[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MDDFZ8AKGGTD5V6JA1JQZX":3,"skill-same:01M6MDDFZ8AKGGTD5V6JA1JQZX":70},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6MDDFZ8AKGGTD5V6JA1JQZX","red-green-proof",null,"Turns a suspected bug into a proven one. Verify the cause against reality before claiming it, write a test that FAILS on the current code, apply the fix, watch it pass — then revert the fix and confirm the test goes red again, because a test that passes both ways proves nothing. Invoked bare after a debugging conversation, it takes the target from context rather than asking. Use when fixing a bug, investigating an incident, hardening a flaky area, or when asked to \"add tests that reveal the bug\". Triggers on \"\u002Fred-green-proof\", \"prove the bug\", \"red-green\", \"make the test fail first\", \"is that test load-bearing\", \"reveal the bug with a test\".","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\u002FRooAGI\u002Fred-green-proof\u002Fskills\u002Fred-green-proof\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"red green proof","green","proof","red","watch","when","bare","reveal","goes","make","add","triggers","debugging","tests","incident","conversation","bug","use","fix","context","write","code","2026-11-10 10:12:30",false,"---\nname: red-green-proof\ndescription: Turns a suspected bug into a proven one. Verify the cause against reality before claiming it, write a test that FAILS on the current code, apply the fix, watch it pass — then revert the fix and confirm the test goes red again, because a test that passes both ways proves nothing. Invoked bare after a debugging conversation, it takes the target from context rather than asking. Use when fixing a bug, investigating an incident, hardening a flaky area, or when asked to \"add tests that reveal the bug\". Triggers on \"\u002Fred-green-proof\", \"prove the bug\", \"red-green\", \"make the test fail first\", \"is that test load-bearing\", \"reveal the bug with a test\".\n---\n\n# Red-Green-Proof\n\nA bug is not fixed because the tests pass. A bug is fixed when a test **fails without your fix and passes with it**, and you have watched it do both.\n\nMost \"regression tests\" written after a fix never had the chance to fail. They are decoration. This skill is the discipline that separates a real test from a decorative one.\n\n## Picking the target\n\n**With an argument**, that is the target: `\u002Fred-green-proof the status endpoint reports finished runs as running`.\n\n**With no argument, take the target from the conversation.** The usual case is that you have just spent a long stretch investigating something — the bug is already on screen. Do not ask what to work on. Scan back through the session and pick, in this order:\n\n1. A defect just identified but not yet fixed.\n2. A fix applied without a failing test to back it — the most valuable target, because the test still has to be proven load-bearing.\n3. A test written but never verified red.\n4. Something described as \"still open\", \"not fixed yet\", or \"characterization only\".\n\nState your pick in one line and start:\n\n> Target: the buffer discards events when the flush write fails (`checkpointBuffer.ts:271`). Verifying before writing the test.\n\nOnly ask the user if two or more candidates are genuinely equal in priority — then list them as a short numbered choice and stop. If several *related* defects came up, handle them one at a time through the full loop rather than batching; each needs its own red.\n\nIf nothing in the conversation qualifies, say so and ask for a target rather than inventing one.\n\n## The loop\n\nRun these in order. Do not skip 1, and never skip 4.\n\n### 1. Verify the cause. Do not infer it.\n\nBefore you write a line of test code, establish what actually happened using evidence you can point at: the real record from the database or API, the real log line, the actual source of the function you are blaming.\n\nSay which of these you have:\n\n- **Proven** — I read the value \u002F ran the code \u002F pulled the record.\n- **Inferred** — consistent with the evidence, but I have not confirmed it.\n- **Unknown** — I cannot determine this from what is available.\n\nState the label out loud. If the honest answer is Unknown, say so and name the one artifact that would settle it. A confident wrong cause costs more than an admitted gap, because it sends the fix to the wrong place.\n\nTwo traps worth naming:\n- **A plausible mechanism is not the mechanism.** Rank candidates, then go rule them out one at a time by reading code, not by reasoning about it.\n- **Check whether the \"bug\" was deliberate.** `git log -S '\u003Cthe exact line>'` and read the commit. If a test already asserts the current behaviour, someone may have wanted it. Understand why before you invert it.\n\n### 2. Write the test. Watch it fail.\n\nThe test must fail **against the code as it is right now**, before any fix exists.\n\nName it after the defect, not the function: `reveals bug: stale status shadows a terminal event`, not `test inferStatus`.\n\nAssert the observable consequence a user or caller would see — the wrong status, the lost record, the 500 — not an internal call count. Call counts pass for the wrong reasons.\n\nIf it does not fail, you have not reproduced the bug. Go back to step 1.\n\n### 3. Fix it.\n\nSmallest change that makes the failing test pass. If the fix needs to be large, the test was probably too broad — narrow it and split.\n\n### 4. Revert the fix. Confirm red. ← the whole point\n\nPut the buggy code back, run the test, and **watch it fail**. Then restore the fix.\n\n```bash\ncp path\u002Fto\u002Ffixed.ts \u002Ftmp\u002Ffix.bak\n# revert the fix (edit, patch, or git stash the single file)\n\u003Crun the specific test>          # MUST fail here\ncp \u002Ftmp\u002Ffix.bak path\u002Fto\u002Ffixed.ts\n\u003Crun the specific test>          # green again\n```\n\nIf it stayed green, **the test is fake**. Not \"probably fine\" — fake. Rewrite it and repeat.\n\nThis is not paranoia. It catches a specific, common failure: a test that exercises a path adjacent to the bug rather than the bug. Two real examples:\n\n- A concurrency test modelled two writers but had no `await` between each writer's read and its write. Both ran to completion atomically, never interleaved, and the test passed with the lock removed. Fix: add latency between read and write, mirroring the real network gap.\n- A fault-isolation test asserted \"no 500 when the store fails\", but the injected failure was a *missing* record, which the loader turns into `null` rather than throwing. The error path never ran. Fix: inject a real 500.\n\nBoth looked correct on the page. Only the revert exposed them.\n\n### 5. Run everything.\n\nThe full suite, plus type checks. A fix that corrects one behaviour often contradicts a test that pinned the old one — which is a finding, not an annoyance. Go read that test and decide deliberately (see step 1).\n\n## When you cannot get a true red\n\nSometimes the buggy code cannot be invoked: it is a closure inside a 3,000-line factory, a route handler, a private method. Do not fake a behavioural test. Pick one of these and **label it in the file header**:\n\n| Type | Use when | Honesty requirement |\n|---|---|---|\n| **Extract, then test** | The logic can be moved to a module with injected dependencies | Preferred. Do this if the extraction is small. |\n| **Structural test** | The call site cannot be reached, but the invariant is visible in the source | Scan the source and assert the property (e.g. \"every write cycle sits inside the lock\"). It will name offenders itself. Say in the header that it is structural and should be replaced when the code becomes reachable. |\n| **Model test** | Testing an interaction between components you cannot both instantiate | Mirror the real code field-for-field, cite the file:line it models, and note in the header that it is a model. Extra important to run step 4 — models are where fake tests hide. |\n| **Characterization test** | Documenting current behaviour you are not fixing yet | Name it as such. Do not call it a regression test. Flag that it will invert when the bug is fixed. |\n\n## Reporting\n\nWhen you present the work, include:\n\n- What you **proved** vs **inferred** vs still do not know.\n- The **revert output** — the actual failure line, not a claim that it failed.\n- Which tests are behavioural, structural, model, or characterization.\n- Anything you got wrong earlier in the investigation, corrected explicitly.\n\nDo not describe a test as \"revealing the bug\" unless you have seen it red.\n\n## Anti-patterns\n\n- Writing the test after the fix and never reverting → decoration.\n- Asserting a mock was called instead of the user-visible outcome → passes for the wrong reason.\n- Widening a test until it passes → deleting the signal.\n- Inverting a pre-existing test because it blocks you → check the history first; it may encode a decision.\n- Reporting \"all green\" as success when nothing was ever red.\n\n## One-line version\n\nRed first, green second, **red again on purpose**, then green — and say which parts you actually proved.\n","# Red-Green-Proof\n\nA bug is not fixed because the tests pass. A bug is fixed when a test **fails without your fix and passes with it**, and you have watched it do both.\n\nMost \"regression tests\" written after a fix never had the chance to fail. They are decoration. This skill is the discipline that separates a real test from a decorative one.\n\n## Picking the target\n\n**With an argument**, that is the target: `\u002Fred-green-proof the status endpoint reports finished runs as running`.\n\n**With no argument, take the target from the conversation.** The usual case is that you have just spent a long stretch investigating something — the bug is already on screen. Do not ask what to work on. Scan back through the session and pick, in this order:\n\n1. A defect just identified but not yet fixed.\n2. A fix applied without a failing test to back it — the most valuable target, because the test still has to be proven load-bearing.\n3. A test written but never verified red.\n4. Something described as \"still open\", \"not fixed yet\", or \"characterization only\".\n\nState your pick in one line and start:\n\n> Target: the buffer discards events when the flush write fails (`checkpointBuffer.ts:271`). Verifying before writing the test.\n\nOnly ask the user if two or more candidates are genuinely equal in priority — then list them as a short numbered choice and stop. If several *related* defects came up, handle them one at a time through the full loop rather than batching; each needs its own red.\n\nIf nothing in the conversation qualifies, say so and ask for a target rather than inventing one.\n\n## The loop\n\nRun these in order. Do not skip 1, and never skip 4.\n\n### 1. Verify the cause. Do not infer it.\n\nBefore you write a line of test code, establish what actually happened using evidence you can point at: the real record from the database or API, the real log line, the actual source of the function you are blaming.\n\nSay which of these you have:\n\n- **Proven** — I read the value \u002F ran the code \u002F pulled the record.\n- **Inferred** — consistent with the evidence, but I have not confirmed it.\n- **Unknown** — I cannot determine this from what is available.\n\nState the label out loud. If the honest answer is Unknown, say so and name the one artifact that would settle it. A confident wrong cause costs more than an admitted gap, because it sends the fix to the wrong place.\n\nTwo traps worth naming:\n- **A plausible mechanism is not the mechanism.** Rank candidates, then go rule them out one at a time by reading code, not by reasoning about it.\n- **Check whether the \"bug\" was deliberate.** `git log -S '\u003Cthe exact line>'` and read the commit. If a test already asserts the current behaviour, someone may have wanted it. Understand why before you invert it.\n\n### 2. Write the test. Watch it fail.\n\nThe test must fail **against the code as it is right now**, before any fix exists.\n\nName it after the defect, not the function: `reveals bug: stale status shadows a terminal event`, not `test inferStatus`.\n\nAssert the observable consequence a user or caller would see — the wrong status, the lost record, the 500 — not an internal call count. Call counts pass for the wrong reasons.\n\nIf it does not fail, you have not reproduced the bug. Go back to step 1.\n\n### 3. Fix it.\n\nSmallest change that makes the failing test pass. If the fix needs to be large, the test was probably too broad — narrow it and split.\n\n### 4. Revert the fix. Confirm red. ← the whole point\n\nPut the buggy code back, run the test, and **watch it fail**. Then restore the fix.\n\n```bash\ncp path\u002Fto\u002Ffixed.ts \u002Ftmp\u002Ffix.bak\n# revert the fix (edit, patch, or git stash the single file)\n\u003Crun the specific test>          # MUST fail here\ncp \u002Ftmp\u002Ffix.bak path\u002Fto\u002Ffixed.ts\n\u003Crun the specific test>          # green again\n```\n\nIf it stayed green, **the test is fake**. Not \"probably fine\" — fake. Rewrite it and repeat.\n\nThis is not paranoia. It catches a specific, common failure: a test that exercises a path adjacent to the bug rather than the bug. Two real examples:\n\n- A concurrency test modelled two writers but had no `await` between each writer's read and its write. Both ran to completion atomically, never interleaved, and the test passed with the lock removed. Fix: add latency between read and write, mirroring the real network gap.\n- A fault-isolation test asserted \"no 500 when the store fails\", but the injected failure was a *missing* record, which the loader turns into `null` rather than throwing. The error path never ran. Fix: inject a real 500.\n\nBoth looked correct on the page. Only the revert exposed them.\n\n### 5. Run everything.\n\nThe full suite, plus type checks. A fix that corrects one behaviour often contradicts a test that pinned the old one — which is a finding, not an annoyance. Go read that test and decide deliberately (see step 1).\n\n## When you cannot get a true red\n\nSometimes the buggy code cannot be invoked: it is a closure inside a 3,000-line factory, a route handler, a private method. Do not fake a behavioural test. Pick one of these and **label it in the file header**:\n\n| Type | Use when | Honesty requirement |\n|---|---|---|\n| **Extract, then test** | The logic can be moved to a module with injected dependencies | Preferred. Do this if the extraction is small. |\n| **Structural test** | The call site cannot be reached, but the invariant is visible in the source | Scan the source and assert the property (e.g. \"every write cycle sits inside the lock\"). It will name offenders itself. Say in the header that it is structural and should be replaced when the code becomes reachable. |\n| **Model test** | Testing an interaction between components you cannot both instantiate | Mirror the real code field-for-field, cite the file:line it models, and note in the header that it is a model. Extra important to run step 4 — models are where fake tests hide. |\n| **Characterization test** | Documenting current behaviour you are not fixing yet | Name it as such. Do not call it a regression test. Flag that it will invert when the bug is fixed. |\n\n## Reporting\n\nWhen you present the work, include:\n\n- What you **proved** vs **inferred** vs still do not know.\n- The **revert output** — the actual failure line, not a claim that it failed.\n- Which tests are behavioural, structural, model, or characterization.\n- Anything you got wrong earlier in the investigation, corrected explicitly.\n\nDo not describe a test as \"revealing the bug\" unless you have seen it red.\n\n## Anti-patterns\n\n- Writing the test after the fix and never reverting → decoration.\n- Asserting a mock was called instead of the user-visible outcome → passes for the wrong reason.\n- Widening a test until it passes → deleting the signal.\n- Inverting a pre-existing test because it blocks you → check the history first; it may encode a decision.\n- Reporting \"all green\" as success when nothing was ever red.\n\n## One-line version\n\nRed first, green second, **red again on purpose**, then green — and say which parts you actually proved.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FRooAGI\u002Fred-green-proof\u002Fskills\u002Fred-green-proof",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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill red-green-proof",{"tool":62,"command":63},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill red-green-proof",{"tool":65,"command":66},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill red-green-proof","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FRooAGI\u002Fred-green-proof\u002Fskills\u002Fred-green-proof\u002FSKILL.md",true,[],[71,81,89,97,105,113],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":76,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":80},"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":80},"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":80},"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":80},"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":80},"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":80},"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",[],[]]