[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MP6X9BZKRK5CT0N71051RD":3,"skill-same:01M6MP6X9BZKRK5CT0N71051RD":59},{"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":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M6MP6X9BZKRK5CT0N71051RD","ci-repair",null,"Fix CI failures by fetching GitHub Actions logs, dispatching dev to fix, verifying locally, and pushing.","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\u002Fci-repair\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29],"ci","repair","ci repair","github","fix ci failures","fix ci","dev","logs","actions","github actions","fix","2026-11-10 10:12:30",false,"---\nname: ci-repair\ndescription: Fix CI failures by fetching GitHub Actions logs, dispatching dev to fix, verifying locally, and pushing.\n---\n\n# AgenTeam CI Repair\n\nFix a CI failure on a pull request. Fetches the failure context from\nGitHub Actions, dispatches the dev role with bounded logs, verifies\nthe fix locally, and pushes only if verification passes.\n\nGitHub Actions only. The workflow is a bounded, resumable\nmonitor → diagnose → repair → verify loop.\n\n## Loop Contract\n\n- Defaults: `max_repair_cycles: 3`, `max_elapsed_minutes: 90`, and a\n  five-minute CI polling interval. User-supplied lower budgets win.\n- Persist every cycle in `.agenteam\u002Fci-repair\u002Fpr-\u003Cpr_number>.json`, keyed by\n  `head_sha`. Record the run ID, failed jobs, repair attempt, local verification,\n  pushed SHA, last heartbeat, and stop reason.\n- Emit a heartbeat while waiting for a role or CI. If the host cannot remain\n  active, schedule a follow-up\u002Fautomation and stop cleanly instead of holding a\n  silent blocking wait.\n- Before replaying a repair after restart, compare the checkpoint head SHA and\n  current PR head. Never repeat a completed repair for the same SHA.\n- Stop explicitly on success, exhausted cycle\u002Felapsed budget, changed PR head,\n  unavailable evidence, or required human approval.\n\n## Process\n\n### 1. Accept Input\n\nGet the PR reference from the user:\n- PR number: `$ateam:ci-repair #42`\n- Branch name: `$ateam:ci-repair feature\u002Fadd-auth`\n- Nothing: use the current branch\n\n### 2. Resolve PR\n\nResolve the input to a canonical tuple: `pr_number`, `pr_url`,\n`pr_branch`, `head_sha`.\n\n**If PR number given:**\n```bash\ngh pr view \u003Cnumber> --json number,url,headRefName,headRefOid\n```\n\n**If branch given or current branch:**\n```bash\nBRANCH=$(git rev-parse --abbrev-ref HEAD)  # if no input\ngh pr list --head \u003Cbranch> --json number,url,headRefName,headRefOid --limit 1\n```\n\nIf no PR found: \"No PR found for branch `\u003Cbranch>`. Push and create\na PR first, then retry.\" Stop.\n\nExtract:\n- `pr_number` from `number`\n- `pr_url` from `url`\n- `pr_branch` from `headRefName`\n- `head_sha` from `headRefOid`\n\n### 3. Check CI Status\n\nGet the latest CI run for the PR's current head commit:\n\n```bash\ngh run list --commit \u003Chead_sha> --limit 5 \\\n  --json status,conclusion,databaseId,name,createdAt\n```\n\nCheck the **latest run for this exact commit**:\n\n- **`failure`** → proceed to fetch context (step 4)\n- **`success`** → \"CI is passing on the current head commit. No\n  repair needed.\" Stop.\n- **`in_progress`** or **`queued`** → Persist the run ID and heartbeat, then\n  monitor it within the elapsed budget. Poll no more frequently than the\n  configured interval. If this invocation cannot keep monitoring, arrange a\n  follow-up and stop with reason `ci_wait_scheduled`.\n- **No runs found** → \"No CI runs found for commit `\u003Chead_sha>`.\n  Push or re-run CI, then retry.\" Stop.\n\n### 4. Fetch Failure Context\n\nGet structural info (which jobs\u002Fsteps failed):\n\n```bash\ngh run view \u003Crun-id> --json jobs\n```\n\nGet truncated logs for failed steps:\n\n```bash\ngh run view \u003Crun-id> --log-failed 2>\u002Fdev\u002Fnull | tail -400\n```\n\n**Context budget:**\n- Max 3 failed jobs included\n- Max 100 lines per failed step\n- Max 400 total log lines\n- If exceeded: prefer the most recent failed step and the final\n  error-bearing lines\n- If logs unavailable (permissions, expired): fall back to structural\n  info only (job name, step name, exit code)\n\n**Format the failure summary:**\n\n```\n## CI Failure Summary\n\n**PR:** #\u003Cnumber> (\u003Cbranch>)\n**Run:** \u003Crun-url>\n**Commit:** \u003Chead_sha>\n**Status:** failure\n\n### Failed Job: \u003Cjob-name> (\u003Crunner>)\n\n**Failed Step:** \u003Cstep-name> (exit code \u003CN>)\n\n\u003Cstep log output, last 100 lines>\n```\n\nIf multiple jobs failed, include up to 3, each with their failed\nstep logs.\n\n### 5. Git Preflight and Branch Checkout\n\nBefore dispatching dev, ensure a clean state on the correct branch.\n\n1. **Preflight:**\n   ```bash\n   bash \u003Cplugin-dir>\u002Fscripts\u002Fgit-isolate.sh preflight\n   ```\n   - `not-a-git-repo` → stop. CI repair requires git.\n   - `dirty-worktree` → stop. Tell user: \"Uncommitted changes\n     detected. Stash or commit before CI repair to avoid staging\n     unrelated files.\"\n   - `detached-head` → stop. Tell user: \"Detached HEAD. Checkout\n     a branch before CI repair.\"\n\n2. **Checkout the PR branch:**\n   ```bash\n   git fetch origin \u003Cpr_branch>\n   git checkout \u003Cpr_branch>\n   git pull origin \u003Cpr_branch>\n   ```\n   If already on the PR branch and up to date, skip checkout.\n\n3. **Record repair baseline:**\n   ```bash\n   REPAIR_BASELINE=$(git rev-parse HEAD)\n   ```\n   Used in step 8 to commit only the repair changes.\n\n### 6. Dispatch Dev\n\nDispatch the dev role as a subagent with:\n- The CI failure summary (from step 4) as primary context\n- Instruction: \"Fix the CI failure described above. Only modify files\n  needed to resolve the failing test\u002Fcheck. Do not refactor or add\n  features beyond the fix.\"\n\nAppend systematic debugging guidance directly to the dev prompt:\n\"Use a systematic debugging approach: reproduce the failure locally\nif possible, identify the root cause from the CI logs, then fix.\nDo not guess — trace the error.\"\n\n**Note:** The `hotl-skills` adapter is NOT used for standalone CI\nrepair invocations — it requires a `--run-id` with pipeline state\nthat doesn't exist here. Debugging guidance is injected directly\ninto the prompt instead.\n\n### 7. Local Verification\n\nAfter dev completes the fix, run local verification:\n\n```bash\npython3 \u003Cruntime>\u002Fagenteam_rt.py final-verify-plan\n```\n\nThis returns the project's verify commands (auto-detected or\nconfigured).\n\n- **Verify commands found:** Run each command. If ALL pass → proceed\n  to push (step 8). If ANY fail → do NOT push. Show failure output.\n  Tell user: \"Local verification failed. The fix may be incomplete.\"\n  Stop.\n- **No verify commands found:** Tell user: \"No local verification\n  available. The fix is unverified locally. Push anyway? (yes\u002Fno)\"\n  Do NOT silently push unverified fixes. Wait for explicit user\n  confirmation.\n\n### 8. Push and Report\n\nOnly if local verify passed (or user confirmed unverified push):\n\nAlways re-read `headRefOid` immediately before committing and pushing. It must equal\nthe checkpoint's expected head SHA; otherwise stop with `head_changed` so a\nconcurrent contributor's update is never overwritten.\n\n```bash\n# Commit only files changed since repair baseline\ngit diff --name-only $REPAIR_BASELINE | xargs git add\ngit commit -m \"[ateam:ci-repair] Fix CI failure in \u003Cfailed-step>\"\ngit push origin \u003Cpr_branch>\n```\n\nIf no files changed since baseline: \"Dev made no changes. The fix\nmay require a different approach.\" Do NOT create an empty commit.\nStop.\n\n**Success report:**\n```\nCI repair pushed to \u003Cpr_branch>.\n- Fixed: \u003Cbrief description of what dev changed>\n- Files changed: \u003Clist of files modified since baseline>\n- Local verify: passed (or: unverified — user confirmed)\n- PR: \u003Cpr_url>\n- CI will re-run automatically.\n```\n\nAfter pushing, store the new head SHA and return to step 3. Continue the bounded\nloop until CI succeeds or `max_repair_cycles`\u002F`max_elapsed_minutes` is reached.\nEach new failing SHA gets its own diagnostic and repair record; the same SHA is\nnever repaired twice after a successful local verification and push.\n\n**Failure report (local verify failed):**\n```\nCI repair NOT pushed — local verification failed.\n- Failure: \u003Cverify output excerpt>\n- The fix may be incomplete. Review and retry with:\n  $ateam:ci-repair \u003Cpr_number>\n```\n\n## Error Handling\n\n- If `gh` CLI is not installed: show install instructions and stop\n- If `gh` is not authenticated: tell user to run `gh auth login`\n- If the PR branch doesn't exist locally or remotely: show error\n- If the CI run has no log access (private repo, expired logs):\n  fall back to structural info only\n- If dev makes no changes: report and stop (don't empty-commit)\n- If push fails (permissions, protected branch): show error and\n  suggest manual push\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","# AgenTeam CI Repair\n\nFix a CI failure on a pull request. Fetches the failure context from\nGitHub Actions, dispatches the dev role with bounded logs, verifies\nthe fix locally, and pushes only if verification passes.\n\nGitHub Actions only. The workflow is a bounded, resumable\nmonitor → diagnose → repair → verify loop.\n\n## Loop Contract\n\n- Defaults: `max_repair_cycles: 3`, `max_elapsed_minutes: 90`, and a\n  five-minute CI polling interval. User-supplied lower budgets win.\n- Persist every cycle in `.agenteam\u002Fci-repair\u002Fpr-\u003Cpr_number>.json`, keyed by\n  `head_sha`. Record the run ID, failed jobs, repair attempt, local verification,\n  pushed SHA, last heartbeat, and stop reason.\n- Emit a heartbeat while waiting for a role or CI. If the host cannot remain\n  active, schedule a follow-up\u002Fautomation and stop cleanly instead of holding a\n  silent blocking wait.\n- Before replaying a repair after restart, compare the checkpoint head SHA and\n  current PR head. Never repeat a completed repair for the same SHA.\n- Stop explicitly on success, exhausted cycle\u002Felapsed budget, changed PR head,\n  unavailable evidence, or required human approval.\n\n## Process\n\n### 1. Accept Input\n\nGet the PR reference from the user:\n- PR number: `$ateam:ci-repair #42`\n- Branch name: `$ateam:ci-repair feature\u002Fadd-auth`\n- Nothing: use the current branch\n\n### 2. Resolve PR\n\nResolve the input to a canonical tuple: `pr_number`, `pr_url`,\n`pr_branch`, `head_sha`.\n\n**If PR number given:**\n```bash\ngh pr view \u003Cnumber> --json number,url,headRefName,headRefOid\n```\n\n**If branch given or current branch:**\n```bash\nBRANCH=$(git rev-parse --abbrev-ref HEAD)  # if no input\ngh pr list --head \u003Cbranch> --json number,url,headRefName,headRefOid --limit 1\n```\n\nIf no PR found: \"No PR found for branch `\u003Cbranch>`. Push and create\na PR first, then retry.\" Stop.\n\nExtract:\n- `pr_number` from `number`\n- `pr_url` from `url`\n- `pr_branch` from `headRefName`\n- `head_sha` from `headRefOid`\n\n### 3. Check CI Status\n\nGet the latest CI run for the PR's current head commit:\n\n```bash\ngh run list --commit \u003Chead_sha> --limit 5 \\\n  --json status,conclusion,databaseId,name,createdAt\n```\n\nCheck the **latest run for this exact commit**:\n\n- **`failure`** → proceed to fetch context (step 4)\n- **`success`** → \"CI is passing on the current head commit. No\n  repair needed.\" Stop.\n- **`in_progress`** or **`queued`** → Persist the run ID and heartbeat, then\n  monitor it within the elapsed budget. Poll no more frequently than the\n  configured interval. If this invocation cannot keep monitoring, arrange a\n  follow-up and stop with reason `ci_wait_scheduled`.\n- **No runs found** → \"No CI runs found for commit `\u003Chead_sha>`.\n  Push or re-run CI, then retry.\" Stop.\n\n### 4. Fetch Failure Context\n\nGet structural info (which jobs\u002Fsteps failed):\n\n```bash\ngh run view \u003Crun-id> --json jobs\n```\n\nGet truncated logs for failed steps:\n\n```bash\ngh run view \u003Crun-id> --log-failed 2>\u002Fdev\u002Fnull | tail -400\n```\n\n**Context budget:**\n- Max 3 failed jobs included\n- Max 100 lines per failed step\n- Max 400 total log lines\n- If exceeded: prefer the most recent failed step and the final\n  error-bearing lines\n- If logs unavailable (permissions, expired): fall back to structural\n  info only (job name, step name, exit code)\n\n**Format the failure summary:**\n\n```\n## CI Failure Summary\n\n**PR:** #\u003Cnumber> (\u003Cbranch>)\n**Run:** \u003Crun-url>\n**Commit:** \u003Chead_sha>\n**Status:** failure\n\n### Failed Job: \u003Cjob-name> (\u003Crunner>)\n\n**Failed Step:** \u003Cstep-name> (exit code \u003CN>)\n\n\u003Cstep log output, last 100 lines>\n```\n\nIf multiple jobs failed, include up to 3, each with their failed\nstep logs.\n\n### 5. Git Preflight and Branch Checkout\n\nBefore dispatching dev, ensure a clean state on the correct branch.\n\n1. **Preflight:**\n   ```bash\n   bash \u003Cplugin-dir>\u002Fscripts\u002Fgit-isolate.sh preflight\n   ```\n   - `not-a-git-repo` → stop. CI repair requires git.\n   - `dirty-worktree` → stop. Tell user: \"Uncommitted changes\n     detected. Stash or commit before CI repair to avoid staging\n     unrelated files.\"\n   - `detached-head` → stop. Tell user: \"Detached HEAD. Checkout\n     a branch before CI repair.\"\n\n2. **Checkout the PR branch:**\n   ```bash\n   git fetch origin \u003Cpr_branch>\n   git checkout \u003Cpr_branch>\n   git pull origin \u003Cpr_branch>\n   ```\n   If already on the PR branch and up to date, skip checkout.\n\n3. **Record repair baseline:**\n   ```bash\n   REPAIR_BASELINE=$(git rev-parse HEAD)\n   ```\n   Used in step 8 to commit only the repair changes.\n\n### 6. Dispatch Dev\n\nDispatch the dev role as a subagent with:\n- The CI failure summary (from step 4) as primary context\n- Instruction: \"Fix the CI failure described above. Only modify files\n  needed to resolve the failing test\u002Fcheck. Do not refactor or add\n  features beyond the fix.\"\n\nAppend systematic debugging guidance directly to the dev prompt:\n\"Use a systematic debugging approach: reproduce the failure locally\nif possible, identify the root cause from the CI logs, then fix.\nDo not guess — trace the error.\"\n\n**Note:** The `hotl-skills` adapter is NOT used for standalone CI\nrepair invocations — it requires a `--run-id` with pipeline state\nthat doesn't exist here. Debugging guidance is injected directly\ninto the prompt instead.\n\n### 7. Local Verification\n\nAfter dev completes the fix, run local verification:\n\n```bash\npython3 \u003Cruntime>\u002Fagenteam_rt.py final-verify-plan\n```\n\nThis returns the project's verify commands (auto-detected or\nconfigured).\n\n- **Verify commands found:** Run each command. If ALL pass → proceed\n  to push (step 8). If ANY fail → do NOT push. Show failure output.\n  Tell user: \"Local verification failed. The fix may be incomplete.\"\n  Stop.\n- **No verify commands found:** Tell user: \"No local verification\n  available. The fix is unverified locally. Push anyway? (yes\u002Fno)\"\n  Do NOT silently push unverified fixes. Wait for explicit user\n  confirmation.\n\n### 8. Push and Report\n\nOnly if local verify passed (or user confirmed unverified push):\n\nAlways re-read `headRefOid` immediately before committing and pushing. It must equal\nthe checkpoint's expected head SHA; otherwise stop with `head_changed` so a\nconcurrent contributor's update is never overwritten.\n\n```bash\n# Commit only files changed since repair baseline\ngit diff --name-only $REPAIR_BASELINE | xargs git add\ngit commit -m \"[ateam:ci-repair] Fix CI failure in \u003Cfailed-step>\"\ngit push origin \u003Cpr_branch>\n```\n\nIf no files changed since baseline: \"Dev made no changes. The fix\nmay require a different approach.\" Do NOT create an empty commit.\nStop.\n\n**Success report:**\n```\nCI repair pushed to \u003Cpr_branch>.\n- Fixed: \u003Cbrief description of what dev changed>\n- Files changed: \u003Clist of files modified since baseline>\n- Local verify: passed (or: unverified — user confirmed)\n- PR: \u003Cpr_url>\n- CI will re-run automatically.\n```\n\nAfter pushing, store the new head SHA and return to step 3. Continue the bounded\nloop until CI succeeds or `max_repair_cycles`\u002F`max_elapsed_minutes` is reached.\nEach new failing SHA gets its own diagnostic and repair record; the same SHA is\nnever repaired twice after a successful local verification and push.\n\n**Failure report (local verify failed):**\n```\nCI repair NOT pushed — local verification failed.\n- Failure: \u003Cverify output excerpt>\n- The fix may be incomplete. Review and retry with:\n  $ateam:ci-repair \u003Cpr_number>\n```\n\n## Error Handling\n\n- If `gh` CLI is not installed: show install instructions and stop\n- If `gh` is not authenticated: tell user to run `gh auth login`\n- If the PR branch doesn't exist locally or remotely: show error\n- If the CI run has no log access (private repo, expired logs):\n  fall back to structural info only\n- If dev makes no changes: report and stop (don't empty-commit)\n- If push fails (permissions, protected branch): show error and\n  suggest manual push\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",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fyimwoo\u002Fcodex-agenteam\u002Fskills\u002Fci-repair",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":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill ci-repair",{"tool":51,"command":52},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill ci-repair",{"tool":54,"command":55},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill ci-repair","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyimwoo\u002Fcodex-agenteam\u002Fskills\u002Fci-repair\u002FSKILL.md",true,[],[60,70,78,86,94,102],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":65,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":69},"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":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":69},"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":69},"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":69},"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":98,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":69},"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":69},"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",[],[]]