge the dreamed scene. Copy the verdict and evidence into the Codex and redraw its page. Keep unfinished needs visibly unfinished. No approval question is needed for local checks or your visual review.\n\nA local review is labelled local, not independent. If a fresh reviewer was requested, give that reviewer the owner's original request, the Codex and real captures\u002Fflow addresses; ask them to judge as owner and customer, need by need. When comparing several businesses, they must read as different places with different work, not a common template recoloured. If one fails, identify what the builder read or skipped, repair that making path, and build\u002Ftest again before saying done.\n\n# Playtest a game\n\nThe question is never \"does it run\". It is: **would a stranger who pressed Play stay for a whole\nround, and come back?** Instruments measure what can be measured; a fresh reviewer who never saw\nthe code answers the rest when the person asks for one.\n\nOne script: `scripts\u002Fplaytest.mjs` in this skill's folder (Claude Code:\n`node \"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fplaytest\u002Fscripts\u002Fplaytest.mjs\" \u003Ccommand>`), run from inside the\nstudio. It needs Node 22, Chrome and the studio's `@homie-rocks\u002Fstudio` (for puppeteer-core and its\nchecks). It opens at most two browsers at a time, all muted: nothing plays out loud.\n\nFor rules games, build first: the guard, strict types and deterministic play check must pass\nbefore Chrome opens. Both online browsers are replicas of a server host; killing the first\nbrowser tests continuity, not host election. Use the real predicted pose in the probe, never\nfake movement or scores. Test local movement with 150 ms delay and also verify hits, scores,\nturns and results agree after authority arrives. A turn game, quiz or live app needs its actual\nbuttons and workflow exercised: movement-only rows do not prove it works, and an app has no\nrequired game round. Use the app check for shared actions and reconnect. Report inapplicable\nrows honestly, and add a manual two-browser trial of the requested mechanic.\n\n## 1. Run the site and the instruments\n\nStart the site as a background task that outlives the command (Claude Code: the Bash tool's\n`run_in_background`), wait until the play page answers, then:\n\n```sh\nnpm run dev                                     # background: http:\u002F\u002F127.0.0.1:8787 (another port: npx --no-install homie-studio dev --port \u003Cn>)\nnode \u003Cplaytest.mjs> run \u003Cgame id> --url http:\u002F\u002F127.0.0.1:8787\n```\n\nIt takes five to ten minutes; poll its output, never end your turn while it runs, and do not rebuild\nwhile it runs (a rebuild under `npm run dev` can stop the dev server). `--only first,look,ui,sound`\nruns some rows; `--seconds 30` plays longer. The live site works too (`--url` the studio's address).\nStop the site afterwards with `npx --no-install homie-studio dev --stop`.\n\n| row | what it does | fails when |\n| --- | --- | --- |\n| `first \u003Cdevice>` | opens the play page like a stranger on a computer, a phone, a phone on its side, and times four separate things: a seat, the page's first paint (the loading card, not the game), the loading cover lifting, and the first picture of the game itself (cover gone, the game's own frames advancing); frames per second; the GPU | no seat, a cover that never lifts, or no picture of the game in 10 s |\n| `move \u003Cdevice>` | waits for a live round and a body that is the player's, then presses right and times the body moving; when nothing moves it presses left too and reports both, with the position, round phase and time left at each press | the body answers after 1.5 s, or neither way moves it in a live round. WARN when only the opposite way moved (a wall on that side looks like this). BLOCKED when no press fit inside a live round with a free body |\n| `look \u003Cdevice>` | plays like a person (holds a direction most of a second, sometimes the action, changes its mind) and shoots the screen: brightness, contrast, colour, visible detail, black or one-colour frames, holes where nothing drew, frames that did not change | a black or one-colour frame, pure-black holes; WARN for dark, flat, featureless or still frames |\n| `ui \u003Cphone>` | waits for active play, holds the thumb on the stick, hides the world, paints the page black then white, and counts what stays: the share of the screen the DOM UI covers and what is opaque in the middle third. Both frames are saved with the game's state at each | over 12% covered, or anything opaque in the middle, during active play. N\u002FA when the screen was the results card, a spectator view, the loading cover or a browser cut off from its room (measured, labelled, not judged by that bar). BLOCKED when the game changed state between the two frames. WARN when it would pass and a DOM HUD element sits under one of the play page's own controls (the room button, the server or chat pill, the banner): the row names the element and the control |\n| `sound` | copies what the game sends to its speaker while it is played (no autoplay flag: the real first-touch rule); loudness overall and through a phone speaker, true peak, clipping, gaps, whether each action press answers with a sound, whether music started | silence, clipping; WARN for quiet, gaps, actions without sound, what a phone loses |\n| `play` | a computer plays (direction holds and the game's primary action) and a phone does nothing, in the same public room, for a round that starts after both are in: places, scores, round length against `game.json`, lead changes, and which inputs the script really pressed | no round finishes; WARN when doing nothing scores as well as playing, everyone ties, or a bot is far ahead (a measured gap in one scripted round, never \"people cannot win\") |\n| `controls` | the owner tests from `homie-studio port check`: hold a direction 5 s (one straight line, the camera's yaw moves under 10°), alternate directions 10 s (every press goes the pressed way), real touch on Android Chrome (and iPhone WebKit when Playwright's WebKit is installed; otherwise that row says skip), the first browser closing (server continuity; host election only for older games), a late joiner, the big screen, audio unlock, errors | any of them (`port` skill: `references\u002FCHECKS.md` says what each failure usually means) |\n| `round` | `homie-studio check`: two fresh browsers press Play, meet in one room and both see a round finish with both of them in the results; reconnects are reported beside completion | they do not. WARN when the round finished and a browser reconnected on the way |\n| `errors` | uncaught errors and failed requests seen along the way | any uncaught error |\n\n**BLOCKED is never PASS.** A browser rendering at a few frames a second (a software renderer, a\nmachine under heavy load) makes any game look stuck: the rows say BLOCKED and judge nothing. Run\nagain on a quieter machine. \"Could not test\" and \"tested and fine\" must never sound the same.\nThe same goes for the instrument's own faults: a screenshot decoder that does not finish in 20 s\nis stopped, that device's rows say BLOCKED, the browser is closed and the run exits non-zero; a\nsite address this computer's Node.js cannot look up (a browser may still open it) stops the run as\nBLOCKED, \"network preflight failed, before any page or game was opened\" (the words `check`, `perf`\nand `port check` use for it too), and offers the local site. **N\u002FA** means the row did not apply to what\nwas on screen. One scripted run is one run: report a gap as measured once, and repeat before\nconcluding.\n\n### What the game tells the instruments\n\nEvery press and every picture is recorded with the game's state, read from its port probe\n(`exposePort`, the `port` skill) and the play page: round phase and time left, whether the body is\nthe player's to steer (`busy`), where it is. A game with no probe still runs, and its rows say the\nphase was unknown. Three optional things make the rows sharper; none is required:\n\n- In `exposePort(net, { extra: { ... } })`: `alive: () => boolean` (false: spectating until the\n  next round), `mode: () => string` (the control mode on screen), `loadout: () => string` (what\n  the player holds, when it changes which controls show), `touchHeld: () => boolean`, and\n  `drawCalls` \u002F `triangles` (`renderer.info.render.calls` \u002F `.triangles`: the look row then\n  reports measured runtime scene cost, which is not the asset inventory's estimate).\n- In `game.json`, the primary action, so a shooter is played by firing and not by the space bar:\n\n  ```json\n  \"playtest\": { \"primary\": { \"label\": \"fire\",\n    \"computer\": { \"mouse\": \"left\" },\n    \"phone\": { \"selector\": \"[data-action=fire]\" } } }\n  ```\n\n  `computer` is `{ \"key\": \"\u003CKeyboardEvent.code>\" }` or `{ \"mouse\": \"left|right|middle\", \"at\": [x, y] }`;\n  `phone` is `{ \"selector\": \"\u003Ccss, in the game's frame>\" }` or `{ \"region\": [x, y, w, h] }`\n  (fractions of the screen). Undeclared, the script presses the space bar and taps a fixed spot,\n  says that was a guess, and qualifies anything it concludes from the scores. It does not aim.\n- In `game.json`, `\"scoring\": \"together\"`: every result row carries the room's one shared total,\n  so the play row marks the active-against-idle comparison not applicable.\n\nThe UI row measures DOM coverage only. A HUD, labels or hints drawn inside the canvas are hidden\nwith the world and are not checked for coverage or overlap; REPORT.md says so beside the result.\n\nThe UI row also lays the game's visible DOM HUD against the play page's own controls, which the\npage draws over the game's frame and reports as `window.__shell.rects` (the game reads the same as\n`net.shell` \u002F `net.on('shell')`). A HUD element under a control that stays is a WARN with both\nnamed; under the \"N playing\" chip, which fades, it is a note. Fix it by laying the HUD out around\n`net.shell`'s rectangles, or by moving the page's controls (`game.json` `screen.share`,\n`screen.chat`). A page that reports no layout (an older studio) is said to be unchecked.\n\nA reading taken while the browser was not in its room is labelled, never judged as play: the\nhelper's link (`window.__homieNet.link`, and `window.__shell.link.state`) says `reconnecting`,\n`alone` (the room never answered; an older browser-hosted game may play locally), `offline` or `closed`, and a\npress, a picture or a UI frame sampled then is BLOCKED or N\u002FA with \"CUT OFF from its room\" in its\nstate. The round row says a browser \"was seen cut off\" beside completion.\n\nThe run writes `.playtest\u002F\u003Cgame>\u002F\u003Ctime>\u002F` in the studio (added to `.gitignore`): `REPORT.md`,\n`report.json`, contact sheets (`sheet-desk.png`, `sheet-phone.png`, `sheet-phone-landscape.png`),\nevery screenshot (the UI row's pair as `*-ui-on-black.png` and `*-ui-on-white.png`), `sound-capture.wav` and its spectrogram, and the owner-test receipts.\n**Open the contact sheets and look at every picture before believing any number.**\n\n## 2. The blind review\n\nFor a rules game with maxSpeed 0 on every player kind, the toolkit marks the\nmovement probe stationary. First-move rows say N\u002FA and directional owner tests\nsay not applicable, never PASS. Exercise its actual choices\u002Ftaps\u002Fturns in two\nbrowsers and measure local feedback separately from authoritative acceptance.\nDo not add movement, fake pose samples or a board-direction probe to silence a check.\nA hold entirely inside a hiding countdown, death or stun is blocked evidence.\nWait for an active, steerable phase and repeat the real controls in both browsers;\nrecord that directed result beside the generic row. Keep the mechanic and honest\nbusy\u002Falive probes; never remove a freeze or disguise it to turn a row green.\n\n```sh\nnode \u003Cplaytest.mjs> review .playtest\u002F\u003Cgame>\u002F\u003Ctime>\n```\n\nIt writes `REVIEW.md` in that folder: a brief for a FRESH reviewer, with the pictures, the numbers and\na rubric.\n\n**An outside review is optional, only when requested.** Finish local checks and your own visual review without an extra question. When an outside review is requested, it hands screenshots outside this session: use the authorization already given, or ask once if the destination was not specified.\nThe command prints `approval`: one self-contained question naming every file it sends (REVIEW.md,\nreport.json and the listed pictures), the report folder they come from, and the destination (name\nit with `--to \"\u003Cthe reviewer>\"`: a subagent in this session, or an external command such as a\nsecond coding agent). For a requested outside review without prior destination consent, ask that question once. One yes covers that report\nfolder and that reviewer; another folder or reviewer is a new question. `review-request.json` in\nthe folder keeps the same list. A host that reviews what an agent sends may still refuse the\ntransfer: that is the host's decision. Do not rephrase and retry it, and do not send the pictures\nanother way. Then one of:\n\n- `node \u003Cplaytest.mjs> review \u003Cfolder> --local` writes `REVIEW-LOCAL.md`: the same rubric for\n  this session to score the contact sheets itself. Nothing leaves the session. It is the builder\n  grading its own build, so it is labelled **not independent** everywhere, and you say so in the\n  first sentence when you report it.\n  Read that brief and every listed picture, follow its JSON rubric and write\n  `VERDICT.json` with `\"review\": \"local\"` in this exact run folder BEFORE calling\n  `reviewed --kind local`. The `reviewed` command records a verdict; it does not create one.\n  Rubric parts use 0–10; the overall JSON `score` and `--score` use **0–100**\n  (for example, an overall seven out of ten is `--score 70`, not `7`).\n- Record what happened, always: `node \u003Cplaytest.mjs> reviewed \u003Cfolder> --kind independent --by\n  \"\u003Cwho>\"`, `--kind local --reason \"\u003Cwhy>\"`, or `--kind none --reason \"\u003Cwhy>\"`. REPORT.md and\n  `report \u003Cfolder>` then say which review this run had. With no record, or `none`, the review line\n  is BLOCKED: a missing review never reads as a passed one. Hand its WHOLE TEXT, unchanged, to a reviewer that has not seen the code, the plan or your\nsummary (Claude Code: the Agent tool with the file's full contents as the prompt, never just its path\nor your summary of it; Codex: a new session). Add nothing about what you built or changed. It plays the game itself, scores it\n0-100 in eight parts, and returns gaps ranked by impact, each with evidence it saw and one concrete\nfix. Its verdict outranks yours. Put it in the run folder as `VERDICT.json`.\n\nComparing against other games (the person's references, the studio's last version, a game they\nadmire): give the reviewer frames of each under shuffled labels, scored before the labels are revealed.\nA reference is a bar (\"is it as good as that\"), never a template (\"make it look like that\").\n\nA game with models: give the reviewer the style board, the golden images and the lineup pictures\n(`homie-studio assets lineup \u003Cid>`, in `.studio\u002Fart\u002F\u003Cid>\u002F`) beside the frames, and add one question: \"does every\nframe look like ONE game?\" (1-10, naming outliers). Record it with `homie-studio assets review \u003Cid> --score \u003Cn>\n--outliers \u003Cids>`.\n\n## 3. Say what is weak\n\nLead with the numbers and the review, most important first: what fails, then what the reviewer would\nfix first. Group findings by cause before proposing work (five complaints about flat shapes are one\nmissing lighting model, not five jobs). Name the one change that would matter most. Then, if the\nperson wants, fix it and run the same instruments again; a change that does not measure better than\nthe version before it is a regression, not progress. When the weak thing is speed (a low frame rate in\n`first`, a slow first ten seconds, a phone that struggles), the `perf` skill measures it properly: frame\ntimes and CPU per frame for player browsers (server tick work is separate), alternating runs,\nand only changes that beat the noise.\nWhen the weak thing is how a move feels (a hit that does not land, a floaty jump), the `lab` skill compares the\nchange with the last commit frame by frame, with the person.\n\n`references\u002FMETHOD.md` has the method behind the rows: playing like a person, the five numbers a\nround owes you, the scenarios, seats with different strategies, the do-nothing test, the ten-second\ntest, and the traps that make an instrument lie.\n\n## Never\n\n- Never call a game good, fixed or finished from the code or a build that passed: play it first, and label your own look as local.\n- Never report a local review as a blind one, and never read a BLOCKED or N\u002FA row, or a missing review, as a pass.\n- Never turn one scripted round into a rule (\"people cannot win\", \"input does not matter\"): say what was measured, and run it again.\n- Never call the builder's local verdict an independent review: an independent reviewer is fresh every time.\n- Never script a player to make a number look good; the instruments play like a person on purpose.\n- Never leave a room open on a live site: the playtest's browsers leave when it ends; do not start\n  more than two browsers of your own beside it.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fplaytest",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill playtest",{"tool":60,"command":61},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill playtest",{"tool":63,"command":64},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill playtest","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fplaytest\u002FSKILL.md",true,[68,74,78,84,88,92,96],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002FMETHOD.md","REFERENCE","参考文档",8176,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fplaytest\u002Freferences\u002FMETHOD.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002FREVIEWER.md",4018,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fplaytest\u002Freferences\u002FREVIEWER.md",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Flib\u002Fexit.mjs","SCRIPT","脚本",1959,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fplaytest\u002Fscripts\u002Flib\u002Fexit.mjs",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Flib\u002Fjudge.mjs",40666,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fplaytest\u002Fscripts\u002Flib\u002Fjudge.mjs",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Flib\u002Fpixels.mjs",7809,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fplaytest\u002Fscripts\u002Flib\u002Fpixels.mjs",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Flib\u002Fpreflight.mjs",5445,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fplaytest\u002Fscripts\u002Flib\u002Fpreflight.mjs",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Fplaytest.mjs",67355,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fplaytest\u002Fscripts\u002Fplaytest.mjs",[101,111,119,127,135,143],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":105,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":110},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":105,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":110},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":105,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":110},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":105,"licenseFileUrl":131,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":110},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":105,"licenseFileUrl":139,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":110},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":105,"licenseFileUrl":147,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":110},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]