[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79R3CPD2F05EKE9N8XCMM90":3,"skill-same:01M79R3CPD2F05EKE9N8XCMM90":55},{"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},"01M79R3CPD2F05EKE9N8XCMM90","triage",null,"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.","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\u002Ftriage\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: triage\ndescription: 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.\nargument-hint: \"[notes]\"\n---\n\n# \u002Ftriage — keep the backlog honest\n\nA backlog rots in specific, findable ways. This skill finds them, reports\nthem with evidence, and applies exactly the actions the user approves —\nnothing more, and nothing silently.\n\n`Adjacent skills:` \u002Faudit docs (read-only drift report; \u002Ftriage proposes\nand applies tracker\u002Fplan actions) · \u002Fticket (files one new item; \u002Ftriage\ngrooms the many existing ones).\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## Stance: report, then apply\n\nThe report opens with a one-line verdict — `backlog healthy` or\n`\u003CN> findings across \u003CM> categories` — before any finding. Then the\nnumbered findings, each with its evidence and its proposed action.\nThen the user picks; only approved actions are executed, and the\nreport closes with the applied-actions list — each action confirmed\nby name.\nNothing is ever silently deleted or closed: every close carries a written\nreason. Supersede-don't-delete applies to backlogs exactly as it applies\nto decisions.\n\n**Applied actions edit the plan in place, so they collide with other\nsessions.** Closing or reopening a box changes any count derived from those\nboxes; two sessions closing *different* items both hand-write the *same* new\ntotal, and git auto-merges the identical edit with no conflict — measured\n2026-09-14, leaving the number one out. So: apply the box changes, and\n**re-derive any stored total with the project's own tool** rather than\nediting the digit. State in the applied-actions list that the post-merge\ntotal belongs to whoever integrates, since this branch cannot see what\nanother session closed.\n\nConfig: `stale-days` from a `## triage` section in `.claude\u002Facstack.md`\n(default 30).\n\n## Mode: the sweep itself\n\nThe sweeps are mode-specific and mutually exclusive — read exactly one,\nchosen by the resolved `tracking` config, and not the other:\n\n- `tracking: tickets` → `references\u002Ftickets-mode.md`\n- `tracking: document` (the default) → `references\u002Fdocument-mode.md`\n\nRoot-cause clustering below runs in BOTH modes, after whichever sweep\nyou read.\n\n## Root-cause clustering (both modes)\n\nEvery sweep above is a **local** comparison — this item against that item,\nthis box against its acceptance. Clustering is the **global** one: twelve\nitems that are all one cause is a finding no pairwise duplicate check can\nsee, because no two of them are duplicates.\n\nRun it last, over the whole backlog at once, after the local sweeps have\nalready removed the noise.\n\n**A cluster needs a stated cause, not a shared topic.** \"These five all\nmention the parser\" is a tag. \"These five all fail because the tokenizer\ndrops the final field when the input has no trailing newline\" is a cause.\nThe test is one sentence: **would fixing the named cause close every item\nin the cluster?** If some would survive it, the cluster is wrong — split it\nor drop it.\n\nThe bar, all three required:\n\n- **Three or more items to propose a PARENT.** A parent over two items is\n  more structure than it earns.\n  **But a same-cause pair is still named, never dropped.** Two items sharing\n  a cause are not a duplicate pair — the duplicate sweep keys on overlapping\n  text and will not see them, so a pair that falls below this bar would\n  otherwise vanish between the two sweeps. Report it under\n  `Related pairs`: the cause, both items, and the evidence, with no parent\n  proposed. Found by shakedown 7, where two items sharing a UTC-boundary\n  cause were invisible to both passes.\n- **A cause written as a sentence**, naming the mechanism — not a\n  component, a label, or a theme.\n- **Evidence per member**: the quoted line, error, or acceptance that ties\n  that specific item to that cause. An item nobody can tie to the cause is\n  not in the cluster.\n\n**Propose nothing when the backlog is genuinely independent.** This is the\nhalf that keeps the pass honest: a backlog of unrelated work is the normal,\nhealthy state, and a clustering step that always finds clusters is\nastrology. Say plainly that no root-cause groups were found and move on —\nthat is a real result, not a failed sweep. Never widen a cause until items\nfit it; a cause broad enough to cover everything explains nothing.\n\nWhat the report proposes, per cluster:\n\n- **A parent** — in tickets mode a new issue titled by the CAUSE; in\n  document mode a parent task in PLAN.md with the children as its subtasks.\n  Never a parent that merely renames the group.\n- **The children redirected**, each with the same standardized line so the\n  tree stays navigable: `rolled up into \u003Cparent> — same cause: \u003Ccause>`.\n- **What stays independent**, listed. An item that resisted clustering is\n  information, not a leftover.\n\nApproval-gated exactly like the rest of this skill: the clusters are\nproposed with their evidence, and nothing is filed, edited, or closed until\nthe user says so. Getting a cluster wrong reshapes someone's whole backlog,\nso this is the sweep where a wrong proposal costs the most.\n\n## Hard rules\n\n- Findings without evidence (the quoted text, the failing command, the\n  date arithmetic) don't make the report.\n- The report states what was NOT swept (e.g. acceptance commands too\n  expensive to run) — a sweep that implies totality it didn't do is\n  drift about drift.\n- Applied actions are listed at the end exactly as executed — issue\n  numbers, label names, PLAN.md lines — so the JOURNAL entry can cite\n  them.\n","# \u002Ftriage — keep the backlog honest\n\nA backlog rots in specific, findable ways. This skill finds them, reports\nthem with evidence, and applies exactly the actions the user approves —\nnothing more, and nothing silently.\n\n`Adjacent skills:` \u002Faudit docs (read-only drift report; \u002Ftriage proposes\nand applies tracker\u002Fplan actions) · \u002Fticket (files one new item; \u002Ftriage\ngrooms the many existing ones).\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## Stance: report, then apply\n\nThe report opens with a one-line verdict — `backlog healthy` or\n`\u003CN> findings across \u003CM> categories` — before any finding. Then the\nnumbered findings, each with its evidence and its proposed action.\nThen the user picks; only approved actions are executed, and the\nreport closes with the applied-actions list — each action confirmed\nby name.\nNothing is ever silently deleted or closed: every close carries a written\nreason. Supersede-don't-delete applies to backlogs exactly as it applies\nto decisions.\n\n**Applied actions edit the plan in place, so they collide with other\nsessions.** Closing or reopening a box changes any count derived from those\nboxes; two sessions closing *different* items both hand-write the *same* new\ntotal, and git auto-merges the identical edit with no conflict — measured\n2026-09-14, leaving the number one out. So: apply the box changes, and\n**re-derive any stored total with the project's own tool** rather than\nediting the digit. State in the applied-actions list that the post-merge\ntotal belongs to whoever integrates, since this branch cannot see what\nanother session closed.\n\nConfig: `stale-days` from a `## triage` section in `.claude\u002Facstack.md`\n(default 30).\n\n## Mode: the sweep itself\n\nThe sweeps are mode-specific and mutually exclusive — read exactly one,\nchosen by the resolved `tracking` config, and not the other:\n\n- `tracking: tickets` → `references\u002Ftickets-mode.md`\n- `tracking: document` (the default) → `references\u002Fdocument-mode.md`\n\nRoot-cause clustering below runs in BOTH modes, after whichever sweep\nyou read.\n\n## Root-cause clustering (both modes)\n\nEvery sweep above is a **local** comparison — this item against that item,\nthis box against its acceptance. Clustering is the **global** one: twelve\nitems that are all one cause is a finding no pairwise duplicate check can\nsee, because no two of them are duplicates.\n\nRun it last, over the whole backlog at once, after the local sweeps have\nalready removed the noise.\n\n**A cluster needs a stated cause, not a shared topic.** \"These five all\nmention the parser\" is a tag. \"These five all fail because the tokenizer\ndrops the final field when the input has no trailing newline\" is a cause.\nThe test is one sentence: **would fixing the named cause close every item\nin the cluster?** If some would survive it, the cluster is wrong — split it\nor drop it.\n\nThe bar, all three required:\n\n- **Three or more items to propose a PARENT.** A parent over two items is\n  more structure than it earns.\n  **But a same-cause pair is still named, never dropped.** Two items sharing\n  a cause are not a duplicate pair — the duplicate sweep keys on overlapping\n  text and will not see them, so a pair that falls below this bar would\n  otherwise vanish between the two sweeps. Report it under\n  `Related pairs`: the cause, both items, and the evidence, with no parent\n  proposed. Found by shakedown 7, where two items sharing a UTC-boundary\n  cause were invisible to both passes.\n- **A cause written as a sentence**, naming the mechanism — not a\n  component, a label, or a theme.\n- **Evidence per member**: the quoted line, error, or acceptance that ties\n  that specific item to that cause. An item nobody can tie to the cause is\n  not in the cluster.\n\n**Propose nothing when the backlog is genuinely independent.** This is the\nhalf that keeps the pass honest: a backlog of unrelated work is the normal,\nhealthy state, and a clustering step that always finds clusters is\nastrology. Say plainly that no root-cause groups were found and move on —\nthat is a real result, not a failed sweep. Never widen a cause until items\nfit it; a cause broad enough to cover everything explains nothing.\n\nWhat the report proposes, per cluster:\n\n- **A parent** — in tickets mode a new issue titled by the CAUSE; in\n  document mode a parent task in PLAN.md with the children as its subtasks.\n  Never a parent that merely renames the group.\n- **The children redirected**, each with the same standardized line so the\n  tree stays navigable: `rolled up into \u003Cparent> — same cause: \u003Ccause>`.\n- **What stays independent**, listed. An item that resisted clustering is\n  information, not a leftover.\n\nApproval-gated exactly like the rest of this skill: the clusters are\nproposed with their evidence, and nothing is filed, edited, or closed until\nthe user says so. Getting a cluster wrong reshapes someone's whole backlog,\nso this is the sweep where a wrong proposal costs the most.\n\n## Hard rules\n\n- Findings without evidence (the quoted text, the failing command, the\n  date arithmetic) don't make the report.\n- The report states what was NOT swept (e.g. acceptance commands too\n  expensive to run) — a sweep that implies totality it didn't do is\n  drift about drift.\n- Applied actions are listed at the end exactly as executed — issue\n  numbers, label names, PLAN.md lines — so the JOURNAL entry can cite\n  them.\n",{"name":5,"description":7,"argument-hint":23},"[notes]","main","6b5be39937ce3823cf8f58c68aadcfdfda839fa0","skills\u002Ftriage",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 triage",{"tool":37,"command":38},"bunx","bunx skills add AaravChadha\u002Facstack --skill triage",{"tool":40,"command":41},"pnpm","pnpm dlx skills add AaravChadha\u002Facstack --skill triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fdocument-mode.md","REFERENCE","参考文档",1689,"https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002Freferences\u002Fdocument-mode.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Ftickets-mode.md",1492,"https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002Freferences\u002Ftickets-mode.md",[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"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":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"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":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M79R2WPCWE214XBCZB1KKQ9M","retro","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.","https:\u002F\u002Fgithub.com\u002FAaravChadha\u002Facstack\u002Fblob\u002Fmain\u002Fskills\u002Fretro\u002FSKILL.md",[],[]]