[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MMX0J1E4X74GDNC25XTW5J":3,"skill-same:01M6MMX0J1E4X74GDNC25XTW5J":93},{"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":23,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":62,"repositoryHtmlUrl":63,"repositoryHomepageUrl":64,"ownerHtmlUrl":65,"ownerBlogUrl":66,"ownerDescription":67,"updatedAt":68,"install":69,"resources":82},"01M6MMX0J1E4X74GDNC25XTW5J","owner-intent-audit",null,"Check agent-produced plans, tests, or code against the owner's actual intent. Find missing meaning, unrequested work, stale truth, unreachable decisions, unsupported completion claims, and implementation debt. Use before approval or merge.","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\u002Fsno-ai\u002Fsno-station-skills\u002Fskills\u002Fowner-intent-audit\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"audit","owner intent audit","intent","use","debt","unreachable","claims","meaning","missing","plans","tests","stale","merge","write","read","decisions","check","find","work","shell","file","code","2026-11-10 10:12:30",false,"---\nname: owner-intent-audit\ndescription: \"Check agent-produced plans, tests, or code against the owner's actual intent. Find missing meaning, unrequested work, stale truth, unreachable decisions, unsupported completion claims, and implementation debt. Use before approval or merge.\"\nrequires:\n  programs: []\n  harness:\n    - {slot: 4.shell, need: required}\n    - {slot: 4.file-read-write, need: required}\n---\n\n# Owner Intent Audit\n\nThe question this review answers is not \"is the artifact good\" but **\"is this what the owner\nmeant, and what did the agent leave behind while making it?\"** (The owner is whoever owns the\nwork and decides what it should be; often that is the user.) An agent can produce a PRD (product\nrequirements document), a plan, or a diff that is locally excellent and still specify a different product, carry work\nnobody asked for, or hide the debts agents characteristically create. Reviewing the artifact\nfor its own defects — bugs, security holes, silent death — is peer-review's job, not this one;\nthe two are run separately and neither substitutes for the other.\n\n- **Plan mode:** PRDs, designs, specs, task lists, refactor plans, and test plans.\n- **Code mode:** diffs, files, tests, or subsystems substantially written by agents.\n\nStart with the ordinary user and system flow. Realistic common-path failure outranks exotic\nedge cases.\n\n## What must be established\n\n### 0. Did the artifact preserve the product meaning?\n\nThis is not “did every source bullet appear?” A locally plausible artifact can retain the\nsame nouns while specifying a different product.\n\nDetermine:\n\n- who needs the outcome and who decides;\n- what result they actually need;\n- when the behavior applies and when it must not;\n- which exceptions, prohibitions, priorities, and trade-offs matter;\n- how separate answers constrain or explain each other;\n- what observable result distinguishes success from an easier proxy.\n\nFind that meaning in the owner's raw request, the complete question-and-answer record, and the\nsettled decisions. If the project keeps no such record, say so and use `incomplete-evidence`.\nFind loss of meaning in the target's requirements, ordinary flow, boundaries,\ndesign choices, and acceptance criteria. In code mode, also look through the governing\ncontract (the spec, interface, or acceptance text the code is supposed to satisfy), callers, state changes, and user-visible result.\n\nImportant shapes include a condition becoming unconditional, an actor changing, an example\nbecoming the whole boundary, a prohibition disappearing, related answers becoming isolated\nfacts, or a familiar implementation replacing the requested outcome.\n\nKeyword overlap and row-count traceability are not proof. Return real ambiguity to the owner;\ndo not invent meaning.\n\n### 1. What did the agent over-build?\n\nRun the `less-is-more` skill in cut mode on the diff (code mode). In plan mode, apply its cut\nlist to the plan as a checklist: what is proposed that the owner did not ask for, and what could\nbe deleted without losing the requested outcome. Every item it reports is a finding here. In plan mode, also ask what wording would invite\na literal agent to build it. Work that is necessary but belongs in a runbook, an orchestration\nstep, or a test harness rather than the product contract is misplaced process work: report where\nit should move, without dropping its constraint.\n\n### 2. Does the artifact graph resolve to one identity?\n\nThe plan or spec and everything tied to it must name the same current artifact by path, hash, and\nstatus, and every referenced file must exist. For example, where the project has them: a PRD, its\nacceptance file, its test commands, its evidence, and its status header. A stale identity or an\nunreachable verifier is a finding. Validate an absence check with a known positive control.\n\n### 3. What is current truth?\n\nSeparate **current contract** (what must be delivered), **current state** (what ran, passed, or\nremains), and **historical narrative** (why it changed). History may explain current truth; it\ncannot override it. A load-bearing claim that no longer matches reality — in a PRD, plan,\ncomment, default, or completed task — is a finding, because it misleads the next agent.\n\n### 4. Is the decision model executable?\n\nCheck decision tables, state machines, ordered guards, schemas, fixtures, and tests. Every\nclaimed branch must be reachable, branches claimed as exclusive must not overlap, and duplicate\nor shadowed branches must not masquerade as distinct outcomes.\n\n### 5. Did claimed work run and reach its consumer?\n\n“Ran,” “wired,” “enabled,” “deployed,” or “passed” require effect proof, not a flag, log line,\nor clean exit. Trace the ordinary entrypoint to an observable result; run the\n`agentic-walkthrough` skill when it is installed.\n\n## Evidence and judgment boundaries\n\nOwner-intent preservation needs the raw request, complete Q&A, and settled decisions. Missing,\npartial, stale, or non-blind intent evidence means `incomplete-evidence`, not `clean`; it limits\nonly the semantic verdict, and every other check still runs and reports. Intent evidence is\nnon-blind when the reviewer had already read the artifact under review before reconstructing the\nowner's meaning, so the comparison is not independent; say so.\n\nA behavior finding needs a realistic trigger and a material consequence; test it against\nguards and reachability before keeping it. An over-build finding from `less-is-more` needs no\ntrigger: the extra code is the consequence. Do not report style debt.\n\n## Output\n\nBy default this audit is one judgment pass: do not rerun it, or run another model review, to\nconfirm the edits that follow it; a project may choose otherwise. Never write a `clean` verdict\nbefore the audit has run. Keep the actual report immutable, record how each finding was handled,\nfix the material blockers in the work under review, prove the fixes deterministically, and\ncontinue without a model confirmation review (unless the project requires one).\n\n```markdown\n## Owner Intent Audit — \u003Ctarget>\nMode: plan | code\nVerdict: clean | findings | incomplete-evidence\n### Semantic preservation\nOwner-intent status: preserved | findings | not-assessable | non-blind\nContract-conformance status: preserved | findings | not-assessable\nEvidence: \u003Cwhat supports the judgment and what is missing>\n### Over-built\n\u003Cthe less-is-more cut output, plus any misplaced process work, or \"Lean already.\">\n### Findings\n[critical|high|medium] \u003Cfinding> — \u003Clocation>\nScenario: \u003Crealistic trigger and concrete consequence; omit for over-build>\nCorrection: \u003Csmallest outcome that removes the risk>\n### Guardrails\n\u003Cplan mode only; concise outcome constraints for the implementing agent>\n```\n\n`clean` requires every check, adequate intent evidence, and no unresolved material blocker in the\nwork under review—not zero raw findings. Resolved findings and non-blocking debt never force another review.\n","# Owner Intent Audit\n\nThe question this review answers is not \"is the artifact good\" but **\"is this what the owner\nmeant, and what did the agent leave behind while making it?\"** (The owner is whoever owns the\nwork and decides what it should be; often that is the user.) An agent can produce a PRD (product\nrequirements document), a plan, or a diff that is locally excellent and still specify a different product, carry work\nnobody asked for, or hide the debts agents characteristically create. Reviewing the artifact\nfor its own defects — bugs, security holes, silent death — is peer-review's job, not this one;\nthe two are run separately and neither substitutes for the other.\n\n- **Plan mode:** PRDs, designs, specs, task lists, refactor plans, and test plans.\n- **Code mode:** diffs, files, tests, or subsystems substantially written by agents.\n\nStart with the ordinary user and system flow. Realistic common-path failure outranks exotic\nedge cases.\n\n## What must be established\n\n### 0. Did the artifact preserve the product meaning?\n\nThis is not “did every source bullet appear?” A locally plausible artifact can retain the\nsame nouns while specifying a different product.\n\nDetermine:\n\n- who needs the outcome and who decides;\n- what result they actually need;\n- when the behavior applies and when it must not;\n- which exceptions, prohibitions, priorities, and trade-offs matter;\n- how separate answers constrain or explain each other;\n- what observable result distinguishes success from an easier proxy.\n\nFind that meaning in the owner's raw request, the complete question-and-answer record, and the\nsettled decisions. If the project keeps no such record, say so and use `incomplete-evidence`.\nFind loss of meaning in the target's requirements, ordinary flow, boundaries,\ndesign choices, and acceptance criteria. In code mode, also look through the governing\ncontract (the spec, interface, or acceptance text the code is supposed to satisfy), callers, state changes, and user-visible result.\n\nImportant shapes include a condition becoming unconditional, an actor changing, an example\nbecoming the whole boundary, a prohibition disappearing, related answers becoming isolated\nfacts, or a familiar implementation replacing the requested outcome.\n\nKeyword overlap and row-count traceability are not proof. Return real ambiguity to the owner;\ndo not invent meaning.\n\n### 1. What did the agent over-build?\n\nRun the `less-is-more` skill in cut mode on the diff (code mode). In plan mode, apply its cut\nlist to the plan as a checklist: what is proposed that the owner did not ask for, and what could\nbe deleted without losing the requested outcome. Every item it reports is a finding here. In plan mode, also ask what wording would invite\na literal agent to build it. Work that is necessary but belongs in a runbook, an orchestration\nstep, or a test harness rather than the product contract is misplaced process work: report where\nit should move, without dropping its constraint.\n\n### 2. Does the artifact graph resolve to one identity?\n\nThe plan or spec and everything tied to it must name the same current artifact by path, hash, and\nstatus, and every referenced file must exist. For example, where the project has them: a PRD, its\nacceptance file, its test commands, its evidence, and its status header. A stale identity or an\nunreachable verifier is a finding. Validate an absence check with a known positive control.\n\n### 3. What is current truth?\n\nSeparate **current contract** (what must be delivered), **current state** (what ran, passed, or\nremains), and **historical narrative** (why it changed). History may explain current truth; it\ncannot override it. A load-bearing claim that no longer matches reality — in a PRD, plan,\ncomment, default, or completed task — is a finding, because it misleads the next agent.\n\n### 4. Is the decision model executable?\n\nCheck decision tables, state machines, ordered guards, schemas, fixtures, and tests. Every\nclaimed branch must be reachable, branches claimed as exclusive must not overlap, and duplicate\nor shadowed branches must not masquerade as distinct outcomes.\n\n### 5. Did claimed work run and reach its consumer?\n\n“Ran,” “wired,” “enabled,” “deployed,” or “passed” require effect proof, not a flag, log line,\nor clean exit. Trace the ordinary entrypoint to an observable result; run the\n`agentic-walkthrough` skill when it is installed.\n\n## Evidence and judgment boundaries\n\nOwner-intent preservation needs the raw request, complete Q&A, and settled decisions. Missing,\npartial, stale, or non-blind intent evidence means `incomplete-evidence`, not `clean`; it limits\nonly the semantic verdict, and every other check still runs and reports. Intent evidence is\nnon-blind when the reviewer had already read the artifact under review before reconstructing the\nowner's meaning, so the comparison is not independent; say so.\n\nA behavior finding needs a realistic trigger and a material consequence; test it against\nguards and reachability before keeping it. An over-build finding from `less-is-more` needs no\ntrigger: the extra code is the consequence. Do not report style debt.\n\n## Output\n\nBy default this audit is one judgment pass: do not rerun it, or run another model review, to\nconfirm the edits that follow it; a project may choose otherwise. Never write a `clean` verdict\nbefore the audit has run. Keep the actual report immutable, record how each finding was handled,\nfix the material blockers in the work under review, prove the fixes deterministically, and\ncontinue without a model confirmation review (unless the project requires one).\n\n```markdown\n## Owner Intent Audit — \u003Ctarget>\nMode: plan | code\nVerdict: clean | findings | incomplete-evidence\n### Semantic preservation\nOwner-intent status: preserved | findings | not-assessable | non-blind\nContract-conformance status: preserved | findings | not-assessable\nEvidence: \u003Cwhat supports the judgment and what is missing>\n### Over-built\n\u003Cthe less-is-more cut output, plus any misplaced process work, or \"Lean already.\">\n### Findings\n[critical|high|medium] \u003Cfinding> — \u003Clocation>\nScenario: \u003Crealistic trigger and concrete consequence; omit for over-build>\nCorrection: \u003Csmallest outcome that removes the risk>\n### Guardrails\n\u003Cplan mode only; concise outcome constraints for the implementing agent>\n```\n\n`clean` requires every check, adequate intent evidence, and no unresolved material blocker in the\nwork under review—not zero raw findings. Resolved findings and non-blocking debt never force another review.\n",{"name":5,"requires":51,"description":7},{"harness":52,"programs":58},[53,56],{"need":54,"slot":55},"required","4.shell",{"need":54,"slot":57},"4.file-read-write",[],"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fsno-ai\u002Fsno-station-skills\u002Fskills\u002Fowner-intent-audit",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":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill owner-intent-audit",{"tool":75,"command":76},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill owner-intent-audit",{"tool":78,"command":79},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill owner-intent-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsno-ai\u002Fsno-station-skills\u002Fskills\u002Fowner-intent-audit\u002FSKILL.md",true,[83,89],{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fselftest\u002Frun-selftest.sh","SCRIPT","脚本",154,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsno-ai\u002Fsno-station-skills\u002Fskills\u002Fowner-intent-audit\u002Fscripts\u002Fselftest\u002Frun-selftest.sh",{"path":90,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fselftest\u002Fverify-review-boundary.sh",920,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsno-ai\u002Fsno-station-skills\u002Fskills\u002Fowner-intent-audit\u002Fscripts\u002Fselftest\u002Fverify-review-boundary.sh",[94,104,112,120,128,136],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":98,"licenseFileUrl":99,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":103},"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":98,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":103},"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":98,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":103},"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":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":98,"licenseFileUrl":124,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":103},"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":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":98,"licenseFileUrl":132,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":103},"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":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":98,"licenseFileUrl":140,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":103},"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",[],[]]