[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79R0KQVRRHGH36EX4Y3K6WB":3,"skill-same:01M79R0KQVRRHGH36EX4Y3K6WB":56},{"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},"01M79R0KQVRRHGH36EX4Y3K6WB","design-audit",null,"Static UI convention check - off-palette colors and wrong product-name casing, dishonest data labels (AI-generated or mock data shown as real), AI-slop (lorem remnants, hedge copy, emoji headings, uniform gradient grids), and client-facing language leaks. Reports file:line findings with fixes; conventions come from config layered over pack defaults. Use when the user asks to design-audit or check UI conventions, polish, or copy.","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\u002Fdesign-audit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: design-audit\ndescription: Static UI convention check - off-palette colors and wrong product-name casing, dishonest data labels (AI-generated or mock data shown as real), AI-slop (lorem remnants, hedge copy, emoji headings, uniform gradient grids), and client-facing language leaks. Reports file:line findings with fixes; conventions come from config layered over pack defaults. Use when the user asks to design-audit or check UI conventions, polish, or copy.\nargument-hint: \"[path | notes]\"\nallowed-tools: Read, Grep, Glob, Bash(grep:*), Bash(ls:*)\n---\n\n# \u002Fdesign-audit — conventions, honesty, and slop\n\nA static pass over the UI's code and copy for the things reviewers skim\npast: colors off the palette, mock data wearing a real-data face, the\ntells of machine-generated filler, and internal language leaking to the\nuser. Nothing is rendered — a rendered mode arrives with the browser\nprobe (same deferral as \u002Fqa, decision 2026-07-27).\n\n`Adjacent skills:` \u002Fdesign (the generative half — it produces UI, this\ninspects it; \u002Fdesign-audit stays purely detective and never generates) ·\n\u002Fqa (behavior; \u002Fdesign-audit is look and language) · \u002Faudit code\n(correctness; \u002Fdesign-audit is convention) · \u002Fsecure (exploitability;\n\u002Fdesign-audit flags leaked internals as language, not as a\nvulnerability).\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## Conventions come from config\n\nRead a `## design-audit` section from `.claude\u002Facstack.md`:\n\n- `palette:` — the allowed hex values; colors outside it are findings.\n- `banned-palette:` — hex values that are findings wherever they appear,\n  even if someone adds them to `palette`. Defaults to the violet-gradient\n  family that generated UI reaches for (`references\u002Fai-tells.md`).\n- `product-names:` — exact casings; other casings are findings.\n\nConfig always wins over the brand-neutral defaults in\n`references\u002Fdesign-conventions.md`. No config → use the defaults and say\nso in scope, naming what the reader is and is NOT getting: \"no palette\nconfigured; flagged raw-hex sprawl and the dated default-look clusters\n(`references\u002Fai-tells.md` Config), **not** brand conformance — nothing here\nknows what your brand is.\" Without a `palette:` there is no allowed set, so\nconformance is unanswerable rather than merely unchecked; saying only\n\"flagged obvious sprawl\" undersold both halves.\n\nWith `palette:` configured, the cluster check is suppressed: a look a\nproject chose and declared is a decision, not a defect.\n\n## The four checks\n\nGrep families and the default convention set live in\n`references\u002Fdesign-conventions.md`. Apply them with the Grep tool — this\nskill grants no shell `git grep`. No Grep tool? Use `grep -rnE`, never\n`git grep`.\n\n1. **Palette + branding.** Hardcoded colors outside the configured\n   palette; product names in the wrong casing; spacing\u002Ffont literals\n   diverging from the project's own design tokens where tokens exist\n   (a raw `#3b82f6` beside a `--color-primary` token is the finding).\n2. **Honest data labels.** AI-generated, illustrative, sample, or mock\n   data shown without saying so; a chart of fabricated numbers presented\n   as real. The honest-measurement principle applied to pixels — the\n   same stance \u002Faudit eval takes toward scores.\n3. **Slop detection.** Placeholder\u002Florem remnants, emoji-decorated\n   headings in product UI, uniform gradient-card grids, hedge copy\n   (\"simply\", \"just\", \"seamlessly\", \"powerful\", \"effortlessly\"),\n   user-visible debug strings (`console.log`, `TODO`, `FIXME` in\n   rendered text).\n4. **Client-facing language.** Internal jargon or codenames in UI\n   strings; error messages exposing internals (stack traces, table\n   names, file paths) — cross-referenced to \u002Fsecure when they leak\n   system detail; inconsistent terminology for the same object across\n   screens (\"order\" here, \"purchase\" there).\n5. **AI tells.** The signature of generated UI — violet gradients,\n   eyebrows, fabricated statistics, motion and materials violations,\n   interaction-feel misses. Rules and greps in `references\u002Fai-tells.md`.\n\n**Severity order is fixed: accessibility, then honesty, then everything\nelse** — regardless of how many hits each class produced. Unreadable text\nand a fabricated statistic are harm; a gradient is embarrassment. One tell\nis a choice; the full set is a signature, so say which it was.\n\n**No UI files in the path → say so and stop.** If the target contains no\nmarkup, styles, or component files, there is nothing to audit; report the\npath, what was looked for, and stop. A \"CLEAN\" verdict over a directory\nwith no UI in it is a true statement that reads as a false reassurance.\n\n## Stance and report shape\n\nRead-only: findings and suggested fixes, never applied edits. First\nline is the verdict: `CLEAN` or `\u003CN> findings`. Then:\n\n- **Findings**, grouped by the four checks: `file:line` · the\n  convention violated · the suggested fix.\n- **`Safety checks:`** the exact greps run.\n- **Scope:** paths covered; static-only stated; whether a palette was\n  configured or defaults were used.\n","# \u002Fdesign-audit — conventions, honesty, and slop\n\nA static pass over the UI's code and copy for the things reviewers skim\npast: colors off the palette, mock data wearing a real-data face, the\ntells of machine-generated filler, and internal language leaking to the\nuser. Nothing is rendered — a rendered mode arrives with the browser\nprobe (same deferral as \u002Fqa, decision 2026-07-27).\n\n`Adjacent skills:` \u002Fdesign (the generative half — it produces UI, this\ninspects it; \u002Fdesign-audit stays purely detective and never generates) ·\n\u002Fqa (behavior; \u002Fdesign-audit is look and language) · \u002Faudit code\n(correctness; \u002Fdesign-audit is convention) · \u002Fsecure (exploitability;\n\u002Fdesign-audit flags leaked internals as language, not as a\nvulnerability).\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## Conventions come from config\n\nRead a `## design-audit` section from `.claude\u002Facstack.md`:\n\n- `palette:` — the allowed hex values; colors outside it are findings.\n- `banned-palette:` — hex values that are findings wherever they appear,\n  even if someone adds them to `palette`. Defaults to the violet-gradient\n  family that generated UI reaches for (`references\u002Fai-tells.md`).\n- `product-names:` — exact casings; other casings are findings.\n\nConfig always wins over the brand-neutral defaults in\n`references\u002Fdesign-conventions.md`. No config → use the defaults and say\nso in scope, naming what the reader is and is NOT getting: \"no palette\nconfigured; flagged raw-hex sprawl and the dated default-look clusters\n(`references\u002Fai-tells.md` Config), **not** brand conformance — nothing here\nknows what your brand is.\" Without a `palette:` there is no allowed set, so\nconformance is unanswerable rather than merely unchecked; saying only\n\"flagged obvious sprawl\" undersold both halves.\n\nWith `palette:` configured, the cluster check is suppressed: a look a\nproject chose and declared is a decision, not a defect.\n\n## The four checks\n\nGrep families and the default convention set live in\n`references\u002Fdesign-conventions.md`. Apply them with the Grep tool — this\nskill grants no shell `git grep`. No Grep tool? Use `grep -rnE`, never\n`git grep`.\n\n1. **Palette + branding.** Hardcoded colors outside the configured\n   palette; product names in the wrong casing; spacing\u002Ffont literals\n   diverging from the project's own design tokens where tokens exist\n   (a raw `#3b82f6` beside a `--color-primary` token is the finding).\n2. **Honest data labels.** AI-generated, illustrative, sample, or mock\n   data shown without saying so; a chart of fabricated numbers presented\n   as real. The honest-measurement principle applied to pixels — the\n   same stance \u002Faudit eval takes toward scores.\n3. **Slop detection.** Placeholder\u002Florem remnants, emoji-decorated\n   headings in product UI, uniform gradient-card grids, hedge copy\n   (\"simply\", \"just\", \"seamlessly\", \"powerful\", \"effortlessly\"),\n   user-visible debug strings (`console.log`, `TODO`, `FIXME` in\n   rendered text).\n4. **Client-facing language.** Internal jargon or codenames in UI\n   strings; error messages exposing internals (stack traces, table\n   names, file paths) — cross-referenced to \u002Fsecure when they leak\n   system detail; inconsistent terminology for the same object across\n   screens (\"order\" here, \"purchase\" there).\n5. **AI tells.** The signature of generated UI — violet gradients,\n   eyebrows, fabricated statistics, motion and materials violations,\n   interaction-feel misses. Rules and greps in `references\u002Fai-tells.md`.\n\n**Severity order is fixed: accessibility, then honesty, then everything\nelse** — regardless of how many hits each class produced. Unreadable text\nand a fabricated statistic are harm; a gradient is embarrassment. One tell\nis a choice; the full set is a signature, so say which it was.\n\n**No UI files in the path → say so and stop.** If the target contains no\nmarkup, styles, or component files, there is nothing to audit; report the\npath, what was looked for, and stop. A \"CLEAN\" verdict over a directory\nwith no UI in it is a true statement that reads as a false reassurance.\n\n## Stance and report shape\n\nRead-only: findings and suggested fixes, never applied edits. First\nline is the verdict: `CLEAN` or `\u003CN> findings`. Then:\n\n- **Findings**, grouped by the four checks: `file:line` · the\n  convention violated · the suggested fix.\n- **`Safety checks:`** the exact greps run.\n- **Scope:** paths covered; static-only stated; whether a palette was\n  configured or defaults were used.\n",{"name":5,"description":7,"allowed-tools":23,"argument-hint":24},"Read, Grep, Glob, Bash(grep:*), Bash(ls:*)","[path | notes]","main","6b5be39937ce3823cf8f58c68aadcfdfda839fa0","skills\u002Fdesign-audit",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 design-audit",{"tool":38,"command":39},"bunx","bunx skills add AaravChadha\u002Facstack --skill design-audit",{"tool":41,"command":42},"pnpm","pnpm dlx skills add AaravChadha\u002Facstack --skill design-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fdesign-audit\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fai-tells.md","REFERENCE","参考文档",16773,"https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fdesign-audit\u002Freferences\u002Fai-tells.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdesign-conventions.md",4942,"https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fdesign-audit\u002Freferences\u002Fdesign-conventions.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"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":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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",[],[]]