[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JWT4ASBR8XW0H0Q6ZEBCPE":3,"skill-same:01M6JWT4ASBR8XW0H0Q6ZEBCPE":75},{"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},"01M6JWT4ASBR8XW0H0Q6ZEBCPE","dev-grill-docs",null,"Clarify feature requirements, pressure-test scope and domain terms, and produce a feature spec before implementation. Use for fuzzy requirements, PRD\u002Fspec requests, 需求对齐, 拷问需求, or 设计文档. Read existing evidence before asking focused questions. For concrete implementation planning use dev-plan; a generic \"do not edit code\" instruction alone does not trigger intake. Supports --quick, --deep, and --spec-only.","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\u002FJason-chen-coder\u002Fdev-skills\u002Fskills\u002Fdev-grill-docs\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"docs","dev grill docs","dev","grill","generic","design","for","quick","scope","feature","deep","domain","do","evidence","only","edit","read","clarify","plan","planning","code","2026-11-10 10:12:30",false,"---\nname: dev-grill-docs\ndescription: 'Clarify feature requirements, pressure-test scope and domain terms, and produce a feature spec before implementation. Use for fuzzy requirements, PRD\u002Fspec requests, 需求对齐, 拷问需求, or 设计文档. Read existing evidence before asking focused questions. For concrete implementation planning use dev-plan; a generic \"do not edit code\" instruction alone does not trigger intake. Supports --quick, --deep, and --spec-only.'\n---\n\n# Dev Grill Docs\n\nTurn the user's feature intent into a usable contract. Preserve decisions already made and ask only about gaps that change behavior, scope, acceptance, or substantial cost. This skill does not implement code or replace analysis-only requests with document work.\n\nRead [references\u002Fdev-baseline.md](references\u002Fdev-baseline.md). Project artifacts belong in the user's project, not the skill directory.\n\n## Routing and depth\n\n- Use this entry point for requirement alignment. `dev-spec` is the compatibility alias for `--spec-only`.\n- When scope is already clear and the user wants implementation steps, use `dev-plan` if available; a particular phrase such as \"写个方案\" does not override the conversation's actual intent.\n- Broken behavior belongs to `dev-fix`. Persistent visual direction belongs to `dev-design-context`.\n- `--quick` requests a compact contract and minimal questions; zero questions is correct when evidence is sufficient.\n- Default depth covers the material uncertainties. `--deep` adds scrutiny of lifecycle, invariants, compatibility, failures, and reversibility where relevant.\n- `--spec-only` disables glossary and ADR writes. It is independent of interview depth.\n\nExplicit analysis-only, chat-only, or no-file instructions govern output. A request to discuss an idea is not permission to write project documents. When the user requests a spec or feature alignment artifact, write `.claude\u002Fartifacts\u002Fdesigns\u002F\u003Cfeature>.md` unless they specify another path.\n\n## Gather evidence before questions\n\nRead the supplied brief and relevant existing spec, `CONTEXT.md`, ADRs, models, APIs, tests, or similar features. Follow the repository's search conventions; inspect enough to ground the decisions, without scanning unrelated modules.\n\nDistinguish confirmed requirements, codebase facts, proposed defaults, and unresolved decisions. Do not ask the user for facts the repository can establish. Do not treat an implementation's current behavior as proof of intended behavior.\n\n## Resolve the material gaps\n\nCheck whether the intended user, desired outcome, in\u002Fout boundary, acceptance behavior, and integration surface are clear enough to write a contract. Ask the highest-impact unresolved question first, with concise context and an evidence-backed recommendation when useful. Group tightly related questions only when the answers depend on each other or the user requests a questionnaire.\n\nPay attention to domain identity: conflicting names, the same name for different entities, lifecycle transitions, ownership, and invariants. Use established project terms; surface real conflicts instead of silently renaming concepts. A stable vocabulary does not prove the feature is ready.\n\nUse qualitative, evidence-backed gaps rather than invented ambiguity percentages. Do not enforce a minimum interview length, a number of entities, or a quota of acceptance criteria. Stop questioning when the contract is sufficient, the user changes scope, or a concrete external decision blocks progress. If repeated questions produce no new information, name the blocker and preserve useful work instead of cycling.\n\nWhen the user asks to proceed, incorporate that authorization. Resolve low-impact details from existing conventions and record consequential assumptions. Do not silently decide unresolved high-impact product behavior; mark the affected scope blocked while completing independent parts.\n\n## Write the feature contract\n\nUse a stable existing slug when it identifies this feature. Otherwise choose a descriptive slug from the request; ask only when there is a real collision or ambiguous work item. Preserve existing content outside this task.\n\n```markdown\n# \u003Cfeature> Spec\n\n> Status: DRAFT | ALIGNED | IMPLEMENTED | STUCK\n> Source: \u003Crequest, document, or existing artifact>\n> Last updated: \u003CYYYY-MM-DD>\n\n## Background\n\u003CUser, problem, and intended outcome>\n\n## In scope\n\u003CBehavior included in this delivery>\n\n## Out of scope\n\u003CRelevant boundaries; say none identified when that is accurate>\n\n## Assumptions\n\u003CConsequential defaults and their basis; omit if none>\n\n## Solution\n\u003CMinimal behavior and integration sketch, not an implementation task list>\n\n## Edge cases & risks\n\u003CRelevant boundaries, failures, invariants, and mitigations>\n\n## Acceptance criteria\n- AC-1 \u003Ccondition or action> -> \u003Cobservable expected result>\n\n## Open questions\n\u003CSpecific blocker, affected scope, needed evidence or decision owner; omit if none>\n```\n\nAdd core entities, state transitions, compatibility constraints, or data contracts when they help downstream implementation. Omit interview transcripts, artificial clarity scores, and empty template sections. Preserve existing AC identifiers during revisions.\n\nStatus semantics:\n\n- `DRAFT`: proposed requirements remain subject to alignment; specify what remains unresolved.\n- `ALIGNED`: material requirements are supported by user direction or an accepted source, and no implementation-blocking question remains. Routine inferred details may be recorded as assumptions.\n- `STUCK`: a concrete unanswered decision or unavailable evidence blocks the intended scope. Identify it explicitly; do not advance affected implementation on that basis.\n- `IMPLEMENTED`: retain only when actual implementation evidence supports it; this intake skill does not implement the feature. Changed requirements invalidate that status for the affected scope.\n\n## Durable documentation\n\nOnly in documentation-authorized work outside `--spec-only`, persist reusable knowledge when it meets these gates. Follow existing project paths and format before creating new ones.\n\n- `CONTEXT.md`: stable domain terms, boundaries, aliases, and evidence-backed meanings. Update related glossary rows only. Keep task checklists, transient copy, unresolved guesses, and implementation diaries in the task artifact.\n- `docs\u002Fadr\u002F\u003Cnnnn>-\u003Cslug>.md`: an accepted decision with real tradeoffs, reuse across features\u002Fmodules, meaningful reversal cost, and a rationale future readers need. Naming choices and local implementation details do not qualify. Use the project's numbering convention; otherwise the next unused number. Record Context, Decision, Consequences, status, and date. Do not label an unconfirmed proposal Accepted.\n\nDurable notes must not conflict with the spec. A decision local to this feature belongs in its plan when implementation planning is requested.\n\n## Handoff\n\nReport the artifact path and status, material decisions, remaining blockers, and the next useful action. Mention glossary\u002FADR changes only if made. If the user requested intake only, stop after the deliverable. If their broader request already authorizes implementation, continue within that scope when requirements are sufficient; do not require a new skill invocation as a permission ceremony.\n\n## SDD Contract\n\nThe downstream anchors are `In scope`, `Out of scope`, `Assumptions`, `Open questions`, and stable `Acceptance criteria`. Existing glossary and ADR decisions also constrain implementation. Report and reconcile material spec drift before delivery instead of treating the artifact as proof that code complies.\n\n## Multi-Agent Note\n\nMain-agent-first: one agent owns user questions and contract writes. When delegation is available and authorized, independent explorers may gather bounded facts or challenge a substantial draft. Avoid duplicate interviews; do not invent independent approval from role labels. In the source repository, `docs\u002Fmulti-agent-policy.md` is optional team guidance, not a standalone dependency.\n","# Dev Grill Docs\n\nTurn the user's feature intent into a usable contract. Preserve decisions already made and ask only about gaps that change behavior, scope, acceptance, or substantial cost. This skill does not implement code or replace analysis-only requests with document work.\n\nRead [references\u002Fdev-baseline.md](references\u002Fdev-baseline.md). Project artifacts belong in the user's project, not the skill directory.\n\n## Routing and depth\n\n- Use this entry point for requirement alignment. `dev-spec` is the compatibility alias for `--spec-only`.\n- When scope is already clear and the user wants implementation steps, use `dev-plan` if available; a particular phrase such as \"写个方案\" does not override the conversation's actual intent.\n- Broken behavior belongs to `dev-fix`. Persistent visual direction belongs to `dev-design-context`.\n- `--quick` requests a compact contract and minimal questions; zero questions is correct when evidence is sufficient.\n- Default depth covers the material uncertainties. `--deep` adds scrutiny of lifecycle, invariants, compatibility, failures, and reversibility where relevant.\n- `--spec-only` disables glossary and ADR writes. It is independent of interview depth.\n\nExplicit analysis-only, chat-only, or no-file instructions govern output. A request to discuss an idea is not permission to write project documents. When the user requests a spec or feature alignment artifact, write `.claude\u002Fartifacts\u002Fdesigns\u002F\u003Cfeature>.md` unless they specify another path.\n\n## Gather evidence before questions\n\nRead the supplied brief and relevant existing spec, `CONTEXT.md`, ADRs, models, APIs, tests, or similar features. Follow the repository's search conventions; inspect enough to ground the decisions, without scanning unrelated modules.\n\nDistinguish confirmed requirements, codebase facts, proposed defaults, and unresolved decisions. Do not ask the user for facts the repository can establish. Do not treat an implementation's current behavior as proof of intended behavior.\n\n## Resolve the material gaps\n\nCheck whether the intended user, desired outcome, in\u002Fout boundary, acceptance behavior, and integration surface are clear enough to write a contract. Ask the highest-impact unresolved question first, with concise context and an evidence-backed recommendation when useful. Group tightly related questions only when the answers depend on each other or the user requests a questionnaire.\n\nPay attention to domain identity: conflicting names, the same name for different entities, lifecycle transitions, ownership, and invariants. Use established project terms; surface real conflicts instead of silently renaming concepts. A stable vocabulary does not prove the feature is ready.\n\nUse qualitative, evidence-backed gaps rather than invented ambiguity percentages. Do not enforce a minimum interview length, a number of entities, or a quota of acceptance criteria. Stop questioning when the contract is sufficient, the user changes scope, or a concrete external decision blocks progress. If repeated questions produce no new information, name the blocker and preserve useful work instead of cycling.\n\nWhen the user asks to proceed, incorporate that authorization. Resolve low-impact details from existing conventions and record consequential assumptions. Do not silently decide unresolved high-impact product behavior; mark the affected scope blocked while completing independent parts.\n\n## Write the feature contract\n\nUse a stable existing slug when it identifies this feature. Otherwise choose a descriptive slug from the request; ask only when there is a real collision or ambiguous work item. Preserve existing content outside this task.\n\n```markdown\n# \u003Cfeature> Spec\n\n> Status: DRAFT | ALIGNED | IMPLEMENTED | STUCK\n> Source: \u003Crequest, document, or existing artifact>\n> Last updated: \u003CYYYY-MM-DD>\n\n## Background\n\u003CUser, problem, and intended outcome>\n\n## In scope\n\u003CBehavior included in this delivery>\n\n## Out of scope\n\u003CRelevant boundaries; say none identified when that is accurate>\n\n## Assumptions\n\u003CConsequential defaults and their basis; omit if none>\n\n## Solution\n\u003CMinimal behavior and integration sketch, not an implementation task list>\n\n## Edge cases & risks\n\u003CRelevant boundaries, failures, invariants, and mitigations>\n\n## Acceptance criteria\n- AC-1 \u003Ccondition or action> -> \u003Cobservable expected result>\n\n## Open questions\n\u003CSpecific blocker, affected scope, needed evidence or decision owner; omit if none>\n```\n\nAdd core entities, state transitions, compatibility constraints, or data contracts when they help downstream implementation. Omit interview transcripts, artificial clarity scores, and empty template sections. Preserve existing AC identifiers during revisions.\n\nStatus semantics:\n\n- `DRAFT`: proposed requirements remain subject to alignment; specify what remains unresolved.\n- `ALIGNED`: material requirements are supported by user direction or an accepted source, and no implementation-blocking question remains. Routine inferred details may be recorded as assumptions.\n- `STUCK`: a concrete unanswered decision or unavailable evidence blocks the intended scope. Identify it explicitly; do not advance affected implementation on that basis.\n- `IMPLEMENTED`: retain only when actual implementation evidence supports it; this intake skill does not implement the feature. Changed requirements invalidate that status for the affected scope.\n\n## Durable documentation\n\nOnly in documentation-authorized work outside `--spec-only`, persist reusable knowledge when it meets these gates. Follow existing project paths and format before creating new ones.\n\n- `CONTEXT.md`: stable domain terms, boundaries, aliases, and evidence-backed meanings. Update related glossary rows only. Keep task checklists, transient copy, unresolved guesses, and implementation diaries in the task artifact.\n- `docs\u002Fadr\u002F\u003Cnnnn>-\u003Cslug>.md`: an accepted decision with real tradeoffs, reuse across features\u002Fmodules, meaningful reversal cost, and a rationale future readers need. Naming choices and local implementation details do not qualify. Use the project's numbering convention; otherwise the next unused number. Record Context, Decision, Consequences, status, and date. Do not label an unconfirmed proposal Accepted.\n\nDurable notes must not conflict with the spec. A decision local to this feature belongs in its plan when implementation planning is requested.\n\n## Handoff\n\nReport the artifact path and status, material decisions, remaining blockers, and the next useful action. Mention glossary\u002FADR changes only if made. If the user requested intake only, stop after the deliverable. If their broader request already authorizes implementation, continue within that scope when requirements are sufficient; do not require a new skill invocation as a permission ceremony.\n\n## SDD Contract\n\nThe downstream anchors are `In scope`, `Out of scope`, `Assumptions`, `Open questions`, and stable `Acceptance criteria`. Existing glossary and ADR decisions also constrain implementation. Report and reconcile material spec drift before delivery instead of treating the artifact as proof that code complies.\n\n## Multi-Agent Note\n\nMain-agent-first: one agent owns user questions and contract writes. When delegation is available and authorized, independent explorers may gather bounded facts or challenge a substantial draft. Avoid duplicate interviews; do not invent independent approval from role labels. In the source repository, `docs\u002Fmulti-agent-policy.md` is optional team guidance, not a standalone dependency.\n",{"name":5,"description":7},"main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FJason-chen-coder\u002Fdev-skills\u002Fskills\u002Fdev-grill-docs",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 dev-grill-docs",{"tool":61,"command":62},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill dev-grill-docs",{"tool":64,"command":65},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill dev-grill-docs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJason-chen-coder\u002Fdev-skills\u002Fskills\u002Fdev-grill-docs\u002FSKILL.md",true,[69],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fdev-baseline.md","REFERENCE","参考文档",3571,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJason-chen-coder\u002Fdev-skills\u002Fskills\u002Fdev-grill-docs\u002Freferences\u002Fdev-baseline.md",[76,86,94,102,110,118],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":81,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":85},"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":85},"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":98,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":85},"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":85},"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":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":85},"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":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":122,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":85},"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",[],[]]