[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MP72DS82BVZE0AXVXZJ5RQ":3,"skill-same:01M6MP72DS82BVZE0AXVXZJ5RQ":62},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M6MP72DS82BVZE0AXVXZJ5RQ","deepdive",null,"Full specialist analysis via parallel agent dispatch. Researcher, Architect, and PM produce a prioritized report of what to build next (30-60s).","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\u002Fyimwoo\u002Fcodex-agenteam\u002Fskills\u002Fdeepdive\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32],"report","produce","analysis","architect","parallel","researcher","dispatch","parallel agent dispatch","build","next","pm","full","via","specialist","2026-11-10 10:12:30",false,"---\nname: deepdive\ndescription: Full specialist analysis via parallel agent dispatch. Researcher, Architect, and PM produce a prioritized report of what to build next (30-60s).\n---\n\n# AgenTeam Deepdive\n\nRun a full specialist analysis by dispatching three roles in parallel.\nUnlike the standup skill (which reads state locally), deepdive launches\nCodex subagents to investigate external signals, internal code health,\nand strategic priorities. Expect 30-60 seconds for completion.\n\n## Process\n\n### 1. Auto-Init Guard\n\nCheck for `.agenteam\u002Fconfig.yaml`, `.agenteam.team\u002Fconfig.yaml`, or legacy\n`agenteam.yaml` in the project root. If all are missing:\n- Create config dir: `mkdir -p .agenteam`\n- Copy the template: `cp \u003Cplugin-dir>\u002Ftemplates\u002Fagenteam.yaml.template .agenteam\u002Fconfig.yaml`\n- Set the team name to the project directory name\n- Generate agents: `python3 \u003Cruntime>\u002Fagenteam_rt.py generate`\n- Tell the user: \"AgenTeam auto-initialized with default roles. Edit `.agenteam\u002Fconfig.yaml` to customize.\"\n\n### 2. Gather State with Dispatch Flag\n\nCall the runtime with the `--dispatch` flag to get state and dispatch\nplans for the three specialist roles:\n\n```bash\npython3 \u003Cruntime>\u002Fagenteam_rt.py standup --dispatch\n```\n\nCapture the JSON output. Expected fields (same as standup, plus\ndispatch info):\n- `health` -- `on-track`, `at-risk`, `off-track`, or `no-active-run`\n- `run_id` -- current run identifier (may be null)\n- `task` -- task description\n- `stages` -- stage statuses\n- `artifact_paths` -- map of role name to artifact directory\n- `output_path` -- where to write the final report (e.g., `docs\u002Fmeetings\u002F\u003Ctimestamp>-deepdive.md`)\n- `dispatch` -- list of `{role, agent}` objects for the three specialist roles (researcher, architect, pm)\n\nCreate a durable checkpoint at `.agenteam\u002Fdeepdive\u002F\u003Crun_id>.json` before\ndispatch. Record `max_elapsed_minutes` (default 60), `max_agents` (default 2\nconcurrent specialists), each role's attempt\u002Fthread ID, last heartbeat, output\nartifact, and stop reason. On restart, validate completed artifacts and resume\nonly missing or interrupted roles; never repeat a completed specialist solely\nbecause the controller restarted.\n\n### 3. Dispatch Specialist Agents in Parallel\n\nLaunch three Codex subagents in parallel. Each role has a focused\nmandate:\n\n#### Researcher (`@Researcher`)\n\nAgent file: `.codex\u002Fagents\u002Fresearcher.toml`\n\nPrompt the researcher with:\n- Read all files in `docs\u002Fresearch\u002F` and assess staleness (anything\n  older than 2 weeks is potentially outdated)\n- Search the web and GitHub for new trends, tools, and community\n  discussions relevant to the project\n- Check for competitor moves, new releases in the dependency ecosystem,\n  and community feedback on similar tools\n- Produce a structured report of external signals\n\nExpected output format:\n```\n## External Signals\n\n### Trends\n- [signal] description and relevance to this project\n\n### Ecosystem\n- [dependency\u002Ftool] notable updates or risks\n\n### Community\n- [source] feedback, requests, or discussions relevant to our work\n```\n\n#### Architect (`@Architect`)\n\nAgent file: `.codex\u002Fagents\u002Farchitect.toml`\n\nPrompt the architect with:\n- Read all files in `docs\u002Fdesigns\u002F` and compare against the current\n  codebase -- identify design drift (where the implementation diverges\n  from the documented design)\n- Check for tech debt signals: duplicated logic, overly complex\n  modules, missing error handling, dead code\n- Review dependency health: outdated packages, known vulnerabilities,\n  abandoned upstream projects\n- Produce a structured report of internal health\n\nExpected output format:\n```\n## Internal Health\n\n### Design Drift\n- [area] how implementation differs from design doc\n\n### Tech Debt\n- [area] description and severity (low\u002Fmedium\u002Fhigh)\n\n### Dependencies\n- [package] status and risk level\n```\n\n#### PM (`@Pm`)\n\nAgent file: `.codex\u002Fagents\u002Fpm.toml`\n\nPrompt the PM with:\n- Wait for and read the Researcher and Architect outputs (passed as\n  context once they complete)\n- Read `docs\u002Fstrategies\u002F` for current roadmap and strategic priorities\n- Cross-reference external signals (Researcher) with internal health\n  (Architect) and existing strategy\n- Produce a prioritized list of recommendations for what to build next,\n  with rationale for each item\n\nExpected output format:\n```\n## Recommendations\n\n1. **[title]** -- rationale based on research + architecture analysis\n   Priority: [high\u002Fmedium\u002Flow]\n   Effort: [small\u002Fmedium\u002Flarge]\n\n2. **[title]** -- rationale\n   Priority: ...\n   Effort: ...\n```\n\n**Dispatch order:** Researcher and Architect run in parallel. PM runs\nafter both complete (it needs their outputs as input).\n\n### 4. Collect Outputs\n\nGather the outputs from all three subagents:\n- Researcher report (external signals)\n- Architect report (internal health)\n- PM report (prioritized recommendations)\n\nIf any agent fails, include an error note in that section and continue\nwith the available outputs.\n\nUpdate the checkpoint and emit a heartbeat whenever a specialist reports\nprogress. Enforce the elapsed and agent budgets. A timed-out specialist is\nrecorded as interrupted; if it has a resumable thread, resume it before\nconsidering a fresh attempt. Synthesis is its own checkpoint and starts only\nafter the Researcher\u002FArchitect terminal states are durable.\n\n### 5. Synthesize Deepdive Report\n\nCombine all three outputs into a single report using this format:\n\n```\n# AgenTeam Deepdive: \u003Cproject-name>\nDate: \u003CYYYY-MM-DD HH:MM>\n\n## Health: [ON TRACK | AT RISK | OFF TRACK]\n\n## External Signals (Researcher)\n- trending approaches, competitor moves, community feedback\n\n## Internal Health (Architect)\n- design drift, tech debt, dependency risks\n\n## Recommendations (PM)\n- prioritized list of what to build next, with rationale\n\n## Action Items\n- specific next steps with owners\n```\n\nRules for the report:\n- **Health** is derived from the runtime JSON, same as the standup\n  skill.\n- **External Signals** comes directly from the Researcher output.\n  Trim to the most actionable items (no more than 5-7 bullets).\n- **Internal Health** comes from the Architect output. Group by\n  severity, high-severity items first.\n- **Recommendations** comes from the PM output. Keep prioritization\n  and effort estimates. Limit to the top 5-7 items.\n- **Action Items** is a synthesis step you perform: extract the most\n  concrete next steps from all three reports, assign an owner (role\n  name) to each, and list them in priority order.\n- Omit any section where the corresponding agent produced no output\n  (e.g., if the Researcher found nothing notable, omit External\n  Signals).\n\n### 6. Write Report\n\nWrite the synthesized report to the `output_path` from the runtime JSON\n(typically `docs\u002Fmeetings\u002F\u003Ctimestamp>-deepdive.md`):\n\n```bash\nmkdir -p \"$(dirname \"$output_path\")\"\n```\n\nWrite the report content to that file.\n\n### 7. Display to User\n\nShow the full deepdive report to the user in the conversation. Include\na timing note:\n\n```\nAgenTeam Deepdive: \u003Cproject-name>\nCompleted in ~\u003Celapsed>s (3 specialists dispatched)\n```\n\n## Runtime Path Resolution\n\nResolve the AgenTeam runtime:\n1. If running from the plugin directory: `.\u002Fruntime\u002Fagenteam_rt.py`\n2. If installed as a Codex plugin: `\u003Cplugin-install-path>\u002Fruntime\u002Fagenteam_rt.py`\n\n## Error Handling\n\n- If a subagent fails, include a note in the corresponding section:\n  \"[role] analysis unavailable -- [error reason]\"\n- If the runtime command fails, fall back to a best-effort report\n  using direct file reads (same approach as the standup skill)\n- Never let one agent's failure block the entire report\n\n## Performance Target\n\nFast runs may finish in 30-60 seconds, but correctness does not depend on that\nestimate. The durable `max_elapsed_minutes` budget and heartbeat\u002Fcheckpoint\nstate govern long-running analysis. Researcher and Architect run in parallel;\nPM starts after both terminal outputs are checkpointed.\n","# AgenTeam Deepdive\n\nRun a full specialist analysis by dispatching three roles in parallel.\nUnlike the standup skill (which reads state locally), deepdive launches\nCodex subagents to investigate external signals, internal code health,\nand strategic priorities. Expect 30-60 seconds for completion.\n\n## Process\n\n### 1. Auto-Init Guard\n\nCheck for `.agenteam\u002Fconfig.yaml`, `.agenteam.team\u002Fconfig.yaml`, or legacy\n`agenteam.yaml` in the project root. If all are missing:\n- Create config dir: `mkdir -p .agenteam`\n- Copy the template: `cp \u003Cplugin-dir>\u002Ftemplates\u002Fagenteam.yaml.template .agenteam\u002Fconfig.yaml`\n- Set the team name to the project directory name\n- Generate agents: `python3 \u003Cruntime>\u002Fagenteam_rt.py generate`\n- Tell the user: \"AgenTeam auto-initialized with default roles. Edit `.agenteam\u002Fconfig.yaml` to customize.\"\n\n### 2. Gather State with Dispatch Flag\n\nCall the runtime with the `--dispatch` flag to get state and dispatch\nplans for the three specialist roles:\n\n```bash\npython3 \u003Cruntime>\u002Fagenteam_rt.py standup --dispatch\n```\n\nCapture the JSON output. Expected fields (same as standup, plus\ndispatch info):\n- `health` -- `on-track`, `at-risk`, `off-track`, or `no-active-run`\n- `run_id` -- current run identifier (may be null)\n- `task` -- task description\n- `stages` -- stage statuses\n- `artifact_paths` -- map of role name to artifact directory\n- `output_path` -- where to write the final report (e.g., `docs\u002Fmeetings\u002F\u003Ctimestamp>-deepdive.md`)\n- `dispatch` -- list of `{role, agent}` objects for the three specialist roles (researcher, architect, pm)\n\nCreate a durable checkpoint at `.agenteam\u002Fdeepdive\u002F\u003Crun_id>.json` before\ndispatch. Record `max_elapsed_minutes` (default 60), `max_agents` (default 2\nconcurrent specialists), each role's attempt\u002Fthread ID, last heartbeat, output\nartifact, and stop reason. On restart, validate completed artifacts and resume\nonly missing or interrupted roles; never repeat a completed specialist solely\nbecause the controller restarted.\n\n### 3. Dispatch Specialist Agents in Parallel\n\nLaunch three Codex subagents in parallel. Each role has a focused\nmandate:\n\n#### Researcher (`@Researcher`)\n\nAgent file: `.codex\u002Fagents\u002Fresearcher.toml`\n\nPrompt the researcher with:\n- Read all files in `docs\u002Fresearch\u002F` and assess staleness (anything\n  older than 2 weeks is potentially outdated)\n- Search the web and GitHub for new trends, tools, and community\n  discussions relevant to the project\n- Check for competitor moves, new releases in the dependency ecosystem,\n  and community feedback on similar tools\n- Produce a structured report of external signals\n\nExpected output format:\n```\n## External Signals\n\n### Trends\n- [signal] description and relevance to this project\n\n### Ecosystem\n- [dependency\u002Ftool] notable updates or risks\n\n### Community\n- [source] feedback, requests, or discussions relevant to our work\n```\n\n#### Architect (`@Architect`)\n\nAgent file: `.codex\u002Fagents\u002Farchitect.toml`\n\nPrompt the architect with:\n- Read all files in `docs\u002Fdesigns\u002F` and compare against the current\n  codebase -- identify design drift (where the implementation diverges\n  from the documented design)\n- Check for tech debt signals: duplicated logic, overly complex\n  modules, missing error handling, dead code\n- Review dependency health: outdated packages, known vulnerabilities,\n  abandoned upstream projects\n- Produce a structured report of internal health\n\nExpected output format:\n```\n## Internal Health\n\n### Design Drift\n- [area] how implementation differs from design doc\n\n### Tech Debt\n- [area] description and severity (low\u002Fmedium\u002Fhigh)\n\n### Dependencies\n- [package] status and risk level\n```\n\n#### PM (`@Pm`)\n\nAgent file: `.codex\u002Fagents\u002Fpm.toml`\n\nPrompt the PM with:\n- Wait for and read the Researcher and Architect outputs (passed as\n  context once they complete)\n- Read `docs\u002Fstrategies\u002F` for current roadmap and strategic priorities\n- Cross-reference external signals (Researcher) with internal health\n  (Architect) and existing strategy\n- Produce a prioritized list of recommendations for what to build next,\n  with rationale for each item\n\nExpected output format:\n```\n## Recommendations\n\n1. **[title]** -- rationale based on research + architecture analysis\n   Priority: [high\u002Fmedium\u002Flow]\n   Effort: [small\u002Fmedium\u002Flarge]\n\n2. **[title]** -- rationale\n   Priority: ...\n   Effort: ...\n```\n\n**Dispatch order:** Researcher and Architect run in parallel. PM runs\nafter both complete (it needs their outputs as input).\n\n### 4. Collect Outputs\n\nGather the outputs from all three subagents:\n- Researcher report (external signals)\n- Architect report (internal health)\n- PM report (prioritized recommendations)\n\nIf any agent fails, include an error note in that section and continue\nwith the available outputs.\n\nUpdate the checkpoint and emit a heartbeat whenever a specialist reports\nprogress. Enforce the elapsed and agent budgets. A timed-out specialist is\nrecorded as interrupted; if it has a resumable thread, resume it before\nconsidering a fresh attempt. Synthesis is its own checkpoint and starts only\nafter the Researcher\u002FArchitect terminal states are durable.\n\n### 5. Synthesize Deepdive Report\n\nCombine all three outputs into a single report using this format:\n\n```\n# AgenTeam Deepdive: \u003Cproject-name>\nDate: \u003CYYYY-MM-DD HH:MM>\n\n## Health: [ON TRACK | AT RISK | OFF TRACK]\n\n## External Signals (Researcher)\n- trending approaches, competitor moves, community feedback\n\n## Internal Health (Architect)\n- design drift, tech debt, dependency risks\n\n## Recommendations (PM)\n- prioritized list of what to build next, with rationale\n\n## Action Items\n- specific next steps with owners\n```\n\nRules for the report:\n- **Health** is derived from the runtime JSON, same as the standup\n  skill.\n- **External Signals** comes directly from the Researcher output.\n  Trim to the most actionable items (no more than 5-7 bullets).\n- **Internal Health** comes from the Architect output. Group by\n  severity, high-severity items first.\n- **Recommendations** comes from the PM output. Keep prioritization\n  and effort estimates. Limit to the top 5-7 items.\n- **Action Items** is a synthesis step you perform: extract the most\n  concrete next steps from all three reports, assign an owner (role\n  name) to each, and list them in priority order.\n- Omit any section where the corresponding agent produced no output\n  (e.g., if the Researcher found nothing notable, omit External\n  Signals).\n\n### 6. Write Report\n\nWrite the synthesized report to the `output_path` from the runtime JSON\n(typically `docs\u002Fmeetings\u002F\u003Ctimestamp>-deepdive.md`):\n\n```bash\nmkdir -p \"$(dirname \"$output_path\")\"\n```\n\nWrite the report content to that file.\n\n### 7. Display to User\n\nShow the full deepdive report to the user in the conversation. Include\na timing note:\n\n```\nAgenTeam Deepdive: \u003Cproject-name>\nCompleted in ~\u003Celapsed>s (3 specialists dispatched)\n```\n\n## Runtime Path Resolution\n\nResolve the AgenTeam runtime:\n1. If running from the plugin directory: `.\u002Fruntime\u002Fagenteam_rt.py`\n2. If installed as a Codex plugin: `\u003Cplugin-install-path>\u002Fruntime\u002Fagenteam_rt.py`\n\n## Error Handling\n\n- If a subagent fails, include a note in the corresponding section:\n  \"[role] analysis unavailable -- [error reason]\"\n- If the runtime command fails, fall back to a best-effort report\n  using direct file reads (same approach as the standup skill)\n- Never let one agent's failure block the entire report\n\n## Performance Target\n\nFast runs may finish in 30-60 seconds, but correctness does not depend on that\nestimate. The durable `max_elapsed_minutes` budget and heartbeat\u002Fcheckpoint\nstate govern long-running analysis. Researcher and Architect run in parallel;\nPM starts after both terminal outputs are checkpointed.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fyimwoo\u002Fcodex-agenteam\u002Fskills\u002Fdeepdive",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":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill deepdive",{"tool":54,"command":55},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill deepdive",{"tool":57,"command":58},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill deepdive","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyimwoo\u002Fcodex-agenteam\u002Fskills\u002Fdeepdive\u002FSKILL.md",true,[],[63,73,81,89,97,105],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":72},"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":72},"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":72},"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":72},"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":72},"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":72},"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",[],[]]