[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7584R71F0P5XAC2PVVWASA3":3,"skill-same:01M7584R71F0P5XAC2PVVWASA3":48},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":31,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7584R71F0P5XAC2PVVWASA3","audit-thread",null,"Use when running a compatibility\u002Fparity AUDIT — enumerating where nub diverges from a reference it claims parity with (pnpm CLI grammar, a lockfile format, a Node behavior, a flag surface). Encodes the hard gates that stop an audit from surfacing false positives. Auto-triggers on \"audit\", \"compat audit\", \"parity audit\", \"find all the gaps\", \"what are we missing vs \u003Ctool>\".","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\u002Faudit-thread\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: audit-thread\ndescription: Use when running a compatibility\u002Fparity AUDIT — enumerating where nub diverges from a reference it claims parity with (pnpm CLI grammar, a lockfile format, a Node behavior, a flag surface). Encodes the hard gates that stop an audit from surfacing false positives. Auto-triggers on \"audit\", \"compat audit\", \"parity audit\", \"find all the gaps\", \"what are we missing vs \u003Ctool>\".\nmetadata:\n  internal: true\n---\n\n# Audit threads\n\nAn **audit**'s deliverable is a CLEAN, COMPLETE, VERIFIED list of real gaps between nub and a reference it claims parity with. A single false positive destroys trust in the whole audit; the bar is zero garbage.\n\n**Canonical methodology: AGENTS.md → \"Audit threads.\"** Read it first. This skill is the operational surface: the gate checklist, the verbatim dispatch template, and the orchestration shape.\n\n## The 5 gates\n\n1. **Pin the reference target surgically.** State the EXACT major (e.g. pnpm 10) and VERIFY every reference checkout's version before reading it (`git -C .repos\u002F\u003Ctool> describe --tags`, its `package.json` `version`, the installed tool's `--version`). Wrong-major reference is the #1 garbage source. **When the audit target is a branch\u002FSHA of THIS repo**, `git fetch origin` FIRST and pin `origin\u002F\u003Cbranch>@\u003Csha>` — never a local worktree\u002Fbranch checkout, which routinely lags origin. Verify reachability (`git merge-base --is-ancestor \u003Csha> origin\u002F\u003Cbranch>`) before reading a byte.\n2. **Empirical over source.** A candidate is not a finding until a differential fixture reproduces it by RUNNING the real pinned tool + nub on identical input and diffing. Source and `--help` reading yield leads only.\n3. **Cross-check the decision record.** Deprecated\u002Fremoved flags, npm-isms nub rejects, the deliberate pnpm-compat divergences, and already-decided\u002Falready-built work are NOT findings. Filter against AGENTS.md \"Core design positions\", `wiki\u002F` decision docs, and prior thread notes.\n4. **Mandatory adversarial self-refutation.** Fresh-context reviewer(s) try to REFUTE each surfaced finding by re-pinning, re-reproducing, and re-checking the decision record. They must also challenge any claim that a gap is *irreducible* by exhausting the mechanism's documented alternatives and testing plausible closures. Default to refuted when uncertain. Surface only survivors, each with reproduction evidence; never forward the raw breadth-pass output.\n5. **Tier + deliverable.** Opus at high+ effort for judgment AND refutation (a cheap tier may harvest breadth, but every item is Opus-verified). Thoroughness is two-dimensional: COVERAGE (enumerate the FULL surface from the pinned reference's own authoritative source) AND PRECISION (every item verified). Catalog → `wiki\u002Fresearch\u002F\u003Ctopic>.md` with all buckets explicit (real gaps \u002F confirmed-OK \u002F intentional-divergence); each finding records reproduction + decision-record cross-check + severity + confidence.\n\n## Orchestration shape\n\nEnumerate the full surface (coverage) → harvest candidate gaps → cross-check the decision record → reproduce each against the pinned real tool → adversarially refute in fresh context → surface ONLY survivors, with evidence.\n\nRun it with individually-dispatched agents — not a blind parallel Workflow fan-out that buries the gates.\n\n**Only a top-level session dispatches those agents.** If you are yourself a dispatched sub-agent, the repo-wide depth cap in `AGENTS.local.md` applies: run the gates INLINE and return. Gate 4's \"fresh context\" is then a fresh PASS, not a fresh agent — re-pin, re-run the fixture, and re-check the decision record yourself, defaulting to refuted when uncertain. An audit prong that cannot be refuted inline returns saying so rather than spawning a refuter.\n\n**When a finding is ACTIONED.** An audit is investigation-scope: it surfaces gaps, it does not land fixes. The moment a finding becomes a code change, verify it the standard way — an ad-hoc fixture sweep against a built binary, re-running the audit's own differential against the pinned reference, then an in-thread read of the diff. A parity fix touching a shared verb\u002Fflag dispatch path routinely ripples to sibling commands, which is one of the cases that earns escalating to a fresh-context `impact-analysis` pass — but that never substitutes for running the sibling commands and diffing them against the reference. Gate 4 asks whether a FINDING is real; impact analysis asks whether a FIX is safe.\n\n## Dispatch template (every audit sub-agent prompt must be self-contained)\n\n```\nYou are running a \u003CSCOPE> audit: find where nub diverges from \u003CREFERENCE> \u003CEXACT MAJOR> on \u003CSURFACE>.\nThis is an AUDIT — the deliverable is a CLEAN, VERIFIED list of REAL gaps. A single false positive is\nunacceptable. Follow all 5 gates; do not skip any.\n\nGATE 1 — PIN: The target is \u003CREFERENCE> \u003CEXACT MAJOR>. BEFORE reading anything, verify the version of\n  every reference you use: `git -C .repos\u002F\u003Ctool> describe --tags` and its package.json version, and\n  `\u003Ctool> --version` for any installed binary. If a checkout is the wrong major, check out the right\n  tag \u002F install the right version FIRST. State the verified versions at the top of your output.\n  If the AUDIT TARGET is a branch\u002FSHA of THIS repo (not a reference tool): `git fetch origin` FIRST,\n  pin `origin\u002F\u003Cbranch>@\u003Csha>` (NEVER a local worktree\u002Fbranch — it routinely lags origin), and verify\n  `git merge-base --is-ancestor \u003Csha> origin\u002F\u003Cbranch>` before reading. State the pinned SHA at the top.\nGATE 2 — EMPIRICAL: A gap is NOT a finding until you reproduce it by RUNNING \u003CREFERENCE> \u003CMAJOR> AND nub\n  on identical input and diffing the actual output. Source-reading and --help parsing are LEADS only.\n  Build a minimal differential fixture per candidate; capture both commands + both outputs.\nGATE 3 — DECISION RECORD: Drop any candidate that is a deprecated\u002Fremoved flag in \u003CREFERENCE> \u003CMAJOR>,\n  an npm-ism nub deliberately rejects, one of nub's intentional pnpm-compat divergences, or already\n  decided\u002Fbuilt. Cross-check AGENTS.md \"Core design positions\", wiki\u002F decision docs, and prior thread notes.\n  Deeply evaluate what has ALREADY been discussed — surfacing a settled call is as bad as a false positive.\nGATE 4 — REFUTE: After harvesting, re-verify every surviving candidate adversarially (try to REFUTE it:\n  re-pin, re-reproduce, re-check the record). Treat \"irreducible\" or \"cannot close\" as claims that also\n  require evidence: exhaust the documented mechanism surface and test plausible closures. Keep only\n  what survives, with its reproduction evidence.\nGATE 5 — COVERAGE + PRECISION: Enumerate the FULL surface from \u003CREFERENCE> \u003CMAJOR>'s own authoritative\n  source (its --help \u002F source), so nothing is missed; AND verify every surfaced item. Output ALL buckets:\n  real gaps \u002F confirmed-OK \u002F intentional-divergence. Each real finding: reproduction command + both\n  outputs + decision-record cross-check + severity + confidence.\n\nDeliverable: a catalog at wiki\u002Fresearch\u002F\u003Ctopic>.md (all buckets) + a tight triaged list of REAL gaps for\nthe maintainer. Investigation-scope — do NOT land fixes; surface findings recommend-only.\n```\n\nWhen an audit reveals a NEW pitfall not covered above, fold it into the gate it strengthens.\n","# Audit threads\n\nAn **audit**'s deliverable is a CLEAN, COMPLETE, VERIFIED list of real gaps between nub and a reference it claims parity with. A single false positive destroys trust in the whole audit; the bar is zero garbage.\n\n**Canonical methodology: AGENTS.md → \"Audit threads.\"** Read it first. This skill is the operational surface: the gate checklist, the verbatim dispatch template, and the orchestration shape.\n\n## The 5 gates\n\n1. **Pin the reference target surgically.** State the EXACT major (e.g. pnpm 10) and VERIFY every reference checkout's version before reading it (`git -C .repos\u002F\u003Ctool> describe --tags`, its `package.json` `version`, the installed tool's `--version`). Wrong-major reference is the #1 garbage source. **When the audit target is a branch\u002FSHA of THIS repo**, `git fetch origin` FIRST and pin `origin\u002F\u003Cbranch>@\u003Csha>` — never a local worktree\u002Fbranch checkout, which routinely lags origin. Verify reachability (`git merge-base --is-ancestor \u003Csha> origin\u002F\u003Cbranch>`) before reading a byte.\n2. **Empirical over source.** A candidate is not a finding until a differential fixture reproduces it by RUNNING the real pinned tool + nub on identical input and diffing. Source and `--help` reading yield leads only.\n3. **Cross-check the decision record.** Deprecated\u002Fremoved flags, npm-isms nub rejects, the deliberate pnpm-compat divergences, and already-decided\u002Falready-built work are NOT findings. Filter against AGENTS.md \"Core design positions\", `wiki\u002F` decision docs, and prior thread notes.\n4. **Mandatory adversarial self-refutation.** Fresh-context reviewer(s) try to REFUTE each surfaced finding by re-pinning, re-reproducing, and re-checking the decision record. They must also challenge any claim that a gap is *irreducible* by exhausting the mechanism's documented alternatives and testing plausible closures. Default to refuted when uncertain. Surface only survivors, each with reproduction evidence; never forward the raw breadth-pass output.\n5. **Tier + deliverable.** Opus at high+ effort for judgment AND refutation (a cheap tier may harvest breadth, but every item is Opus-verified). Thoroughness is two-dimensional: COVERAGE (enumerate the FULL surface from the pinned reference's own authoritative source) AND PRECISION (every item verified). Catalog → `wiki\u002Fresearch\u002F\u003Ctopic>.md` with all buckets explicit (real gaps \u002F confirmed-OK \u002F intentional-divergence); each finding records reproduction + decision-record cross-check + severity + confidence.\n\n## Orchestration shape\n\nEnumerate the full surface (coverage) → harvest candidate gaps → cross-check the decision record → reproduce each against the pinned real tool → adversarially refute in fresh context → surface ONLY survivors, with evidence.\n\nRun it with individually-dispatched agents — not a blind parallel Workflow fan-out that buries the gates.\n\n**Only a top-level session dispatches those agents.** If you are yourself a dispatched sub-agent, the repo-wide depth cap in `AGENTS.local.md` applies: run the gates INLINE and return. Gate 4's \"fresh context\" is then a fresh PASS, not a fresh agent — re-pin, re-run the fixture, and re-check the decision record yourself, defaulting to refuted when uncertain. An audit prong that cannot be refuted inline returns saying so rather than spawning a refuter.\n\n**When a finding is ACTIONED.** An audit is investigation-scope: it surfaces gaps, it does not land fixes. The moment a finding becomes a code change, verify it the standard way — an ad-hoc fixture sweep against a built binary, re-running the audit's own differential against the pinned reference, then an in-thread read of the diff. A parity fix touching a shared verb\u002Fflag dispatch path routinely ripples to sibling commands, which is one of the cases that earns escalating to a fresh-context `impact-analysis` pass — but that never substitutes for running the sibling commands and diffing them against the reference. Gate 4 asks whether a FINDING is real; impact analysis asks whether a FIX is safe.\n\n## Dispatch template (every audit sub-agent prompt must be self-contained)\n\n```\nYou are running a \u003CSCOPE> audit: find where nub diverges from \u003CREFERENCE> \u003CEXACT MAJOR> on \u003CSURFACE>.\nThis is an AUDIT — the deliverable is a CLEAN, VERIFIED list of REAL gaps. A single false positive is\nunacceptable. Follow all 5 gates; do not skip any.\n\nGATE 1 — PIN: The target is \u003CREFERENCE> \u003CEXACT MAJOR>. BEFORE reading anything, verify the version of\n  every reference you use: `git -C .repos\u002F\u003Ctool> describe --tags` and its package.json version, and\n  `\u003Ctool> --version` for any installed binary. If a checkout is the wrong major, check out the right\n  tag \u002F install the right version FIRST. State the verified versions at the top of your output.\n  If the AUDIT TARGET is a branch\u002FSHA of THIS repo (not a reference tool): `git fetch origin` FIRST,\n  pin `origin\u002F\u003Cbranch>@\u003Csha>` (NEVER a local worktree\u002Fbranch — it routinely lags origin), and verify\n  `git merge-base --is-ancestor \u003Csha> origin\u002F\u003Cbranch>` before reading. State the pinned SHA at the top.\nGATE 2 — EMPIRICAL: A gap is NOT a finding until you reproduce it by RUNNING \u003CREFERENCE> \u003CMAJOR> AND nub\n  on identical input and diffing the actual output. Source-reading and --help parsing are LEADS only.\n  Build a minimal differential fixture per candidate; capture both commands + both outputs.\nGATE 3 — DECISION RECORD: Drop any candidate that is a deprecated\u002Fremoved flag in \u003CREFERENCE> \u003CMAJOR>,\n  an npm-ism nub deliberately rejects, one of nub's intentional pnpm-compat divergences, or already\n  decided\u002Fbuilt. Cross-check AGENTS.md \"Core design positions\", wiki\u002F decision docs, and prior thread notes.\n  Deeply evaluate what has ALREADY been discussed — surfacing a settled call is as bad as a false positive.\nGATE 4 — REFUTE: After harvesting, re-verify every surviving candidate adversarially (try to REFUTE it:\n  re-pin, re-reproduce, re-check the record). Treat \"irreducible\" or \"cannot close\" as claims that also\n  require evidence: exhaust the documented mechanism surface and test plausible closures. Keep only\n  what survives, with its reproduction evidence.\nGATE 5 — COVERAGE + PRECISION: Enumerate the FULL surface from \u003CREFERENCE> \u003CMAJOR>'s own authoritative\n  source (its --help \u002F source), so nothing is missed; AND verify every surfaced item. Output ALL buckets:\n  real gaps \u002F confirmed-OK \u002F intentional-divergence. Each real finding: reproduction command + both\n  outputs + decision-record cross-check + severity + confidence.\n\nDeliverable: a catalog at wiki\u002Fresearch\u002F\u003Ctopic>.md (all buckets) + a tight triaged list of REAL gaps for\nthe maintainer. Investigation-scope — do NOT land fixes; surface findings recommend-only.\n```\n\nWhen an audit reveals a NEW pitfall not covered above, fold it into the gate it strengthens.\n",{"name":5,"metadata":24,"description":7},{"internal":25},true,"main","9b734566fd36ceed8379f67a92291bc68af60801",".claude\u002Fskills\u002Faudit-thread",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":36,"prompt":46,"zipAvailable":25},[37,40,43],{"tool":38,"command":39},"npx","npx skills add nubjs\u002Fnub --skill audit-thread",{"tool":41,"command":42},"bunx","bunx skills add nubjs\u002Fnub --skill audit-thread",{"tool":44,"command":45},"pnpm","pnpm dlx skills add nubjs\u002Fnub --skill audit-thread","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Faudit-thread\u002FSKILL.md",[],[49,55,61,68,75,82],{"skillNo":50,"name":51,"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":52,"categories":53,"keywords":54,"publishedAt":19},"01M758BSH88RVXBG8TPCT427TY","nub","https:\u002F\u002Fgithub.com\u002Fnubjs\u002Fnub\u002Fblob\u002Fmain\u002Fskills\u002Fnub\u002FSKILL.md",[],[],{"skillNo":56,"name":51,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"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":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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",[],[]]