[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MGSX1GTJTZZWBYFFHWFGVE":3,"skill-same:01M6MGSX1GTJTZZWBYFFHWFGVE":69},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6MGSX1GTJTZZWBYFFHWFGVE","parallel",null,"Build a planned game with several agents at once — game logic and netcode, levels, art, sound, the landing page — each in its own folders, then one merge, a two-browser check, a playtest and a blind review. Use only when parallel work is requested and the host supports it. Use after the plan step, or when someone asks to \"build it in parallel\", \"use more agents\", \"split the work\" or \"go faster\".","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\u002Fparallel\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"use","when","at","more","split","with","host","logic","build","Art","only","review","landing","check","work","page","game","plan","browser","merge","go","2026-11-10 10:12:30",false,"---\nname: parallel\ndescription: Build a planned game with several agents at once — game logic and netcode, levels, art, sound, the landing page — each in its own folders, then one merge, a two-browser check, a playtest and a blind review. Use only when parallel work is requested and the host supports it. Use after the plan step, or when someone asks to \"build it in parallel\", \"use more agents\", \"split the work\" or \"go faster\".\n---\n\n# Build in parallel\n\nOne agent building step by step is slower but uses the least. Several agents, each on its own part of\nthe game at the same time, finish sooner and use more. The person chooses.\n\n## 1. Only when requested\n\nUse one agent by default. Do not turn implementation staffing into a question for the person.\nWhen parallel work is requested and the host supports it, choose the number of agents from the\nindependent work available, within the agreed usage budget. Say the allocation briefly and proceed.\n\n## 2. Split the work: one folder each\n\nEvery agent writes only in its own folders. Pick the parts the codex calls for:\n\n| Part | Writes only in | Reads | Hands back |\n| --- | --- | --- | --- |\n| Rules, movement and view | `games\u002F\u003Cid>\u002Fsrc\u002F` (not `src\u002Flevels\u002F`) | the codex's Concept, Rooms and players, Controls; the game skill's RULES.md and NETPLAY.md section 29 | declared truth and events in rules.ts, prediction in move.ts, input and rendering in view.ts; server host by default |\n| Levels and content | `games\u002F\u003Cid>\u002Fsrc\u002Flevels\u002F` | the codex's World and Characters | levels, waves or maps as data the game logic loads |\n| Art | `games\u002F\u003Cid>\u002Fpublic\u002Fart\u002F`, `games\u002F\u003Cid>\u002Fart\u002F` | the codex's Art direction and Characters; the `art` skill | sprites, backdrops, the cover, at the sizes the contract names |\n| Sound | `games\u002F\u003Cid>\u002Fpublic\u002Fsound\u002F`, `music\u002F\u003Cslug>\u002F` | the codex's Music and sound; the `sound` skill | the named sound effects and the theme |\n| Landing page | `games\u002F\u003Cid>\u002Fhero\u002F`, `site\u002Fpartials\u002Fgame-\u003Cid>.html` | the codex's Concept and Art direction; the `game` skill's landing | hero footage once the game runs, the landing's words as a proposal |\n\n**Shared files have one owner: you, the lead.** `game.json`, `CODEX.md`, `index.html`, `package.json`,\n`studio.json` and `site\u002Ftheme.json` are written only in the merge. A part that needs one changed says so\nin its report.\n\n**Write the contract into the codex before anyone starts**, so the parts meet without talking: the sound\nnames the game logic calls (`pickup`, `hit`, `win`), the art files and their sizes, the shape of a level.\nEach goes in its section (Music and sound, Art direction, World), with a dated line under Latest.\n\n## 3. Brief each agent\n\nGive every agent the same shape of brief:\n\n- **Goal**: its part, in a paragraph, from the codex (`games\u002F\u003Cid>\u002FCODEX.md`, which it reads first).\n- **Its folders**: where it may write; everything else is read-only; never another part's folder.\n- **The contract**: names, paths and shapes from the codex.\n- **How to check its part alone**: `npm run build` passes; the `sound` skill's measure; the `art` skill's\n  look at its pictures; for levels, the game loads them.\n- **Not its job**: running the dev server, deploying, committing, installing packages, ending the\n  progress feed, editing the shared files.\n- **Progress**: `npx --no-install homie-studio progress check \u003Cpart> running --label \"\u003CPart>\"` when it\n  starts, `pass` or `fail` when it ends (you opened the feed with `progress start`).\n- **Its report**: what it made, the files, what the shared files need, and anything it could not decide.\n\nIn Claude Code (2.1.287 or later), the Homie mod's parts pane (`\u002Fparts`; it opens by itself when two\nagents run) shows each agent's time, tool calls, files and last step, and the feed's check for each part,\nso the person can watch the parts without asking you.\n\nCommit first, so the tree is clean and each part's work is easy to see and to undo. Start them in one\nmessage so they run at the same time (Claude Code: several Agent calls in one reply),\nand wait for every report before merging. Money (painted art, generated video, songs) stays inside the\nbudget the person set, split between the parts that spend; each spend goes on the feed with\n`progress spend`.\n\n## 4. Merge, check, playtest, review\n\n1. Read every report. Apply what the shared files need (wire the sound names and art paths into\n   `game.json` and the code, the landing words into `game.json` `landing`).\n2. `npm run build`, and fix what does not fit together yourself.\n3. `npm run dev` in the background, then `npx --no-install homie-studio check \u003Cid> --url\n   http:\u002F\u002F127.0.0.1:8787`: two browsers, one room, a finished round.\n4. The `playtest` skill: the instruments, then its blind review by a fresh agent that has not seen the\n   code, the codex or any report (`playtest` skill: `references\u002FREVIEWER.md`). It ranks what is weak; fix\n   the top of the list, and check again.\n5. Update the codex: tick the milestone, a dated line under Latest for what changed, redraw it\n   (`homie-studio codex \u003Cid>`, and the artifact if there is one), and end the feed (`progress end passed`).\n6. Commit once, after the merge (`git add -A && git commit` in the studio).\n\n## When a part goes wrong\n\nA part that fails its own check, or writes outside its folders, is redone, not patched over: put its\nfolders back as they were at the last commit (`git restore -- \u003Cfolder>`; `git clean -nd -- \u003Cfolder>` lists\nthe new files it made there, and `git clean -fd -- \u003Cfolder>` removes them), then brief it again with what\nwent wrong. Two failures in a row: do that part yourself, step by step.\n","# Build in parallel\n\nOne agent building step by step is slower but uses the least. Several agents, each on its own part of\nthe game at the same time, finish sooner and use more. The person chooses.\n\n## 1. Only when requested\n\nUse one agent by default. Do not turn implementation staffing into a question for the person.\nWhen parallel work is requested and the host supports it, choose the number of agents from the\nindependent work available, within the agreed usage budget. Say the allocation briefly and proceed.\n\n## 2. Split the work: one folder each\n\nEvery agent writes only in its own folders. Pick the parts the codex calls for:\n\n| Part | Writes only in | Reads | Hands back |\n| --- | --- | --- | --- |\n| Rules, movement and view | `games\u002F\u003Cid>\u002Fsrc\u002F` (not `src\u002Flevels\u002F`) | the codex's Concept, Rooms and players, Controls; the game skill's RULES.md and NETPLAY.md section 29 | declared truth and events in rules.ts, prediction in move.ts, input and rendering in view.ts; server host by default |\n| Levels and content | `games\u002F\u003Cid>\u002Fsrc\u002Flevels\u002F` | the codex's World and Characters | levels, waves or maps as data the game logic loads |\n| Art | `games\u002F\u003Cid>\u002Fpublic\u002Fart\u002F`, `games\u002F\u003Cid>\u002Fart\u002F` | the codex's Art direction and Characters; the `art` skill | sprites, backdrops, the cover, at the sizes the contract names |\n| Sound | `games\u002F\u003Cid>\u002Fpublic\u002Fsound\u002F`, `music\u002F\u003Cslug>\u002F` | the codex's Music and sound; the `sound` skill | the named sound effects and the theme |\n| Landing page | `games\u002F\u003Cid>\u002Fhero\u002F`, `site\u002Fpartials\u002Fgame-\u003Cid>.html` | the codex's Concept and Art direction; the `game` skill's landing | hero footage once the game runs, the landing's words as a proposal |\n\n**Shared files have one owner: you, the lead.** `game.json`, `CODEX.md`, `index.html`, `package.json`,\n`studio.json` and `site\u002Ftheme.json` are written only in the merge. A part that needs one changed says so\nin its report.\n\n**Write the contract into the codex before anyone starts**, so the parts meet without talking: the sound\nnames the game logic calls (`pickup`, `hit`, `win`), the art files and their sizes, the shape of a level.\nEach goes in its section (Music and sound, Art direction, World), with a dated line under Latest.\n\n## 3. Brief each agent\n\nGive every agent the same shape of brief:\n\n- **Goal**: its part, in a paragraph, from the codex (`games\u002F\u003Cid>\u002FCODEX.md`, which it reads first).\n- **Its folders**: where it may write; everything else is read-only; never another part's folder.\n- **The contract**: names, paths and shapes from the codex.\n- **How to check its part alone**: `npm run build` passes; the `sound` skill's measure; the `art` skill's\n  look at its pictures; for levels, the game loads them.\n- **Not its job**: running the dev server, deploying, committing, installing packages, ending the\n  progress feed, editing the shared files.\n- **Progress**: `npx --no-install homie-studio progress check \u003Cpart> running --label \"\u003CPart>\"` when it\n  starts, `pass` or `fail` when it ends (you opened the feed with `progress start`).\n- **Its report**: what it made, the files, what the shared files need, and anything it could not decide.\n\nIn Claude Code (2.1.287 or later), the Homie mod's parts pane (`\u002Fparts`; it opens by itself when two\nagents run) shows each agent's time, tool calls, files and last step, and the feed's check for each part,\nso the person can watch the parts without asking you.\n\nCommit first, so the tree is clean and each part's work is easy to see and to undo. Start them in one\nmessage so they run at the same time (Claude Code: several Agent calls in one reply),\nand wait for every report before merging. Money (painted art, generated video, songs) stays inside the\nbudget the person set, split between the parts that spend; each spend goes on the feed with\n`progress spend`.\n\n## 4. Merge, check, playtest, review\n\n1. Read every report. Apply what the shared files need (wire the sound names and art paths into\n   `game.json` and the code, the landing words into `game.json` `landing`).\n2. `npm run build`, and fix what does not fit together yourself.\n3. `npm run dev` in the background, then `npx --no-install homie-studio check \u003Cid> --url\n   http:\u002F\u002F127.0.0.1:8787`: two browsers, one room, a finished round.\n4. The `playtest` skill: the instruments, then its blind review by a fresh agent that has not seen the\n   code, the codex or any report (`playtest` skill: `references\u002FREVIEWER.md`). It ranks what is weak; fix\n   the top of the list, and check again.\n5. Update the codex: tick the milestone, a dated line under Latest for what changed, redraw it\n   (`homie-studio codex \u003Cid>`, and the artifact if there is one), and end the feed (`progress end passed`).\n6. Commit once, after the merge (`git add -A && git commit` in the studio).\n\n## When a part goes wrong\n\nA part that fails its own check, or writes outside its folders, is redone, not patched over: put its\nfolders back as they were at the last commit (`git restore -- \u003Cfolder>`; `git clean -nd -- \u003Cfolder>` lists\nthe new files it made there, and `git clean -fd -- \u003Cfolder>` removes them), then brief it again with what\nwent wrong. Two failures in a row: do that part yourself, step by step.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fparallel",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":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill parallel",{"tool":61,"command":62},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill parallel",{"tool":64,"command":65},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill parallel","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhomie-rocks\u002Fhomie\u002Fskills\u002Fparallel\u002FSKILL.md",true,[],[70,80,88,96,104,112],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":75,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":79},"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":79},"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":79},"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":79},"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":79},"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":79},"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",[],[]]