[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NJG99DARGP3GF1ADWCA7ER":3,"skill-same:01M6NJG99DARGP3GF1ADWCA7ER":60},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":6,"updatedAt":45,"install":46,"resources":59},"01M6NJG99DARGP3GF1ADWCA7ER","recall",null,"Reconstruct and narrate the current development context from contextual commits. Run at session start, when resuming work, or when switching branches. Produces a brief, conversational summary of where things stand.","mistakenot\u002Fauto-stack","mistakenot","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7852099?v=4","01M6CY3K3NE7B30VD9C8HP815J","Charlie","01M6NHYR6FB2SEZ7DFHD3PS3D6",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmistakenot\u002Fauto-stack\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frecall\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"development","run","brief","start","commits","work","context","session","summary","branches","switching","session start","at","things","resuming","2026-11-10 10:12:30",false,"---\nname: recall\ndescription: >-\n    Reconstruct and narrate the current development context from contextual commits. Run at session start, when resuming work, or when switching branches. Produces a brief, conversational summary of where things stand.\nlicense: MIT\n---\n\n# Context Recall\n\nReconstruct the development story from contextual commit history and present it as a natural briefing.\n\n## Argument Detection\n\nCheck how `recall` was invoked:\n\n- **No arguments** — run the default mode (full branch\u002Fsession briefing below).\n- **Bare word** (e.g. `recall auth`) — treat as a scope query. Jump to **Scope Query**.\n- **`word(word)` pattern** (e.g. `recall rejected(auth)`) — treat as an action+scope query. Jump to **Action+Scope Query**.\n\n---\n\n## Default Mode (no arguments)\n\n### Step 1: Detect Branch State\n\nDetermine the working state:\n\n```bash\nCURRENT_BRANCH=$(git branch --show-current)\nDEFAULT_BRANCH=$(git symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD 2>\u002Fdev\u002Fnull | sed 's@^refs\u002Fremotes\u002Forigin\u002F@@' || echo \"main\")\n\n# Find the actual parent branch, not just the repo default.\n# Try upstream tracking branch first (fast path).\nBASE_BRANCH=$(git rev-parse --abbrev-ref @{upstream} 2>\u002Fdev\u002Fnull | sed 's|^origin\u002F||')\n\n# If no upstream, find the nearest local branch by commit distance.\nif [ -z \"$BASE_BRANCH\" ]; then\n    BASE_BRANCH=$(git for-each-ref --format='%(refname:short)' refs\u002Fheads\u002F | while read branch; do\n        [ \"$branch\" = \"$CURRENT_BRANCH\" ] && continue\n        echo \"$(git log --oneline \"$branch..$CURRENT_BRANCH\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ') $branch\"\n    done | sort -n | head -1 | awk '{print $2}')\nfi\n\n# Final fallback to default branch.\nBASE_BRANCH=${BASE_BRANCH:-$DEFAULT_BRANCH}\n\nUNSTAGED=$(git diff --stat)\nSTAGED=$(git diff --cached --stat)\nBRANCH_COMMITS=$(git log ${BASE_BRANCH}..HEAD --oneline 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n```\n\n`DEFAULT_BRANCH` identifies the repository's primary branch (for scenario C\u002FD detection). `BASE_BRANCH` identifies the closest ancestor branch — which may differ when feature branches are created from non-default branches (e.g., a feature branched from `develop`). All branch-relative queries use `BASE_BRANCH`.\n\n### Step 2: Gather Raw Material\n\n#### Scenario A — On a feature branch with commits\n\nThis is the richest scenario. Gather:\n\n```bash\n# Contextual action lines from all branch commits\ngit log ${BASE_BRANCH}..HEAD --format=\"%H%n%s%n%b%n---COMMIT_END---\"\n\n# Unstaged changes (what's in progress right now)\ngit diff --stat\ngit diff  # read the actual diff for key changes\n\n# Staged changes\ngit diff --cached --stat\n```\n\n#### Scenario B — On a feature branch with no commits yet\n\n```bash\n# Unstaged and staged changes only\ngit diff --stat\ngit diff --cached --stat\n\n# Last few commits on the parent branch for project context\ngit log ${BASE_BRANCH} -10 --format=\"%H%n%s%n%b%n---COMMIT_END---\"\n```\n\n#### Scenario C — On the default branch\n\n```bash\n# Recent commit history with contextual action lines\ngit log -20 --format=\"%H%n%s%n%b%n---COMMIT_END---\"\n```\n\n#### Scenario D — On the default branch with uncommitted changes\n\n```bash\n# Same as C plus uncommitted changes\ngit log -20 --format=\"%H%n%s%n%b%n---COMMIT_END---\"\ngit diff --stat\ngit diff --cached --stat\n```\n\n### Step 3: Extract Action Lines\n\nFrom the gathered commit bodies, extract lines matching:\n```\n^(intent|decision|rejected|constraint|learned)\\(\n```\n\nGroup them by commit (preserve chronological order) and by type (for synthesis).\n\n### Step 4: Synthesize Output\n\n**Signal density over narrative flow.** The output should be compact, scannable, and grounded entirely in what the commits and diffs show. Every line should be actionable information. No fluff, no conversational padding.\n\n#### For Scenario A (branch with commits):\n\nOutput the branch state, then synthesize the contextual action lines into a dense briefing organized by what matters most for continuing work.\n\nExample output:\n```\nBranch: feat\u002Fgoogle-oauth (4 commits ahead of main, unstaged changes in tests\u002F)\n\nActive intent: Add Google as first social login provider. GitHub and Apple to follow.\nApproach: passport.js with \u002Fapi\u002Fauth\u002Fcallback\u002F:provider convention.\nRejected: auth0-sdk — session model incompatible with redis store.\nConstraints:\n  - Redis session TTL 24h, tokens must refresh within window\n  - Callback routes must follow existing :provider pattern\nLearned: passport-google needs explicit offline_access scope for refresh tokens.\nIn progress: Integration tests for callback handler (unstaged).\n```\n\nWhen branched from a non-default branch:\n\n```\nBranch: feat\u002Foauth-refresh (2 commits ahead of develop, no uncommitted changes)\n\nActive intent: Implement token refresh for OAuth providers.\nConstraint: Must stay compatible with the session store changes on develop.\n```\n\nPriority order:\n1. Active intent (what we're building and why)\n2. Current approach (decisions made)\n3. Rejected approaches (what NOT to re-explore — critical)\n4. Constraints (hard boundaries)\n5. Learnings (things that save time)\n6. In-progress work (unstaged\u002Fstaged changes)\n\nIf intent evolved during the branch (a pivot), show both the original and current intent to make the pivot visible.\n\n#### For Scenario B (branch with no commits):\n\n```\nBranch: feat\u002Fnew-feature (0 commits ahead of develop)\n\nNo contextual history on this branch yet.\nStaged: 2 files (src\u002Fauth\u002Fprovider.ts, src\u002Fauth\u002Ftypes.ts)\nUnstaged: none\n\nRecent project activity (from develop):\n  - Auth: OAuth provider framework merged, Google working\n  - Payments: Multi-currency support shipped (EUR, GBP alongside USD)\n```\n\n#### For Scenario C (default branch, no changes):\n\nSynthesize recent merged work from the last 20 commits. Group by area of activity. Surface any active constraints or learnings that apply broadly.\n\n```\nRecent project activity:\n\nAuth: OAuth provider framework merged. Google working, GitHub and Apple planned.\n  - Rejected auth0-sdk (session model incompatible with redis store)\n  - Constraint: redis session TTL 24h, tokens must refresh within window\n\nPayments: Multi-currency support shipped (USD, EUR, GBP).\n  - Per-transaction currency, not account-level\n  - Constraint: Stripe locks currency at PaymentIntent creation\n  - Learned: presentment ≠ settlement currency in Stripe\n\nWhat do you want to work on?\n```\n\n#### For Scenario D (default branch with uncommitted changes):\n\nSame as Scenario C, with uncommitted changes noted at the top.\n\n#### When there are no contextual commits at all\n\nIf the history contains conventional commits but no contextual action lines, **still produce useful output** from what exists:\n\n```\nBranch: main (no contextual commits found in recent history)\n\nRecent activity (from commit subjects):\n  - auth: 6 commits (OAuth implementation, middleware updates) — 2 days ago\n  - payments: 4 commits (currency handling, Stripe integration) — last week\n  - tests: 3 commits — last week\n  - config: 2 commits\n\nMost recent: feat(auth): implement Google OAuth provider\n\nNo explicit intent, decisions, or constraints are captured in commit history.\nUsing the contextual-commit skill on future commits will surface\nthe reasoning behind changes that commit subjects alone cannot show.\n```\n\nThis is honest about the signal quality while still providing useful orientation. The suggestion to adopt the skill is a natural next step, not a sales pitch.\n\n### Guidelines\n\n- **Dense over conversational.** Every line should carry information. No \"Here's what's been happening\" or \"Let me tell you about.\"\n- **Grounded in data.** Only report what the action lines, commit subjects, and diffs actually show. Do not infer, speculate, or fill gaps.\n- **Surface rejections prominently.** Rejected approaches are the highest-value signal — they prevent wasted exploration.\n- **Group by scope when multiple scopes exist.** On the default branch with broad history, organize by domain area rather than chronologically.\n- **End with a prompt.** Close with \"What do you want to work on?\" or similar. Keep it short.\n- **Scale to the data.** If there are 2 contextual commits, the output is 3-4 lines. If there are 20, it's a few grouped paragraphs. Never pad thin data into a long output.\n\n---\n\n## Scope Query (`recall \u003Cscope>`)\n\nTargeted query across full repo history for a given scope. Prefix matching: `auth` matches `auth`, `auth-tokens`, `auth-library`, etc.\n\n### Step 1: Query\n\n```bash\ngit log --all --grep=\"(${SCOPE}\" --format=\"%H%n%s%n%b%n---COMMIT_END---\"\n```\n\n### Step 2: Extract\n\nFrom the gathered commit bodies, extract lines matching:\n```bash\ngrep -E \"^(intent|decision|rejected|constraint|learned)\\(${SCOPE}\"\n```\n\nThis captures all action lines whose scope starts with the query term.\n\n### Step 3: Output\n\nGroup by action type, chronological within each group. Show which sub-scopes were found.\n\nExample (`recall auth`):\n```\nScope: auth (also found: auth-tokens, auth-library)\n\nintent:\n  - social login starting with Google, then GitHub and Apple\n  - original session approach incompatible with redis cluster setup\n\ndecision:\n  - passport.js over auth0-sdk for multi-provider flexibility\n  - JWT with short expiry + refresh token pattern\n\nrejected:\n  - auth0-sdk — locks into their session model, incompatible with redis store\n  - auth-sessions — redis cluster doesn't support session stickiness needed by passport sessions\n\nconstraint:\n  - callback routes must follow \u002Fapi\u002Fauth\u002Fcallback\u002F:provider pattern per existing convention\n  - redis 24h TTL means tokens must refresh within that window\n\nlearned:\n  - passport-google needs explicit offline_access scope for refresh tokens\n  - redis-cluster session affinity requires sticky sessions at load balancer level — too invasive\n```\n\nIf no matches are found, say so plainly and suggest checking the scope name.\n\n---\n\n## Action+Scope Query (`recall \u003Caction>(\u003Cscope>)`)\n\nQuery a specific action type for a scope across full repo history.\n\n### Step 1: Query\n\n```bash\ngit log --all --grep=\"${ACTION}(${SCOPE}\" --format=\"%H%n%s%n%b%n---COMMIT_END---\"\n```\n\n### Step 2: Extract\n\n```bash\ngrep \"^${ACTION}(${SCOPE}\"\n```\n\n### Step 3: Output\n\nFlat chronological list with commit subject for provenance.\n\nExample (`recall rejected(auth)`):\n```\nrejected(auth) across history:\n\n  - auth0-sdk — locks into their session model, incompatible with redis store\n    from: feat(auth): implement Google OAuth provider\n\n  - auth-sessions — redis cluster doesn't support session stickiness needed by passport sessions\n    from: refactor(auth): switch from session-based to JWT tokens\n```\n\nIf no matches are found, say so plainly.\n\n---\n\n## Proactive Usage\n\nBefore making a significant decision in any scope area, check `rejected` and `constraint` lines for that scope first:\n\n```bash\ngit log --all --grep=\"rejected(${SCOPE}\" --format=\"%b\" | grep \"^rejected(${SCOPE}\"\ngit log --all --grep=\"constraint(${SCOPE}\" --format=\"%b\" | grep \"^constraint(${SCOPE}\"\n```\n\nIf a previous commit recorded a `rejected` line for the approach you're about to propose, surface the rejection reason to the user **before** re-proposing it. The rejection may still stand, or circumstances may have changed — but the user should make that call with full context, not rediscover the same dead end.\n\nSimilarly, check `constraint` lines before proposing an approach that might violate a known boundary.\n\nThis check is lightweight and should become habitual for any scope you're actively working in.\n","# Context Recall\n\nReconstruct the development story from contextual commit history and present it as a natural briefing.\n\n## Argument Detection\n\nCheck how `recall` was invoked:\n\n- **No arguments** — run the default mode (full branch\u002Fsession briefing below).\n- **Bare word** (e.g. `recall auth`) — treat as a scope query. Jump to **Scope Query**.\n- **`word(word)` pattern** (e.g. `recall rejected(auth)`) — treat as an action+scope query. Jump to **Action+Scope Query**.\n\n---\n\n## Default Mode (no arguments)\n\n### Step 1: Detect Branch State\n\nDetermine the working state:\n\n```bash\nCURRENT_BRANCH=$(git branch --show-current)\nDEFAULT_BRANCH=$(git symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD 2>\u002Fdev\u002Fnull | sed 's@^refs\u002Fremotes\u002Forigin\u002F@@' || echo \"main\")\n\n# Find the actual parent branch, not just the repo default.\n# Try upstream tracking branch first (fast path).\nBASE_BRANCH=$(git rev-parse --abbrev-ref @{upstream} 2>\u002Fdev\u002Fnull | sed 's|^origin\u002F||')\n\n# If no upstream, find the nearest local branch by commit distance.\nif [ -z \"$BASE_BRANCH\" ]; then\n    BASE_BRANCH=$(git for-each-ref --format='%(refname:short)' refs\u002Fheads\u002F | while read branch; do\n        [ \"$branch\" = \"$CURRENT_BRANCH\" ] && continue\n        echo \"$(git log --oneline \"$branch..$CURRENT_BRANCH\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ') $branch\"\n    done | sort -n | head -1 | awk '{print $2}')\nfi\n\n# Final fallback to default branch.\nBASE_BRANCH=${BASE_BRANCH:-$DEFAULT_BRANCH}\n\nUNSTAGED=$(git diff --stat)\nSTAGED=$(git diff --cached --stat)\nBRANCH_COMMITS=$(git log ${BASE_BRANCH}..HEAD --oneline 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n```\n\n`DEFAULT_BRANCH` identifies the repository's primary branch (for scenario C\u002FD detection). `BASE_BRANCH` identifies the closest ancestor branch — which may differ when feature branches are created from non-default branches (e.g., a feature branched from `develop`). All branch-relative queries use `BASE_BRANCH`.\n\n### Step 2: Gather Raw Material\n\n#### Scenario A — On a feature branch with commits\n\nThis is the richest scenario. Gather:\n\n```bash\n# Contextual action lines from all branch commits\ngit log ${BASE_BRANCH}..HEAD --format=\"%H%n%s%n%b%n---COMMIT_END---\"\n\n# Unstaged changes (what's in progress right now)\ngit diff --stat\ngit diff  # read the actual diff for key changes\n\n# Staged changes\ngit diff --cached --stat\n```\n\n#### Scenario B — On a feature branch with no commits yet\n\n```bash\n# Unstaged and staged changes only\ngit diff --stat\ngit diff --cached --stat\n\n# Last few commits on the parent branch for project context\ngit log ${BASE_BRANCH} -10 --format=\"%H%n%s%n%b%n---COMMIT_END---\"\n```\n\n#### Scenario C — On the default branch\n\n```bash\n# Recent commit history with contextual action lines\ngit log -20 --format=\"%H%n%s%n%b%n---COMMIT_END---\"\n```\n\n#### Scenario D — On the default branch with uncommitted changes\n\n```bash\n# Same as C plus uncommitted changes\ngit log -20 --format=\"%H%n%s%n%b%n---COMMIT_END---\"\ngit diff --stat\ngit diff --cached --stat\n```\n\n### Step 3: Extract Action Lines\n\nFrom the gathered commit bodies, extract lines matching:\n```\n^(intent|decision|rejected|constraint|learned)\\(\n```\n\nGroup them by commit (preserve chronological order) and by type (for synthesis).\n\n### Step 4: Synthesize Output\n\n**Signal density over narrative flow.** The output should be compact, scannable, and grounded entirely in what the commits and diffs show. Every line should be actionable information. No fluff, no conversational padding.\n\n#### For Scenario A (branch with commits):\n\nOutput the branch state, then synthesize the contextual action lines into a dense briefing organized by what matters most for continuing work.\n\nExample output:\n```\nBranch: feat\u002Fgoogle-oauth (4 commits ahead of main, unstaged changes in tests\u002F)\n\nActive intent: Add Google as first social login provider. GitHub and Apple to follow.\nApproach: passport.js with \u002Fapi\u002Fauth\u002Fcallback\u002F:provider convention.\nRejected: auth0-sdk — session model incompatible with redis store.\nConstraints:\n  - Redis session TTL 24h, tokens must refresh within window\n  - Callback routes must follow existing :provider pattern\nLearned: passport-google needs explicit offline_access scope for refresh tokens.\nIn progress: Integration tests for callback handler (unstaged).\n```\n\nWhen branched from a non-default branch:\n\n```\nBranch: feat\u002Foauth-refresh (2 commits ahead of develop, no uncommitted changes)\n\nActive intent: Implement token refresh for OAuth providers.\nConstraint: Must stay compatible with the session store changes on develop.\n```\n\nPriority order:\n1. Active intent (what we're building and why)\n2. Current approach (decisions made)\n3. Rejected approaches (what NOT to re-explore — critical)\n4. Constraints (hard boundaries)\n5. Learnings (things that save time)\n6. In-progress work (unstaged\u002Fstaged changes)\n\nIf intent evolved during the branch (a pivot), show both the original and current intent to make the pivot visible.\n\n#### For Scenario B (branch with no commits):\n\n```\nBranch: feat\u002Fnew-feature (0 commits ahead of develop)\n\nNo contextual history on this branch yet.\nStaged: 2 files (src\u002Fauth\u002Fprovider.ts, src\u002Fauth\u002Ftypes.ts)\nUnstaged: none\n\nRecent project activity (from develop):\n  - Auth: OAuth provider framework merged, Google working\n  - Payments: Multi-currency support shipped (EUR, GBP alongside USD)\n```\n\n#### For Scenario C (default branch, no changes):\n\nSynthesize recent merged work from the last 20 commits. Group by area of activity. Surface any active constraints or learnings that apply broadly.\n\n```\nRecent project activity:\n\nAuth: OAuth provider framework merged. Google working, GitHub and Apple planned.\n  - Rejected auth0-sdk (session model incompatible with redis store)\n  - Constraint: redis session TTL 24h, tokens must refresh within window\n\nPayments: Multi-currency support shipped (USD, EUR, GBP).\n  - Per-transaction currency, not account-level\n  - Constraint: Stripe locks currency at PaymentIntent creation\n  - Learned: presentment ≠ settlement currency in Stripe\n\nWhat do you want to work on?\n```\n\n#### For Scenario D (default branch with uncommitted changes):\n\nSame as Scenario C, with uncommitted changes noted at the top.\n\n#### When there are no contextual commits at all\n\nIf the history contains conventional commits but no contextual action lines, **still produce useful output** from what exists:\n\n```\nBranch: main (no contextual commits found in recent history)\n\nRecent activity (from commit subjects):\n  - auth: 6 commits (OAuth implementation, middleware updates) — 2 days ago\n  - payments: 4 commits (currency handling, Stripe integration) — last week\n  - tests: 3 commits — last week\n  - config: 2 commits\n\nMost recent: feat(auth): implement Google OAuth provider\n\nNo explicit intent, decisions, or constraints are captured in commit history.\nUsing the contextual-commit skill on future commits will surface\nthe reasoning behind changes that commit subjects alone cannot show.\n```\n\nThis is honest about the signal quality while still providing useful orientation. The suggestion to adopt the skill is a natural next step, not a sales pitch.\n\n### Guidelines\n\n- **Dense over conversational.** Every line should carry information. No \"Here's what's been happening\" or \"Let me tell you about.\"\n- **Grounded in data.** Only report what the action lines, commit subjects, and diffs actually show. Do not infer, speculate, or fill gaps.\n- **Surface rejections prominently.** Rejected approaches are the highest-value signal — they prevent wasted exploration.\n- **Group by scope when multiple scopes exist.** On the default branch with broad history, organize by domain area rather than chronologically.\n- **End with a prompt.** Close with \"What do you want to work on?\" or similar. Keep it short.\n- **Scale to the data.** If there are 2 contextual commits, the output is 3-4 lines. If there are 20, it's a few grouped paragraphs. Never pad thin data into a long output.\n\n---\n\n## Scope Query (`recall \u003Cscope>`)\n\nTargeted query across full repo history for a given scope. Prefix matching: `auth` matches `auth`, `auth-tokens`, `auth-library`, etc.\n\n### Step 1: Query\n\n```bash\ngit log --all --grep=\"(${SCOPE}\" --format=\"%H%n%s%n%b%n---COMMIT_END---\"\n```\n\n### Step 2: Extract\n\nFrom the gathered commit bodies, extract lines matching:\n```bash\ngrep -E \"^(intent|decision|rejected|constraint|learned)\\(${SCOPE}\"\n```\n\nThis captures all action lines whose scope starts with the query term.\n\n### Step 3: Output\n\nGroup by action type, chronological within each group. Show which sub-scopes were found.\n\nExample (`recall auth`):\n```\nScope: auth (also found: auth-tokens, auth-library)\n\nintent:\n  - social login starting with Google, then GitHub and Apple\n  - original session approach incompatible with redis cluster setup\n\ndecision:\n  - passport.js over auth0-sdk for multi-provider flexibility\n  - JWT with short expiry + refresh token pattern\n\nrejected:\n  - auth0-sdk — locks into their session model, incompatible with redis store\n  - auth-sessions — redis cluster doesn't support session stickiness needed by passport sessions\n\nconstraint:\n  - callback routes must follow \u002Fapi\u002Fauth\u002Fcallback\u002F:provider pattern per existing convention\n  - redis 24h TTL means tokens must refresh within that window\n\nlearned:\n  - passport-google needs explicit offline_access scope for refresh tokens\n  - redis-cluster session affinity requires sticky sessions at load balancer level — too invasive\n```\n\nIf no matches are found, say so plainly and suggest checking the scope name.\n\n---\n\n## Action+Scope Query (`recall \u003Caction>(\u003Cscope>)`)\n\nQuery a specific action type for a scope across full repo history.\n\n### Step 1: Query\n\n```bash\ngit log --all --grep=\"${ACTION}(${SCOPE}\" --format=\"%H%n%s%n%b%n---COMMIT_END---\"\n```\n\n### Step 2: Extract\n\n```bash\ngrep \"^${ACTION}(${SCOPE}\"\n```\n\n### Step 3: Output\n\nFlat chronological list with commit subject for provenance.\n\nExample (`recall rejected(auth)`):\n```\nrejected(auth) across history:\n\n  - auth0-sdk — locks into their session model, incompatible with redis store\n    from: feat(auth): implement Google OAuth provider\n\n  - auth-sessions — redis cluster doesn't support session stickiness needed by passport sessions\n    from: refactor(auth): switch from session-based to JWT tokens\n```\n\nIf no matches are found, say so plainly.\n\n---\n\n## Proactive Usage\n\nBefore making a significant decision in any scope area, check `rejected` and `constraint` lines for that scope first:\n\n```bash\ngit log --all --grep=\"rejected(${SCOPE}\" --format=\"%b\" | grep \"^rejected(${SCOPE}\"\ngit log --all --grep=\"constraint(${SCOPE}\" --format=\"%b\" | grep \"^constraint(${SCOPE}\"\n```\n\nIf a previous commit recorded a `rejected` line for the approach you're about to propose, surface the rejection reason to the user **before** re-proposing it. The rejection may still stand, or circumstances may have changed — but the user should make that call with full context, not rediscover the same dead end.\n\nSimilarly, check `constraint` lines before proposing an approach that might violate a known boundary.\n\nThis check is lightweight and should become habitual for any scope you're actively working in.\n",{"name":5,"license":15,"description":7},"main","8075db80b0f662909c8c49bbf04da1acb03c24e1",".agents\u002Fskills\u002Frecall","https:\u002F\u002Fgithub.com\u002Fmistakenot\u002Fauto-stack","https:\u002F\u002Fgithub.com\u002Fmistakenot","charliedaly.co.uk","2026-10-29 07:32:11",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add mistakenot\u002Fauto-stack --skill recall",{"tool":52,"command":53},"bunx","bunx skills add mistakenot\u002Fauto-stack --skill recall",{"tool":55,"command":56},"pnpm","pnpm dlx skills add mistakenot\u002Fauto-stack --skill recall","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmistakenot\u002Fauto-stack\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frecall\u002FSKILL.md",true,[],[61,76,81,112,137,154],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":34},"01M6NK49FNTVKG4KNN4ZZ1XH84","release","Create a new auto-stack release by tagging a commit and pushing the tag. The GitHub Actions release workflow builds binaries and publishes the release.","https:\u002F\u002Fgithub.com\u002Fmistakenot\u002Fauto-stack\u002Fblob\u002Fmain\u002Fskills\u002Frelease\u002FSKILL.md",[],[63,68,69,70,71,72,73,74,75],"auto","stack","github actions","actions","create","commit","workflow","github",{"skillNo":77,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":34},"01M6NK3M6TNEBZBBTMY0JM6884","https:\u002F\u002Fgithub.com\u002Fmistakenot\u002Fauto-stack\u002Fblob\u002Fmain\u002Fskills\u002Frecall\u002FSKILL.md",[],[5,19,20,21,22,23,32,33,24,31,30,29,28,27,26,25],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":92,"publishedAt":34},"01M6NK3C68MGDACSHXF0MAF07Y","readme-updater","Bring a project's README up to date with the current state of the codebase. Audits the existing README for stale commands, dead links, renamed tools, and drifted status claims; surveys what's changed since the README was last touched; rewrites it with verified facts; then commits and pushes. Use this skill whenever the user says \"update the README\", \"the readme is stale\", \"refresh the README\", \"rewrite README.md\", \"add new features to the readme\", or otherwise asks for documentation that reflects the current state of the project. Also trigger when a README clearly hasn't kept pace with the codebase (e.g. recent feature commits not reflected, broken examples).","https:\u002F\u002Fgithub.com\u002Fmistakenot\u002Fauto-stack\u002Fblob\u002Fmain\u002Fskills\u002Freadme-updater\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[93,94,95,96,97,98,99,100,101,102,103,104,105,106,23,107,108,109,110,111],"readme updater","updater","README","bring","feature","verified","claims","for","add","features","links","project","up","broken","Tools","update","documentation","status","commands",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":34},"01M6NK2W0073Z14AYD6FBQH3V8","contextual-commit","Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.","https:\u002F\u002Fgithub.com\u002Fmistakenot\u002Fauto-stack\u002Fblob\u002Fmain\u002Fskills\u002Fcontextual-commit\u002FSKILL.md",[],[119,73,120,121,122,123,23,124,125,126,127,128,129,130,131,132,133,134,135,136],"contextual commit","decisions","capture","just","capture intent","why","constraints","code","write","preserve","changes","action","with","task","intent","conventional commits","use","user",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":146,"publishedAt":34},"01M6NK2JEGH6QC2EPQSZNCTDWC","deploy-checklist","A pre-deployment checklist for safe releases.","https:\u002F\u002Fgithub.com\u002Fmistakenot\u002Fauto-stack\u002Fblob\u002Fmain\u002Fharness\u002Fscenarios\u002Fskill-remote\u002Ffixtures\u002Fskills\u002Fdeploy-checklist\u002FSKILL.md",[143],{"categoryNo":144,"categoryName":145,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000011","运维与部署",[147,148,149,100,150,151,152,153],"deploy checklist","checklist","deploy","deployment checklist","releases","deployment","safe",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":168,"publishedAt":34},"01M6NK2EDH7XHR830B51AA750P","code-review","Structured code review with severity labels.","https:\u002F\u002Fgithub.com\u002Fmistakenot\u002Fauto-stack\u002Fblob\u002Fmain\u002Fharness\u002Fscenarios\u002Fskill-remote\u002Ffixtures\u002Fskills\u002Fcode-review\u002FSKILL.md",[160,163],{"categoryNo":161,"categoryName":162,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":164,"categoryName":165,"taxonomyType":166,"taxonomyTypeDesc":167},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[169,126,170,171,131,172,173],"review","code review","labels","structured","severity"]