[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75862H17BC1K9VCYE0B31AM":3,"skill-same:01M75862H17BC1K9VCYE0B31AM":47},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":29,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M75862H17BC1K9VCYE0B31AM","ci-triage",null,"Find and diagnose RED CI with the gh CLI — answer \"is anything failing?\" and \"why?\" correctly, without being handed a URL. Invoke (via the Skill tool) whenever you need to check whether a branch, commit, or PR is green, whenever someone reports failing CI, before cutting a release, and before claiming any commit is green. THE FAILURE THIS SKILL EXISTS TO PREVENT: `gh run list` reports a RUN-level `conclusion`, and a run whose rollup is `cancelled` can contain a job whose conclusion is `failure` — so filtering runs on `conclusion==\"failure\"` silently misses real red, and taking the latest run per workflow hides an older failed run on the same SHA. The authoritative instrument is the commit's CHECK-RUNS, which is what the GitHub UI renders. Pairs with `ci-watch` (blocking until a run is terminal) and `ci-adhoc-test` (running a probe on a real OS).","nubjs\u002Fnub","nubjs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6785695?v=4","01M7583N3EYYHSNB6FJQXCDMQH","Nub","01M7583N44MVMSN8385QEF3C8V",4440,"MIT","https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fci-triage\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ci-triage\ndescription: >-\n  Find and diagnose RED CI with the gh CLI — answer \"is anything failing?\" and\n  \"why?\" correctly, without being handed a URL. Invoke (via the Skill tool)\n  whenever you need to check whether a branch, commit, or PR is green, whenever\n  someone reports failing CI, before cutting a release, and before claiming any\n  commit is green. THE FAILURE THIS SKILL EXISTS TO PREVENT: `gh run list`\n  reports a RUN-level `conclusion`, and a run whose rollup is `cancelled` can\n  contain a job whose conclusion is `failure` — so filtering runs on\n  `conclusion==\"failure\"` silently misses real red, and taking the latest run\n  per workflow hides an older failed run on the same SHA. The authoritative\n  instrument is the commit's CHECK-RUNS, which is what the GitHub UI renders.\n  Pairs with `ci-watch` (blocking until a run is terminal) and `ci-adhoc-test`\n  (running a probe on a real OS).\n---\n\n# Investigating CI\n\n`ci-watch` answers *\"has it finished, and did it pass?\"* for one run you are waiting on. This skill answers the two questions you get asked cold: **\"is anything red?\"** and **\"why is this red?\"** — starting from a branch name or a commit, never from a URL someone hands you.\n\n## The rule\n\n**Never answer \"is it green?\" from run-level `conclusion`. Query the commit's check-runs.**\n\nA GitHub Actions *run* rolls up its jobs into one conclusion, and that rollup is lossy in the exact case that matters:\n\n| What happened | Run `conclusion` | Job conclusions | `gh run list` shows |\n| --- | --- | --- | --- |\n| A job failed | `failure` | one `failure` | ✅ red — you see it |\n| **A job failed inside a run that also got cancelled** | **`cancelled`** | **one `failure`** | ❌ **nothing — filtered out** |\n| Superseded by `cancel-in-progress` | `cancelled` | all `cancelled` | ❌ nothing (correctly) |\n\nThe middle row is real and it is what the UI paints red on the commit. It happens whenever a workflow has an aggregation\u002Fgate job that runs after its matrix legs: `concurrency: cancel-in-progress` cancels the legs, the gate still runs, sees `cancelled`, and **fails**. The run rolls up `cancelled`; the gate job is `failure`.\n\n## The one command that is always correct\n\n```bash\nSHA=$(git rev-parse origin\u002Fmain)   # or a PR head, or any commit\ngh api repos\u002Fnubjs\u002Fnub\u002Fcommits\u002F$SHA\u002Fcheck-runs --paginate \\\n  --jq '.check_runs[] | select(.conclusion != \"success\" and .conclusion != \"skipped\" and .conclusion != \"neutral\")\n        | \"\\(.conclusion \u002F\u002F .status) | \\(.name) | \\(.html_url)\"'\n```\n\nEmpty output means genuinely green. Anything else is exactly what a human sees in the Actions tab, with a clickable URL per finding. This endpoint is the source of truth because it is what the UI renders — run-level data is downstream of it.\n\n### Counting, and the `--paginate` trap\n\n**`--paginate` runs `--jq` once PER PAGE.** A per-item filter like the one above is fine — each page emits its own lines and they concatenate. But any *aggregation* (`length`, `add`, `group_by`) silently returns one result per page instead of a total:\n\n```bash\n# WRONG — prints \"0\" then \"1\" on a 2-page response. Reads like 0 if you only look at line 1.\ngh api repos\u002Fnubjs\u002Fnub\u002Fcommits\u002F$SHA\u002Fcheck-runs --paginate --jq '[.check_runs[]|select(.conclusion==\"failure\")]|length'\n```\n\nUse `--slurp` to get one array across pages, and pipe to external `jq` — `--slurp` is rejected together with `--jq`:\n\n```bash\n# RIGHT — one number for the whole commit.\ngh api repos\u002Fnubjs\u002Fnub\u002Fcommits\u002F$SHA\u002Fcheck-runs --paginate --slurp \\\n  | jq '[.[].check_runs[] | select(.conclusion==\"failure\")] | length'\n```\n\nThis is not hypothetical: a release commit here carried **192 check-runs across 2 pages**, and the naive count printed `0` on the first line.\n\n## Diagnosing one failure\n\nGiven a failing check, get the run, then the job, then the log — in that order.\n\n```bash\ngh run view \u003Crun-id> --json name,status,conclusion,headBranch,headSha,event,createdAt\ngh run view \u003Crun-id> --json jobs --jq '.jobs[] | \"\\(.conclusion \u002F\u002F .status) | \\(.name)\"'\ngh run view \u003Crun-id> --log-failed > \u002Ftmp\u002Ffail.log 2>&1; echo \"EXIT=$?\"\nsed -e 's\u002F\\x1b\\[[0-9;]*m\u002F\u002Fg' \u002Ftmp\u002Ffail.log | grep -viE '^\\s*$' | tail -40\n```\n\nStrip ANSI escapes (`sed -e 's\u002F\\x1b\\[[0-9;]*m\u002F\u002Fg'`) or the log is unreadable. `--log-failed` returns only failing steps, which is usually 40 lines rather than 40,000.\n\n**Read the `event` and `createdAt` fields before concluding anything.** They tell you whether the run was superseded, and by what.\n\n## Superseded-run triage — is this red REAL?\n\nA red check on a commit is not automatically a broken commit. Decide with this:\n\n1. **List every run of that workflow on that SHA.** More than one is the tell.\n   ```bash\n   gh run list --workflow \u003Cfile>.yml --limit 30 \\\n     --json databaseId,status,conclusion,headSha,headBranch,event,createdAt \\\n     --jq '.[] | select(.headSha==\"'\"$SHA\"'\") | \"id=\\(.databaseId) | \\(.conclusion \u002F\u002F .status) | \\(.event) | \\(.createdAt)\"'\n   ```\n2. **If a later run of the same workflow on the same SHA is fully green, the code is fine** — the red one was superseded. The commit still *shows* red, which is a workflow defect worth fixing, not a code defect.\n3. **Check the concurrency group.** `group: ${{ github.workflow }}-${{ github.ref }}` means a `schedule` run and a `push` run on `main` share a group and will cancel each other, because both carry `refs\u002Fheads\u002Fmain`. That is a common and surprising source of self-inflicted red.\n\n## The gate-job anti-pattern, and its fix\n\nA gate job that aggregates matrix legs must treat `cancelled` as *not a verdict*. This is wrong:\n\n```bash\n[[ \"$smoke\" == \"success\" || \"$smoke\" == \"skipped\" ]] || { echo \"smoke failed\"; exit 1; }\n```\n\nA superseded run sets `smoke=cancelled`, so the gate fails and paints the commit red forever. Accept `cancelled` too — it does not mask a real failure, because a genuinely failing leg aggregates to `failure`, not `cancelled`:\n\n```bash\n[[ \"$smoke\" == \"success\" || \"$smoke\" == \"skipped\" || \"$smoke\" == \"cancelled\" ]] || { echo \"smoke failed\"; exit 1; }\n```\n\n## What NOT to do\n\n- **Do not** filter `gh run list` on `conclusion==\"failure\"` and call the absence of hits \"green\". That is the whole bug this skill exists for.\n- **Do not** take the latest run per workflow (`group_by(.name) | max_by(.createdAt)`). A later scheduled run can hide an earlier failed push run on the same SHA.\n- **Do not** trust `--branch main` alone to find everything; a check can be attached by an app or a `workflow_run`. Check-runs on the SHA catch all of them.\n- **Do not** conclude \"not failing\" from a bot issue being absent. The trunk-red bot files on its own schedule and its silence proves nothing.\n- **Do not** read an exit code through a pipe (`gh ... | head` then `$?`). Redirect, capture `$?` on its own line, then inspect.\n\n## Reporting a finding\n\nState the commit, the check name, the run URL, whether a later run on the same SHA passed, and the mechanism. \"CI is red\" without those is not a diagnosis. If a superseded run is the cause, say so plainly and name the fix — the commit is still red in the UI and someone has to look at it.\n","# Investigating CI\n\n`ci-watch` answers *\"has it finished, and did it pass?\"* for one run you are waiting on. This skill answers the two questions you get asked cold: **\"is anything red?\"** and **\"why is this red?\"** — starting from a branch name or a commit, never from a URL someone hands you.\n\n## The rule\n\n**Never answer \"is it green?\" from run-level `conclusion`. Query the commit's check-runs.**\n\nA GitHub Actions *run* rolls up its jobs into one conclusion, and that rollup is lossy in the exact case that matters:\n\n| What happened | Run `conclusion` | Job conclusions | `gh run list` shows |\n| --- | --- | --- | --- |\n| A job failed | `failure` | one `failure` | ✅ red — you see it |\n| **A job failed inside a run that also got cancelled** | **`cancelled`** | **one `failure`** | ❌ **nothing — filtered out** |\n| Superseded by `cancel-in-progress` | `cancelled` | all `cancelled` | ❌ nothing (correctly) |\n\nThe middle row is real and it is what the UI paints red on the commit. It happens whenever a workflow has an aggregation\u002Fgate job that runs after its matrix legs: `concurrency: cancel-in-progress` cancels the legs, the gate still runs, sees `cancelled`, and **fails**. The run rolls up `cancelled`; the gate job is `failure`.\n\n## The one command that is always correct\n\n```bash\nSHA=$(git rev-parse origin\u002Fmain)   # or a PR head, or any commit\ngh api repos\u002Fnubjs\u002Fnub\u002Fcommits\u002F$SHA\u002Fcheck-runs --paginate \\\n  --jq '.check_runs[] | select(.conclusion != \"success\" and .conclusion != \"skipped\" and .conclusion != \"neutral\")\n        | \"\\(.conclusion \u002F\u002F .status) | \\(.name) | \\(.html_url)\"'\n```\n\nEmpty output means genuinely green. Anything else is exactly what a human sees in the Actions tab, with a clickable URL per finding. This endpoint is the source of truth because it is what the UI renders — run-level data is downstream of it.\n\n### Counting, and the `--paginate` trap\n\n**`--paginate` runs `--jq` once PER PAGE.** A per-item filter like the one above is fine — each page emits its own lines and they concatenate. But any *aggregation* (`length`, `add`, `group_by`) silently returns one result per page instead of a total:\n\n```bash\n# WRONG — prints \"0\" then \"1\" on a 2-page response. Reads like 0 if you only look at line 1.\ngh api repos\u002Fnubjs\u002Fnub\u002Fcommits\u002F$SHA\u002Fcheck-runs --paginate --jq '[.check_runs[]|select(.conclusion==\"failure\")]|length'\n```\n\nUse `--slurp` to get one array across pages, and pipe to external `jq` — `--slurp` is rejected together with `--jq`:\n\n```bash\n# RIGHT — one number for the whole commit.\ngh api repos\u002Fnubjs\u002Fnub\u002Fcommits\u002F$SHA\u002Fcheck-runs --paginate --slurp \\\n  | jq '[.[].check_runs[] | select(.conclusion==\"failure\")] | length'\n```\n\nThis is not hypothetical: a release commit here carried **192 check-runs across 2 pages**, and the naive count printed `0` on the first line.\n\n## Diagnosing one failure\n\nGiven a failing check, get the run, then the job, then the log — in that order.\n\n```bash\ngh run view \u003Crun-id> --json name,status,conclusion,headBranch,headSha,event,createdAt\ngh run view \u003Crun-id> --json jobs --jq '.jobs[] | \"\\(.conclusion \u002F\u002F .status) | \\(.name)\"'\ngh run view \u003Crun-id> --log-failed > \u002Ftmp\u002Ffail.log 2>&1; echo \"EXIT=$?\"\nsed -e 's\u002F\\x1b\\[[0-9;]*m\u002F\u002Fg' \u002Ftmp\u002Ffail.log | grep -viE '^\\s*$' | tail -40\n```\n\nStrip ANSI escapes (`sed -e 's\u002F\\x1b\\[[0-9;]*m\u002F\u002Fg'`) or the log is unreadable. `--log-failed` returns only failing steps, which is usually 40 lines rather than 40,000.\n\n**Read the `event` and `createdAt` fields before concluding anything.** They tell you whether the run was superseded, and by what.\n\n## Superseded-run triage — is this red REAL?\n\nA red check on a commit is not automatically a broken commit. Decide with this:\n\n1. **List every run of that workflow on that SHA.** More than one is the tell.\n   ```bash\n   gh run list --workflow \u003Cfile>.yml --limit 30 \\\n     --json databaseId,status,conclusion,headSha,headBranch,event,createdAt \\\n     --jq '.[] | select(.headSha==\"'\"$SHA\"'\") | \"id=\\(.databaseId) | \\(.conclusion \u002F\u002F .status) | \\(.event) | \\(.createdAt)\"'\n   ```\n2. **If a later run of the same workflow on the same SHA is fully green, the code is fine** — the red one was superseded. The commit still *shows* red, which is a workflow defect worth fixing, not a code defect.\n3. **Check the concurrency group.** `group: ${{ github.workflow }}-${{ github.ref }}` means a `schedule` run and a `push` run on `main` share a group and will cancel each other, because both carry `refs\u002Fheads\u002Fmain`. That is a common and surprising source of self-inflicted red.\n\n## The gate-job anti-pattern, and its fix\n\nA gate job that aggregates matrix legs must treat `cancelled` as *not a verdict*. This is wrong:\n\n```bash\n[[ \"$smoke\" == \"success\" || \"$smoke\" == \"skipped\" ]] || { echo \"smoke failed\"; exit 1; }\n```\n\nA superseded run sets `smoke=cancelled`, so the gate fails and paints the commit red forever. Accept `cancelled` too — it does not mask a real failure, because a genuinely failing leg aggregates to `failure`, not `cancelled`:\n\n```bash\n[[ \"$smoke\" == \"success\" || \"$smoke\" == \"skipped\" || \"$smoke\" == \"cancelled\" ]] || { echo \"smoke failed\"; exit 1; }\n```\n\n## What NOT to do\n\n- **Do not** filter `gh run list` on `conclusion==\"failure\"` and call the absence of hits \"green\". That is the whole bug this skill exists for.\n- **Do not** take the latest run per workflow (`group_by(.name) | max_by(.createdAt)`). A later scheduled run can hide an earlier failed push run on the same SHA.\n- **Do not** trust `--branch main` alone to find everything; a check can be attached by an app or a `workflow_run`. Check-runs on the SHA catch all of them.\n- **Do not** conclude \"not failing\" from a bot issue being absent. The trunk-red bot files on its own schedule and its silence proves nothing.\n- **Do not** read an exit code through a pipe (`gh ... | head` then `$?`). Redirect, capture `$?` on its own line, then inspect.\n\n## Reporting a finding\n\nState the commit, the check name, the run URL, whether a later run on the same SHA passed, and the mechanism. \"CI is red\" without those is not a diagnosis. If a superseded run is the cause, say so plainly and name the fix — the commit is still red in the UI and someone has to look at it.\n",{"name":5,"description":7},"main","9b734566fd36ceed8379f67a92291bc68af60801",".claude\u002Fskills\u002Fci-triage",71,"https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub","https:\u002F\u002Fnubjs.com","https:\u002F\u002Fgithub.com\u002Fnubjs","The all-in-one Node.js toolkit","2026-11-14 14:11:35",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add nubjs\u002Fnub --skill ci-triage",{"tool":39,"command":40},"bunx","bunx skills add nubjs\u002Fnub --skill ci-triage",{"tool":42,"command":43},"pnpm","pnpm dlx skills add nubjs\u002Fnub --skill ci-triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fci-triage\u002FSKILL.md",true,[],[48,54,60,67,74,81],{"skillNo":49,"name":50,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M758BSH88RVXBG8TPCT427TY","nub","https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub\u002Fblob\u002Fmain\u002Fskills\u002Fnub\u002FSKILL.md",[],[],{"skillNo":55,"name":50,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M758BKPRHXS5MS27WG908PBG","This project uses nub, a single Rust CLI that runs on the project's installed Node and replaces the everyday Node toolchain. ALWAYS prefer nub over node, bun, npm, npx, pnpm, and yarn for: executing JS\u002FTS files, running package.json scripts, the npx-equivalent, installing dependencies, watch mode, and Node version management. Surfaces whenever you would otherwise reach for node\u002Fbun\u002Fnpm\u002Fnpx or a package manager.","https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub\u002Fblob\u002Fmain\u002Fsite\u002Fpublic\u002Fskill.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M758BCR8A21H8P4TQ0YRHTC7","worktree","Create and manage isolated git worktrees for parallel build\u002Ftest\u002Flanding work on the nub repo. Invoke (via the Skill tool) whenever you need a fresh worktree to land a change, when you want to know what `.worktreeinclude` does or how to add an entry, or when cleaning up after a merge. Encodes the one-command setup (`nub scripts\u002Fnew-worktree.ts \u003Cslug>` or `node …`) that bakes in the proven recipe — worktree off origin\u002Fmain (vendor\u002Faube is plain in-tree files now, no submodule init), the shared CARGO_TARGET_DIR (`~\u002F.cache\u002Fnub\u002Fshared-target`) that all worktrees reuse, and applying `.worktreeinclude` — plus the eagerly-pull-the-shared-tree discipline and the safe cleanup path. Pairs with the `dev-loop` build skill.","https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fworktree\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M758B9NZ1GQMD1A6B25NK0D9","windows-vm-test","Run ad-hoc Nub tests and debugging probes in the maintainer's existing local Windows 11 ARM64 QEMU\u002FHVF VM when its external disk and runbook are present. Use for interactive win32-arm64 or Windows-on-ARM x64-emulation checks; use ci-adhoc-test for true x64-native behavior or when the local VM is unavailable.","https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwindows-vm-test\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M758B2JHMBB6YJTGYSJR65S4","visual-review","Verify UI\u002Flayout\u002Fstyling changes are correct by computing occlusion, clipping, and alignment from the browser's resolved paint order via the chrome-devtools MCP `evaluate_script` tool — instead of eyeballing a flat screenshot. Invoke BEFORE declaring any UI, site, or styling\u002Flayout change correct. Screenshots have no depth buffer, so z-index\u002Focclusion\u002Fclip bugs are exactly where \"just look at it\" fails; the `evaluate_script` routines below turn those fuzzy visual judgments into deterministic measurements — including optical center-of-mass, which measures the glyph ink's true visual center so differently-sized labels can be aligned by more than eye.","https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvisual-review\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":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M758AWPM7CE440NBAYJHD44J","type-declarations","Add, audit, or update @nubjs\u002Ftypes declarations for Nub runtime APIs. Use whenever Nub adds or changes a user-visible global, built-in method, module loader type, or TC39 proposal; when TypeScript or @types\u002Fnode gains an overlapping declaration; and before every release to reconcile runtime changes since the previous tag. Covers conflict-safe global augmentation, compiler-version routing, fixture matrices, and package verification.","https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftype-declarations\u002FSKILL.md",[],[]]