[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MNZWHAWQ29B182FP073Y8T":3,"skill-same:01M6MNZWHAWQ29B182FP073Y8T":81},{"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":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":62,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6MNZWHAWQ29B182FP073Y8T","clean-room-loop",null,"Front door for running the clean-room unattended loop as a Claude Code dynamic WORKFLOW using in-session subagents, so it never spends `claude -p` API tokens. Use when the user wants to run a clean-room \u002F reverse-engineering \u002F source-to-clean-implementation task hands-off but without paying per-token for `clean-room-skill run`, or says \"clean-room as a workflow\", \"unattended clean-room without API cost\", \"\u002Fclean-room-loop\". Runs a short discussion (authorization, end goal, target stack, policies, source roots, output roots, iterations) then launches the `clean-room-loop` workflow with the answers. NOT the enforced OS-level wall - that is `clean-room-skill run --agent-runtime claude`.","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\u002Fwhit3rabbit\u002Fclean-room-skill\u002Fskills\u002Fclean-room-loop\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],"clean room loop","loop","clean room","clean","max","when","unattended","source","os","end","token","but","workflow","goal","never","subagents","short","stack","api","reverse-engineering","code","run","2026-11-10 10:12:30",false,"---\nname: clean-room-loop\ndescription: Front door for running the clean-room unattended loop as a Claude Code dynamic WORKFLOW using in-session subagents, so it never spends `claude -p` API tokens. Use when the user wants to run a clean-room \u002F reverse-engineering \u002F source-to-clean-implementation task hands-off but without paying per-token for `clean-room-skill run`, or says \"clean-room as a workflow\", \"unattended clean-room without API cost\", \"\u002Fclean-room-loop\". Runs a short discussion (authorization, end goal, target stack, policies, source roots, output roots, iterations) then launches the `clean-room-loop` workflow with the answers. NOT the enforced OS-level wall - that is `clean-room-skill run --agent-runtime claude`.\nargument-hint: [end goal, authorized source roots, target stack, output roots, optional max iterations]\n---\n\n# Clean-room loop (discussion -> clean-room-loop workflow launch)\n\nConversational front door to the `clean-room-loop` dynamic workflow (`.claude\u002Fworkflows\u002Fclean-room-loop.js`).\nThe workflow runs in the background with no way to ask anything mid-run, so the discussion happens\nHERE; answers pass as `args`.\n\n**Claude Code only.** Dynamic workflows are a Claude Code feature. In Pi\u002FCodex\u002FOpenCode the\n`Workflow()` call will not exist - see the Fallback step. Only this workflow shortcut is Claude\nCode specific; the underlying clean-room skills (`\u002Fclean-room:unattended`, `clean-room-skill run`)\nwork on every supported runtime.\n\n**Installed project-local.** The workflow script ships to project-local `.claude\u002Fworkflows\u002F`\n(not global). `Workflow({ name })` discovers it from the current project's `.claude\u002Fworkflows\u002F`\n(or `~\u002F.claude\u002Fworkflows\u002F` if a personal copy exists). If the current project does not have it,\ninitialize a project-local install before launching - see Step 3.\n\n## What this is (and is NOT)\n\n- It drives the six clean-room roles with the workflow's OWN `agent()` subagents (in-session,\n  subscription, **no `claude -p`**), gating every wall crossing with the real\n  `clean-room-skill artifact validate --role` leakage + schema hooks.\n- It is a **cost-free path with context-level separation**, NOT the OS-enforced wall. A workflow\n  cannot set `CLEAN_ROOM_*` env or install hooks, so nothing stops a clean subagent from reading\n  source off disk except the neutral-artifact discipline + the leakage gate. If the user needs the\n  enforced boundary, use `clean-room-skill run --agent-runtime claude` instead (that path costs API\n  tokens by design).\n- The workflow READS the authorized source and WRITES clean specs, plans, code, and reports under the\n  external artifact roots. Confirm authorization and paths before launching.\n\n## Steps\n\n1. **Get the brief.** Take the end goal from the invocation if present. If missing, ask what they are\n   reimplementing and why they are authorized to.\n\n2. **Run the discussion.** Collect the fields below with `AskUserQuestion` (batch - max 4 per call,\n   ~3 calls); ask free-text ones plainly. Offer defaults so a terse brief is still runnable. Do NOT\n   infer the end goal or target stack from source - clean-room forbids it; if unknown, ask.\n\n   Batch A (goal + stack):\n   - **endGoal** (free-text): what the clean implementation must do; its success definition.\n   - **targetStack**: language \u002F runtime \u002F framework \u002F packageManager \u002F testFramework. Pass as a nested object.\n   - **compatibilityPolicy**: public-behavior-and-API-names only (default) or public-behavior-only.\n     Private structure\u002Fcomments\u002Finternal names are NEVER mirrored.\n   - **featurePolicy** (skippable): features to preserve \u002F remove \u002F add \u002F non-goals.\n\n   Batch B (policy):\n   - **licensePolicy**: destination license + any blocked dep licenses.\n   - **dependencyPolicy**: allow new deps? prefer stdlib? require approval for native deps.\n   - **codeHygienePolicy** (skippable): max lines per code\u002Ftest file, max files per iteration.\n   - **schemaProfile**: speckit-feature-folder (default) \u002F openspec-delta \u002F gsd-planning-package \u002F kiro-spec-folder.\n\n   Batch C (roots + bounds - all safety-relevant):\n   - **sourceRoots** (REQUIRED): absolute path(s) to the authorized source. No source = cannot run.\n   - **artifactBase**: where run artifacts live (default `~\u002FDocuments\u002FCleanRoom`). Must be OUTSIDE the\n     source tree and neutral-named.\n   - **project \u002F taskId** (skippable): neutral names; the CLI generates neutral ones if omitted.\n   - **maxIterations**: finite inner-loop cap (default 3).\n\n3. **Ensure the workflow is installed project-local, preview, STOP for confirmation, then launch.**\n   First confirm this project has the workflow. Dynamic workflows load from project-local\n   `.claude\u002Fworkflows\u002F`. If `.claude\u002Fworkflows\u002Fclean-room-loop.js` is absent in the current project\n   (and no `~\u002F.claude\u002Fworkflows\u002Fclean-room-loop.js` personal copy exists), initialize a project-local\n   install before launching:\n\n   ```bash\n   clean-room-skill --claude --local --yes\n   # or, without a global CLI:\n   npx clean-room-skill@latest --claude --local --yes\n   ```\n\n   That writes `clean-room-loop.js` into the current project's `.claude\u002Fworkflows\u002F` so\n   `Workflow({ name })` can discover it. Then show a compact preview of the `args`\n   (at least `endGoal`, `sourceRoots`, `artifactBase`, `targetStack`, `maxIterations`) so a wrong\n   source path or output root is caught BEFORE a filesystem-writing, source-reading run starts. STOP\n   and wait for an explicit \"yes\". Do NOT call `Workflow` in the same turn as the preview. Only after\n   the user confirms:\n\n   ```\n   Workflow({ name: \"clean-room-loop\", args: {\n     endGoal,\n     targetStack,                 \u002F\u002F { language, runtime, framework, packageManager, testFramework }\n     compatibilityPolicy, featurePolicy,\n     licensePolicy, dependencyPolicy, codeHygienePolicy,\n     sourceRoots,                 \u002F\u002F array of absolute paths (REQUIRED)\n     artifactBase, project, taskId,\n     schemaProfile, maxIterations,\n     specSliceRef,                \u002F\u002F optional\n   }})\n   ```\n\n   Pass only what was gathered; omit the rest (the workflow defaults them).\n\n4. **Fallback.** If `Workflow()` errors or is unavailable (non-Claude host, or dynamic workflows\n   disabled), do NOT hand-run the roles here. Route the user to `\u002Fclean-room:unattended`, which\n   prefers fresh-context in-harness roles on that harness and drops to the durable runner only as a\n   last resort: `clean-room-skill run --agent-commands \u003Cadapter>` on Codex\u002FPi\u002Fother runtimes (spawns\n   the harness CLI, `shell: false`), or `--agent-runtime claude` (spawns `claude -p`, Claude only,\n   per-token) last. Use the runner only once a runner-ready manifest with `loop_context` exists.\n\n5. **Hand back** the workflow's result (the terminal `clean-room-result.json` result string, task\n   root, and clean\u002Fimplementation roots).\n","# Clean-room loop (discussion -> clean-room-loop workflow launch)\n\nConversational front door to the `clean-room-loop` dynamic workflow (`.claude\u002Fworkflows\u002Fclean-room-loop.js`).\nThe workflow runs in the background with no way to ask anything mid-run, so the discussion happens\nHERE; answers pass as `args`.\n\n**Claude Code only.** Dynamic workflows are a Claude Code feature. In Pi\u002FCodex\u002FOpenCode the\n`Workflow()` call will not exist - see the Fallback step. Only this workflow shortcut is Claude\nCode specific; the underlying clean-room skills (`\u002Fclean-room:unattended`, `clean-room-skill run`)\nwork on every supported runtime.\n\n**Installed project-local.** The workflow script ships to project-local `.claude\u002Fworkflows\u002F`\n(not global). `Workflow({ name })` discovers it from the current project's `.claude\u002Fworkflows\u002F`\n(or `~\u002F.claude\u002Fworkflows\u002F` if a personal copy exists). If the current project does not have it,\ninitialize a project-local install before launching - see Step 3.\n\n## What this is (and is NOT)\n\n- It drives the six clean-room roles with the workflow's OWN `agent()` subagents (in-session,\n  subscription, **no `claude -p`**), gating every wall crossing with the real\n  `clean-room-skill artifact validate --role` leakage + schema hooks.\n- It is a **cost-free path with context-level separation**, NOT the OS-enforced wall. A workflow\n  cannot set `CLEAN_ROOM_*` env or install hooks, so nothing stops a clean subagent from reading\n  source off disk except the neutral-artifact discipline + the leakage gate. If the user needs the\n  enforced boundary, use `clean-room-skill run --agent-runtime claude` instead (that path costs API\n  tokens by design).\n- The workflow READS the authorized source and WRITES clean specs, plans, code, and reports under the\n  external artifact roots. Confirm authorization and paths before launching.\n\n## Steps\n\n1. **Get the brief.** Take the end goal from the invocation if present. If missing, ask what they are\n   reimplementing and why they are authorized to.\n\n2. **Run the discussion.** Collect the fields below with `AskUserQuestion` (batch - max 4 per call,\n   ~3 calls); ask free-text ones plainly. Offer defaults so a terse brief is still runnable. Do NOT\n   infer the end goal or target stack from source - clean-room forbids it; if unknown, ask.\n\n   Batch A (goal + stack):\n   - **endGoal** (free-text): what the clean implementation must do; its success definition.\n   - **targetStack**: language \u002F runtime \u002F framework \u002F packageManager \u002F testFramework. Pass as a nested object.\n   - **compatibilityPolicy**: public-behavior-and-API-names only (default) or public-behavior-only.\n     Private structure\u002Fcomments\u002Finternal names are NEVER mirrored.\n   - **featurePolicy** (skippable): features to preserve \u002F remove \u002F add \u002F non-goals.\n\n   Batch B (policy):\n   - **licensePolicy**: destination license + any blocked dep licenses.\n   - **dependencyPolicy**: allow new deps? prefer stdlib? require approval for native deps.\n   - **codeHygienePolicy** (skippable): max lines per code\u002Ftest file, max files per iteration.\n   - **schemaProfile**: speckit-feature-folder (default) \u002F openspec-delta \u002F gsd-planning-package \u002F kiro-spec-folder.\n\n   Batch C (roots + bounds - all safety-relevant):\n   - **sourceRoots** (REQUIRED): absolute path(s) to the authorized source. No source = cannot run.\n   - **artifactBase**: where run artifacts live (default `~\u002FDocuments\u002FCleanRoom`). Must be OUTSIDE the\n     source tree and neutral-named.\n   - **project \u002F taskId** (skippable): neutral names; the CLI generates neutral ones if omitted.\n   - **maxIterations**: finite inner-loop cap (default 3).\n\n3. **Ensure the workflow is installed project-local, preview, STOP for confirmation, then launch.**\n   First confirm this project has the workflow. Dynamic workflows load from project-local\n   `.claude\u002Fworkflows\u002F`. If `.claude\u002Fworkflows\u002Fclean-room-loop.js` is absent in the current project\n   (and no `~\u002F.claude\u002Fworkflows\u002Fclean-room-loop.js` personal copy exists), initialize a project-local\n   install before launching:\n\n   ```bash\n   clean-room-skill --claude --local --yes\n   # or, without a global CLI:\n   npx clean-room-skill@latest --claude --local --yes\n   ```\n\n   That writes `clean-room-loop.js` into the current project's `.claude\u002Fworkflows\u002F` so\n   `Workflow({ name })` can discover it. Then show a compact preview of the `args`\n   (at least `endGoal`, `sourceRoots`, `artifactBase`, `targetStack`, `maxIterations`) so a wrong\n   source path or output root is caught BEFORE a filesystem-writing, source-reading run starts. STOP\n   and wait for an explicit \"yes\". Do NOT call `Workflow` in the same turn as the preview. Only after\n   the user confirms:\n\n   ```\n   Workflow({ name: \"clean-room-loop\", args: {\n     endGoal,\n     targetStack,                 \u002F\u002F { language, runtime, framework, packageManager, testFramework }\n     compatibilityPolicy, featurePolicy,\n     licensePolicy, dependencyPolicy, codeHygienePolicy,\n     sourceRoots,                 \u002F\u002F array of absolute paths (REQUIRED)\n     artifactBase, project, taskId,\n     schemaProfile, maxIterations,\n     specSliceRef,                \u002F\u002F optional\n   }})\n   ```\n\n   Pass only what was gathered; omit the rest (the workflow defaults them).\n\n4. **Fallback.** If `Workflow()` errors or is unavailable (non-Claude host, or dynamic workflows\n   disabled), do NOT hand-run the roles here. Route the user to `\u002Fclean-room:unattended`, which\n   prefers fresh-context in-harness roles on that harness and drops to the durable runner only as a\n   last resort: `clean-room-skill run --agent-commands \u003Cadapter>` on Codex\u002FPi\u002Fother runtimes (spawns\n   the harness CLI, `shell: false`), or `--agent-runtime claude` (spawns `claude -p`, Claude only,\n   per-token) last. Use the runner only once a runner-ready manifest with `loop_context` exists.\n\n5. **Hand back** the workflow's result (the terminal `clean-room-result.json` result string, task\n   root, and clean\u002Fimplementation roots).\n",{"name":5,"description":7,"argument-hint":51},[52,53,54,55,56],"end goal","authorized source roots","target stack","output roots","optional max iterations","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fwhit3rabbit\u002Fclean-room-skill\u002Fskills\u002Fclean-room-loop",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":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill clean-room-loop",{"tool":73,"command":74},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill clean-room-loop",{"tool":76,"command":77},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill clean-room-loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fwhit3rabbit\u002Fclean-room-skill\u002Fskills\u002Fclean-room-loop\u002FSKILL.md",true,[],[82,92,100,108,116,124],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":91},"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":91},"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":91},"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":91},"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":91},"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":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":128,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":91},"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",[],[]]