[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79R2WPCWE214XBCZB1KKQ9M":3,"skill-same:01M79R2WPCWE214XBCZB1KKQ9M":51},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M79R2WPCWE214XBCZB1KKQ9M","retro",null,"Trend review across many sessions - velocity vs planned dates, eval-score trend toward target, failure-category trends from journal triage and investigations, and a status check on every open PLAN risk. Reads JOURNAL\u002FPLAN\u002Feval history, writes a dated retro entry into JOURNAL.md. Use when the user asks for a retro, a weekly review, or a phase-end wrap-up.","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\u002Fretro\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: retro\ndescription: Trend review across many sessions - velocity vs planned dates, eval-score trend toward target, failure-category trends from journal triage and investigations, and a status check on every open PLAN risk. Reads JOURNAL\u002FPLAN\u002Feval history, writes a dated retro entry into JOURNAL.md. Use when the user asks for a retro, a weekly review, or a phase-end wrap-up.\nargument-hint: \"[week | phase N | notes]\"\n---\n\n# \u002Fretro — the trend across sessions\n\n\u002Fjournal records one session; \u002Fretro reads many and says where the line\nis heading. Not a summary — a trend, with the numbers that make \"we're\nslipping\" or \"the eval is climbing\" a fact instead of a feeling.\n\n`Adjacent skills:` \u002Fjournal (one session's worklog; \u002Fretro trends across\nmany) · \u002Faudit eval (one report's honesty; \u002Fretro the trend across runs)\n· \u002Ftriage (grooms the backlog; \u002Fretro reviews the trajectory).\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**One document set.** Resolve exactly ONE BRIEF\u002FPLAN\u002FJOURNAL set and name\nits path in the report's scope line. If more than one candidate set exists\n— a monorepo, nested products, an `apps\u002F*` tree each with its own docs —\nlist the candidates and STOP. Never pick one silently: a confident answer\nabout the wrong product is worse than no answer (conduct rule 8).\n\n## Inputs\n\n- JOURNAL.md entries since the last retro (the window; `week` or\n  `phase N` in the argument narrows it).\n- PLAN.md: planned phase dates, exit criteria, the open risks and items.\n- Eval artifacts when present: `eval\u002Fspec.md` targets and the result\n  files across runs.\n- `git log` over the window for commit \u002F checkbox velocity.\n\n**Retrieve by window, don't ingest the file.** Past roughly 500 lines,\nJOURNAL.md is read headings-first: scan the `###` entry headings and their\ndates, select the ones inside the window (`week`, `phase N`, or since the\nlast retro), and fetch full text for those only. Entries outside the window\nare not evidence for this retro — reading them wastes budget and, worse,\ninvites a trend claim drawn from data the window explicitly excluded. State\nthe window and how many entries fell inside it, so a reader can tell a\nfive-entry trend from a one-entry anecdote.\n\n**Missing inputs are named, never worked around.** No JOURNAL.md → stop:\na retro is a trend across recorded sessions, and without the record there\nis no trend, only the git log's shape — say that and point at `\u002Fjournal`.\nNo PLAN.md → run the trends that only need the journal and state that\nvelocity-vs-plan and the risk review were skipped for want of the plan. A\nwindow containing one entry is reported as one entry, not extrapolated\ninto a trend.\n\n## Sections\n\nThe four sections live in `references\u002Fretro-sections.md` with their\nquestion sets and honest-degradation lines. Lead with a verdict:\n`on plan` \u002F `slipping — \u003Cwhere>` \u002F `off plan`.\n\n1. **Velocity vs plan.** Planned phase dates vs actual; boxes or issues\n   closed per period vs the plan's implied rate; slippage named in days\n   with the cause pulled from journal entries, not guessed.\n2. **Eval trend.** Headline score per run across the window, per-category\n   direction, distance to target. No eval history → one honest line and\n   the section ends.\n3. **Failure-category trends.** Counts by class from the journal's eval\n   triage sections and \u002Finvestigate write-ups; a class recurring 2+\n   times is named as a \u002Flearn promotion candidate.\n4. **Risk review.** Each open PLAN risk: still real \u002F materialized \u002F\n   retired, with evidence. New risks are proposed as dated PLAN edits —\n   proposed, never applied by \u002Fretro.\n\n## Not in wave 3\n\nNo skill-usage \u002F telemetry section — it arrives with the local\ntelemetry it reads (PLAN task 4.3, moved to wave 4.5 post-launch by the\n2026-07-29 split). Don't emit a placeholder for it; its absence is\ncorrect, not a gap.\n\n## Output\n\nAppend to JOURNAL.md as a dated entry under `## Key decisions and\njourney`, newest first:\n`### Retro (YYYY-MM-DD — \u003Cwindow>)`. **This is the same anchor `\u002Fjournal`\nwrites at**, so a retro and a journal entry from two concurrent sessions\nconflict — which is the safe outcome, and is resolved by keeping both\nentries rather than choosing one (see `\u002Fjournal` step 2). A journal without that heading —\nhand-kept rather than seeded from \u002Fjournal's template — takes the entry\nper that journal's own convention: appended where its entries actually\ngo (top of a newest-first record, bottom of a chronological one), with\nthe divergence named inside the entry; never scaffold the pack's\nskeleton into a journal the project keeps by hand, and never impose the\npack's ordering on it. Commit using the project's\n`journal-commit-format` (pack default `Journal \u003Cdate>: \u003Csummary>`) with\n`retro — \u003Csummary>` as the summary, brief body, attribution per config.\nPLAN edits the retro proposes are listed for the user to apply\nvia `\u002Fplan replan` — \u002Fretro writes the journal, not the plan.\n\n## Tickets-mode delta\n\nVelocity becomes closed issues + milestone burn via\n`gh issue list --state closed` and the milestone API; failure classes\nare additionally mined from issue labels and closing comments.\nPreconditions — `gh` installed, `gh auth status` succeeding, and a\nGitHub remote present. Any failure names WHICH one failed and offers\ndocument mode; never guess.\n","# \u002Fretro — the trend across sessions\n\n\u002Fjournal records one session; \u002Fretro reads many and says where the line\nis heading. Not a summary — a trend, with the numbers that make \"we're\nslipping\" or \"the eval is climbing\" a fact instead of a feeling.\n\n`Adjacent skills:` \u002Fjournal (one session's worklog; \u002Fretro trends across\nmany) · \u002Faudit eval (one report's honesty; \u002Fretro the trend across runs)\n· \u002Ftriage (grooms the backlog; \u002Fretro reviews the trajectory).\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**One document set.** Resolve exactly ONE BRIEF\u002FPLAN\u002FJOURNAL set and name\nits path in the report's scope line. If more than one candidate set exists\n— a monorepo, nested products, an `apps\u002F*` tree each with its own docs —\nlist the candidates and STOP. Never pick one silently: a confident answer\nabout the wrong product is worse than no answer (conduct rule 8).\n\n## Inputs\n\n- JOURNAL.md entries since the last retro (the window; `week` or\n  `phase N` in the argument narrows it).\n- PLAN.md: planned phase dates, exit criteria, the open risks and items.\n- Eval artifacts when present: `eval\u002Fspec.md` targets and the result\n  files across runs.\n- `git log` over the window for commit \u002F checkbox velocity.\n\n**Retrieve by window, don't ingest the file.** Past roughly 500 lines,\nJOURNAL.md is read headings-first: scan the `###` entry headings and their\ndates, select the ones inside the window (`week`, `phase N`, or since the\nlast retro), and fetch full text for those only. Entries outside the window\nare not evidence for this retro — reading them wastes budget and, worse,\ninvites a trend claim drawn from data the window explicitly excluded. State\nthe window and how many entries fell inside it, so a reader can tell a\nfive-entry trend from a one-entry anecdote.\n\n**Missing inputs are named, never worked around.** No JOURNAL.md → stop:\na retro is a trend across recorded sessions, and without the record there\nis no trend, only the git log's shape — say that and point at `\u002Fjournal`.\nNo PLAN.md → run the trends that only need the journal and state that\nvelocity-vs-plan and the risk review were skipped for want of the plan. A\nwindow containing one entry is reported as one entry, not extrapolated\ninto a trend.\n\n## Sections\n\nThe four sections live in `references\u002Fretro-sections.md` with their\nquestion sets and honest-degradation lines. Lead with a verdict:\n`on plan` \u002F `slipping — \u003Cwhere>` \u002F `off plan`.\n\n1. **Velocity vs plan.** Planned phase dates vs actual; boxes or issues\n   closed per period vs the plan's implied rate; slippage named in days\n   with the cause pulled from journal entries, not guessed.\n2. **Eval trend.** Headline score per run across the window, per-category\n   direction, distance to target. No eval history → one honest line and\n   the section ends.\n3. **Failure-category trends.** Counts by class from the journal's eval\n   triage sections and \u002Finvestigate write-ups; a class recurring 2+\n   times is named as a \u002Flearn promotion candidate.\n4. **Risk review.** Each open PLAN risk: still real \u002F materialized \u002F\n   retired, with evidence. New risks are proposed as dated PLAN edits —\n   proposed, never applied by \u002Fretro.\n\n## Not in wave 3\n\nNo skill-usage \u002F telemetry section — it arrives with the local\ntelemetry it reads (PLAN task 4.3, moved to wave 4.5 post-launch by the\n2026-07-29 split). Don't emit a placeholder for it; its absence is\ncorrect, not a gap.\n\n## Output\n\nAppend to JOURNAL.md as a dated entry under `## Key decisions and\njourney`, newest first:\n`### Retro (YYYY-MM-DD — \u003Cwindow>)`. **This is the same anchor `\u002Fjournal`\nwrites at**, so a retro and a journal entry from two concurrent sessions\nconflict — which is the safe outcome, and is resolved by keeping both\nentries rather than choosing one (see `\u002Fjournal` step 2). A journal without that heading —\nhand-kept rather than seeded from \u002Fjournal's template — takes the entry\nper that journal's own convention: appended where its entries actually\ngo (top of a newest-first record, bottom of a chronological one), with\nthe divergence named inside the entry; never scaffold the pack's\nskeleton into a journal the project keeps by hand, and never impose the\npack's ordering on it. Commit using the project's\n`journal-commit-format` (pack default `Journal \u003Cdate>: \u003Csummary>`) with\n`retro — \u003Csummary>` as the summary, brief body, attribution per config.\nPLAN edits the retro proposes are listed for the user to apply\nvia `\u002Fplan replan` — \u002Fretro writes the journal, not the plan.\n\n## Tickets-mode delta\n\nVelocity becomes closed issues + milestone burn via\n`gh issue list --state closed` and the milestone API; failure classes\nare additionally mined from issue labels and closing comments.\nPreconditions — `gh` installed, `gh auth status` succeeding, and a\nGitHub remote present. Any failure names WHICH one failed and offers\ndocument mode; never guess.\n",{"name":5,"description":7,"argument-hint":23},"[week | phase N | notes]","main","6b5be39937ce3823cf8f58c68aadcfdfda839fa0","skills\u002Fretro",0,"https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack","https:\u002F\u002Fgithub.com\u002FAaravChadha","2026-09-28 13:07:41",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add AaravChadha\u002Facstack --skill retro",{"tool":37,"command":38},"bunx","bunx skills add AaravChadha\u002Facstack --skill retro",{"tool":40,"command":41},"pnpm","pnpm dlx skills add AaravChadha\u002Facstack --skill retro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fretro\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fretro-sections.md","REFERENCE","参考文档",2899,"https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fretro\u002Freferences\u002Fretro-sections.md",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"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":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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",[],[]]