[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79R07EZ44P2FNB5XM322JZF":3,"skill-same:01M79R07EZ44P2FNB5XM322JZF":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M79R07EZ44P2FNB5XM322JZF","deps",null,"Dependency hygiene review - for each declared package, whether it is imported at all, whether the standard library or an existing dependency already does its job, whether it is still maintained, and whether its license fits the project's. Reports findings against the manifest line, ordered by how decidable each one is, and never edits the manifest. The upgrade mode pre-flights a version bump against this repo's call sites and ends GO\u002FNO-GO. Use when the user asks to review dependencies, check what a package is for, audit the manifest, or ask whether an upgrade is safe.","AaravChadha\u002Facstack","AaravChadha","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F224610398?v=4","01M79QZCAGEMRNH32DKH6VC5RJ","01M79QZCB37TR94RNR32TM7YTV",2,"MIT","https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fdeps\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deps\ndescription: \"Dependency hygiene review - for each declared package, whether it is imported at all, whether the standard library or an existing dependency already does its job, whether it is still maintained, and whether its license fits the project's. Reports findings against the manifest line, ordered by how decidable each one is, and never edits the manifest. The upgrade mode pre-flights a version bump against this repo's call sites and ends GO\u002FNO-GO. Use when the user asks to review dependencies, check what a package is for, audit the manifest, or ask whether an upgrade is safe.\"\nargument-hint: \"[review | upgrade \u003Cpackage> \u003Ctarget-version> [\u003Cunpacked-target-dir>]]\"\nallowed-tools: Read, Grep, Glob, Bash(cat:*), Bash(ls:*), Bash(git ls-files:*), Bash(npm view:*)\n---\n\n# \u002Fdeps — what did we take on, and does it earn its place\n\nAgents add packages reflexively. Nothing else in this pack looks at what\naccumulated. This skill is read-only: it has no Edit, no Write, and no\ninstall or update command. It reports; the operator decides. Two modes:\n`review` (the default) asks whether each dependency earns its place;\n`upgrade` asks whether a version bump is safe to take.\n\n`Adjacent skills:` \u002Fsecure (vulnerabilities in what you depend on; this\ncovers whether you should depend on it) · \u002Fcontract-check (breaking changes\nin your own surface; this covers your suppliers) · \u002Fmigrate-check (the same\ngate shape, applied to the database).\n\n\u003C!-- acstack:runtime -->\nRun before the skill's steps — per invocation, not per session (4.36); failures degrade to markdown:\n```bash\nlink=\"$(readlink \"$HOME\u002F.claude\u002Fskills\u002Fhealth\" 2>\u002Fdev\u002Fnull || true)\"   # empty = not symlinked\npack=\"$(dirname \"$(dirname \"$link\")\")\"   # NEVER trust this unless $link was non-empty\nif [ \"${link#\u002F}\" != \"$link\" ] && [ -x \"$pack\u002Fbin\u002Facstack-config\" ] && ! \"$pack\u002Fbin\u002Facstack-config\" runtime | grep -q '=off'; then\n  \"$pack\u002Fbin\u002Facstack-config\" || true          # resolved keys, with sources\n  \"$pack\u002Fbin\u002Facstack-update-check\" || true    # ≤1 fetch\u002Fday; silent ONLY if already checked today\n  \"$pack\u002Fbin\u002Facstack-recall\" || true          # LEARNINGS.md + bug-class names, capped 3KB\nelse\n  echo \"runtime off — proceeding without recall\u002Fupdate-check\"\nfi\n```\n\u003C!-- \u002Facstack:runtime -->\n\n\u003C!-- acstack:principles -->\n## Operating principles\n\n- Be direct. Push back in writing when the plan or the user is wrong. No sycophancy.\n- Never delete a decision. Supersede it: `~~old~~ → **Verdict (YYYY-MM-DD):** new call — reason.`\n- Never fix, tune, or delete a test or eval case to raise a score. Log the miss honestly and leave the case unchanged.\n- Name exact things: regex patterns, function signatures, model names, before → after numbers. Never \"fixed bugs\".\n- Attribution: follow the project's `attribution` setting (default `none`) — no AI-tool mentions in generated docs, no attribution trailers in commits or PRs. Commit with explicit `-m`\u002F`-F` messages only.\n- Config: read `.claude\u002Facstack.md` at the project root (fall back to `~\u002F.claude\u002Facstack.md`) before acting. `## Settings` keys override pack defaults; a `## \u003Cskill-name>` section overrides both. Unknown keys and sections are ignored.\n- Docs: BRIEF.md (frozen seed) \u002F PLAN.md (living plan) \u002F JOURNAL.md (rolling journal). If the repo uses legacy names (PLANNING_PROMPT.md \u002F PLANNING.md \u002F STATUS.md), use those instead — never create both.\n- Recall: if `LEARNINGS.md` exists at the project root, read it before starting.\n- Conduct: follow the `acstack-conduct` block in this repo's AGENTS.md — the word is the mode; the user sets the pace.\n- Hackathon lane: if the project's AGENTS.md carries the `acstack:hackathon-lane` block, only `\u002Fdo` changes the repository during the event. Any other skill that would write a tracked file, commit or push says what it would have done and stops; a change that is not a task goes through the lane's operator route.\n\u003C!-- \u002Facstack:principles -->\n\n## Mode: review (the default)\n\nFour checks, and **the order is the point**. They are listed most-decidable\nfirst, and the report must preserve that order and that framing — a judgment\ncall printed beside a fact, in the same voice, reads as a fact.\n\n### 1. Never imported — decidable, stated flatly\n\nFor every declared dependency, search the tree for an import, require, or\nother use site. A package with zero use sites is dead weight: the finding is\ncertain, and it is the only one stated without hedging.\n\nSearch the source, not the lockfile. Exclude the manifest itself — a package\nnaming itself in `package.json` is not a use site. Report the package, its\nmanifest line, and the fact that no site was found.\n\n### 2. The standard library already does this — evidence, then judgment\n\nName the stdlib call that replaces it, so the reader can disagree. \"This is\n`Object.assign`\" is checkable; \"this seems unnecessary\" is not.\n\nOnly claim it when the replacement is a genuine one-liner. A package that\nhandles edge cases the stdlib call does not is a real dependency, and saying\notherwise burns the reader's trust in the other three findings.\n\n### 3. Unmaintained — a date, never an adjective\n\nRead the registry (`npm view \u003Cpkg> time.modified`) and report the **date**.\nThe bar is no release in over two years; state the date and let the reader\napply their own bar.\n\n**If the registry cannot be reached, say the check did not run.** Do not\ninfer staleness from a version number, a lockfile, or vibes. A skipped check\nnamed is honest; a guessed one is the confident-wrong answer this pack\nexists to prevent.\n\n### 4. License conflict — both licenses named\n\nRead the project's declared license and each dependency's from its installed\nmetadata. Report the pair — `project MIT vs dep GPL-3.0` — never a verdict\nlike \"incompatible\" on its own. Licence compatibility is a legal judgment;\nthe skill's job is to surface the pair that needs one.\n\n## Mode: upgrade\n\n`\u002Fdeps upgrade \u003Cpackage> \u003Ctarget-version> [\u003Cunpacked-target-dir>]` — is this\nversion bump safe to take? Upgrading is a breaking-change problem, not a\njustification problem:\nthe question is which changelog entries between the pinned and target\nversions break a call site **this repo actually has**. A breaking change in\nan API nothing here calls is not a blocker, and saying so is the value.\n\nFull procedure: `references\u002Fupgrade.md` — where the pinned version, the\ntarget's metadata and its changelog are read from (a local tree or the\nregistry; this skill has no network tool beyond `npm view`, so a changelog\nis never fetched), the classification table, transitive bumps, the rollback\npin, and the report shape. The report anatomy is\n`..\u002Fmigrate-check\u002Freferences\u002Fgate-shape.md`: verdict first, every entry\nclassified, a safe alternative per destructive row, never fix, and state\nwhat the verdict does not cover.\n\n**Verdict rule.** `NO-GO` when any breaking entry has an affected call site\nand no migration note names that site and its replacement; otherwise `GO`.\nA migration note is a concrete plan per site — \"we'll deal with it\" is not\none. A changelog that cannot be read is a `NO-GO` naming the missing fact,\nnever a `GO` on the assumption that nothing changed.\n\n## Report\n\nVerdict first: in review, the count of findings or `no findings`; in\nupgrade, `GO` or `NO-GO` as the literal first line. The review report then\ncarries one section per check that fired, each finding with **the manifest\nline**. A dependency that passes all four is not listed — but the report\nstates how many were examined, so a reader can tell a clean manifest from a\nshort one. The upgrade report's sections are listed in\n`references\u002Fupgrade.md`.\n\nState what was not checked: dependencies whose registry lookup failed,\necosystems the pass did not cover, and transitive dependencies, which are\nout of scope here.\n\n## Hard rules\n\n- Never edits the manifest, the lockfile, or any dependency.\n- Check 1 is the only one stated as fact; 2 through 4 carry their evidence so\n  the reader can overrule them.\n- No finding without its manifest line.\n- A registry lookup that failed is reported as not-run, never as a pass and\n  never as staleness.\n- `no findings` means the four checks found nothing, not that the dependency\n  set is good.\n- Upgrade: the word BREAKING decides nothing — call sites decide, and every\n  affected one is cited `file:line`.\n- Upgrade: the rollback pin is the exact installed version, named in every\n  report; a manifest range is not a pin, and is reported as a range.\n","# \u002Fdeps — what did we take on, and does it earn its place\n\nAgents add packages reflexively. Nothing else in this pack looks at what\naccumulated. This skill is read-only: it has no Edit, no Write, and no\ninstall or update command. It reports; the operator decides. Two modes:\n`review` (the default) asks whether each dependency earns its place;\n`upgrade` asks whether a version bump is safe to take.\n\n`Adjacent skills:` \u002Fsecure (vulnerabilities in what you depend on; this\ncovers whether you should depend on it) · \u002Fcontract-check (breaking changes\nin your own surface; this covers your suppliers) · \u002Fmigrate-check (the same\ngate shape, applied to the database).\n\n\u003C!-- acstack:runtime -->\nRun before the skill's steps — per invocation, not per session (4.36); failures degrade to markdown:\n```bash\nlink=\"$(readlink \"$HOME\u002F.claude\u002Fskills\u002Fhealth\" 2>\u002Fdev\u002Fnull || true)\"   # empty = not symlinked\npack=\"$(dirname \"$(dirname \"$link\")\")\"   # NEVER trust this unless $link was non-empty\nif [ \"${link#\u002F}\" != \"$link\" ] && [ -x \"$pack\u002Fbin\u002Facstack-config\" ] && ! \"$pack\u002Fbin\u002Facstack-config\" runtime | grep -q '=off'; then\n  \"$pack\u002Fbin\u002Facstack-config\" || true          # resolved keys, with sources\n  \"$pack\u002Fbin\u002Facstack-update-check\" || true    # ≤1 fetch\u002Fday; silent ONLY if already checked today\n  \"$pack\u002Fbin\u002Facstack-recall\" || true          # LEARNINGS.md + bug-class names, capped 3KB\nelse\n  echo \"runtime off — proceeding without recall\u002Fupdate-check\"\nfi\n```\n\u003C!-- \u002Facstack:runtime -->\n\n\u003C!-- acstack:principles -->\n## Operating principles\n\n- Be direct. Push back in writing when the plan or the user is wrong. No sycophancy.\n- Never delete a decision. Supersede it: `~~old~~ → **Verdict (YYYY-MM-DD):** new call — reason.`\n- Never fix, tune, or delete a test or eval case to raise a score. Log the miss honestly and leave the case unchanged.\n- Name exact things: regex patterns, function signatures, model names, before → after numbers. Never \"fixed bugs\".\n- Attribution: follow the project's `attribution` setting (default `none`) — no AI-tool mentions in generated docs, no attribution trailers in commits or PRs. Commit with explicit `-m`\u002F`-F` messages only.\n- Config: read `.claude\u002Facstack.md` at the project root (fall back to `~\u002F.claude\u002Facstack.md`) before acting. `## Settings` keys override pack defaults; a `## \u003Cskill-name>` section overrides both. Unknown keys and sections are ignored.\n- Docs: BRIEF.md (frozen seed) \u002F PLAN.md (living plan) \u002F JOURNAL.md (rolling journal). If the repo uses legacy names (PLANNING_PROMPT.md \u002F PLANNING.md \u002F STATUS.md), use those instead — never create both.\n- Recall: if `LEARNINGS.md` exists at the project root, read it before starting.\n- Conduct: follow the `acstack-conduct` block in this repo's AGENTS.md — the word is the mode; the user sets the pace.\n- Hackathon lane: if the project's AGENTS.md carries the `acstack:hackathon-lane` block, only `\u002Fdo` changes the repository during the event. Any other skill that would write a tracked file, commit or push says what it would have done and stops; a change that is not a task goes through the lane's operator route.\n\u003C!-- \u002Facstack:principles -->\n\n## Mode: review (the default)\n\nFour checks, and **the order is the point**. They are listed most-decidable\nfirst, and the report must preserve that order and that framing — a judgment\ncall printed beside a fact, in the same voice, reads as a fact.\n\n### 1. Never imported — decidable, stated flatly\n\nFor every declared dependency, search the tree for an import, require, or\nother use site. A package with zero use sites is dead weight: the finding is\ncertain, and it is the only one stated without hedging.\n\nSearch the source, not the lockfile. Exclude the manifest itself — a package\nnaming itself in `package.json` is not a use site. Report the package, its\nmanifest line, and the fact that no site was found.\n\n### 2. The standard library already does this — evidence, then judgment\n\nName the stdlib call that replaces it, so the reader can disagree. \"This is\n`Object.assign`\" is checkable; \"this seems unnecessary\" is not.\n\nOnly claim it when the replacement is a genuine one-liner. A package that\nhandles edge cases the stdlib call does not is a real dependency, and saying\notherwise burns the reader's trust in the other three findings.\n\n### 3. Unmaintained — a date, never an adjective\n\nRead the registry (`npm view \u003Cpkg> time.modified`) and report the **date**.\nThe bar is no release in over two years; state the date and let the reader\napply their own bar.\n\n**If the registry cannot be reached, say the check did not run.** Do not\ninfer staleness from a version number, a lockfile, or vibes. A skipped check\nnamed is honest; a guessed one is the confident-wrong answer this pack\nexists to prevent.\n\n### 4. License conflict — both licenses named\n\nRead the project's declared license and each dependency's from its installed\nmetadata. Report the pair — `project MIT vs dep GPL-3.0` — never a verdict\nlike \"incompatible\" on its own. Licence compatibility is a legal judgment;\nthe skill's job is to surface the pair that needs one.\n\n## Mode: upgrade\n\n`\u002Fdeps upgrade \u003Cpackage> \u003Ctarget-version> [\u003Cunpacked-target-dir>]` — is this\nversion bump safe to take? Upgrading is a breaking-change problem, not a\njustification problem:\nthe question is which changelog entries between the pinned and target\nversions break a call site **this repo actually has**. A breaking change in\nan API nothing here calls is not a blocker, and saying so is the value.\n\nFull procedure: `references\u002Fupgrade.md` — where the pinned version, the\ntarget's metadata and its changelog are read from (a local tree or the\nregistry; this skill has no network tool beyond `npm view`, so a changelog\nis never fetched), the classification table, transitive bumps, the rollback\npin, and the report shape. The report anatomy is\n`..\u002Fmigrate-check\u002Freferences\u002Fgate-shape.md`: verdict first, every entry\nclassified, a safe alternative per destructive row, never fix, and state\nwhat the verdict does not cover.\n\n**Verdict rule.** `NO-GO` when any breaking entry has an affected call site\nand no migration note names that site and its replacement; otherwise `GO`.\nA migration note is a concrete plan per site — \"we'll deal with it\" is not\none. A changelog that cannot be read is a `NO-GO` naming the missing fact,\nnever a `GO` on the assumption that nothing changed.\n\n## Report\n\nVerdict first: in review, the count of findings or `no findings`; in\nupgrade, `GO` or `NO-GO` as the literal first line. The review report then\ncarries one section per check that fired, each finding with **the manifest\nline**. A dependency that passes all four is not listed — but the report\nstates how many were examined, so a reader can tell a clean manifest from a\nshort one. The upgrade report's sections are listed in\n`references\u002Fupgrade.md`.\n\nState what was not checked: dependencies whose registry lookup failed,\necosystems the pass did not cover, and transitive dependencies, which are\nout of scope here.\n\n## Hard rules\n\n- Never edits the manifest, the lockfile, or any dependency.\n- Check 1 is the only one stated as fact; 2 through 4 carry their evidence so\n  the reader can overrule them.\n- No finding without its manifest line.\n- A registry lookup that failed is reported as not-run, never as a pass and\n  never as staleness.\n- `no findings` means the four checks found nothing, not that the dependency\n  set is good.\n- Upgrade: the word BREAKING decides nothing — call sites decide, and every\n  affected one is cited `file:line`.\n- Upgrade: the rollback pin is the exact installed version, named in every\n  report; a manifest range is not a pin, and is reported as a range.\n",{"name":5,"description":7,"allowed-tools":23,"argument-hint":24},"Read, Grep, Glob, Bash(cat:*), Bash(ls:*), Bash(git ls-files:*), Bash(npm view:*)","[review | upgrade \u003Cpackage> \u003Ctarget-version> [\u003Cunpacked-target-dir>]]","main","6b5be39937ce3823cf8f58c68aadcfdfda839fa0","skills\u002Fdeps",0,"https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack","https:\u002F\u002Fgithub.com\u002FAaravChadha","2026-09-28 13:07:41",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add AaravChadha\u002Facstack --skill deps",{"tool":38,"command":39},"bunx","bunx skills add AaravChadha\u002Facstack --skill deps",{"tool":41,"command":42},"pnpm","pnpm dlx skills add AaravChadha\u002Facstack --skill deps","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fdeps\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fupgrade.md","REFERENCE","参考文档",6356,"https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fdeps\u002Freferences\u002Fupgrade.md",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M79R3MBE63G66XVKHV652YAD","why","Decision archaeology - answers why the code, config, or plan is the way it is by searching the record in a fixed order: BRIEF constraints, dated PLAN decisions, JOURNAL entries, then git history. Stops at the first real answer, cites it with a date, and says no recorded rationale rather than inventing one. Use when someone asks why something is this way, why a choice was made, or where a decision is written down.","https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M79R3G7EA313SYFS30H1K51A","verify","Audit a completion claim made by someone else - another session, agent, or teammate - against the running system rather than the diff. Re-derives what the claim's acceptance demands, runs it, and returns CONFIRMED, OVERSTATED, FALSE or UNVERIFIABLE with the command and its output. Never fixes, never edits the claim or the acceptance. Use when handed a \"done\", \"all green\", \"merged\" or \"it works\" you did not produce yourself.","https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M79R3CPD2F05EKE9N8XCMM90","triage","Backlog hygiene sweep - stale items, duplicate pairs, missing acceptance criteria, unblocked-but-unassigned work, and milestone burn, delivered as a report first with only user-approved actions applied. Works on GitHub Issues in tickets mode and on PLAN.md checkboxes in document mode. Use when the user asks to triage, groom, or clean up the backlog or the plan's open tasks.","https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M79R395S4TS1XENQWWCSBT56","ticket","Capture a brain-dump as a well-formed work item - verb-first title, acceptance criteria, file paths when known, an out-of-scope line. Files a GitHub issue in tickets mode or appends a numbered PLAN.md task in document mode; unknowns are marked TBD, never invented. Use when the user brain-dumps an idea, bug, or task to capture for later, or asks to ticket, file, or note something as work.","https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fticket\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M79R358JKQ1EB3TQKT2MPSB6","ship","Branch-level release with five gates before the act - clean-state, tests, eval-vs-target, docs drift, and attribution sweep; any failing gate stops the release with its output. Then push, and under push: branch-pr open a report-shaped PR wiring the issue-closing reference in tickets mode or PLAN task IDs in document mode. Use when the user asks to ship, release, cut, or open the PR for a feature or branch.","https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fship\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M79R2ZXGVB7W1J8ZH8TRGWDN","secure","Security review with a confidence gate - a finding exists only with a concrete exploit scenario and a high\u002Fmedium\u002Flow confidence rating; everything else goes to a worth-hardening list, never inflated. Sweeps five surfaces: auth gates, secrets hygiene, injection and unsafe sinks, unsafe deserialization\u002Fcrypto\u002Ftransport, and LLM tool-use trust boundaries. Reports only, never fixes. Use when the user asks for a security review or to check vulnerabilities, secrets, or auth.","https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fsecure\u002FSKILL.md",[],[]]