[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-apache-magpie-issue-reassess-stats":3,"mdc-xpwx30-key":40,"related-org-apache-magpie-issue-reassess-stats":1321,"related-repo-apache-magpie-issue-reassess-stats":1474},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":35,"sourceUrl":38,"mdContent":39},"magpie-issue-reassess-stats","analyze magpie issue reassessment statistics","Read-only dashboard over a directory of `verdict.json` files\nproduced by `issue-reassess` campaigns. Surfaces a health\nrating, classification distribution, partial-fix surfaces,\noldest-unresolved buckets, and per-component breakdowns.\nOutput is HTML by default; markdown fallback available.\nRead-only on tracker state; consumes campaign artefacts.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"apache","Apache Software Foundation","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fapache.png",[12,16,19],{"name":13,"slug":14,"type":15},"Dashboards","dashboards","tag",{"name":17,"slug":18,"type":15},"Engineering","engineering",{"name":20,"slug":21,"type":15},"Analytics","analytics",61,"https:\u002F\u002Fgithub.com\u002Fapache\u002Fmagpie","2026-07-12T08:34:40.191847","Apache-2.0",42,[28,8,29,30,31,32,33,34],"agent-skills","automation","claude-code","cve","security","vulnerability-disclosure","vulnerability-management",{"repoUrl":23,"stars":22,"forks":26,"topics":36,"description":37},[28,8,29,30,31,32,33,34],"Agent-assisted maintainership and development framework for Apache projects — Triage, Mentoring, Drafting (agent-authored fixes with human review), and Pairing (developer-side dev-cycle) skills shipping; Agentic Autonomous (auto-merge) on the roadmap.","https:\u002F\u002Fgithub.com\u002Fapache\u002Fmagpie\u002Ftree\u002FHEAD\u002Fskills\u002Fissue-reassess-stats","---\n# SPDX-License-Identifier: Apache-2.0\n# https:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\nname: magpie-issue-reassess-stats\nfamily: issue\nmode: Meta\ndescription: |\n  Read-only dashboard over a directory of `verdict.json` files\n  produced by `issue-reassess` campaigns. Surfaces a health\n  rating, classification distribution, partial-fix surfaces,\n  oldest-unresolved buckets, and per-component breakdowns.\n  Output is HTML by default; markdown fallback available.\n  Read-only on tracker state; consumes campaign artefacts.\nwhen_to_use: |\n  When a maintainer asks \"what's the state of the reassessment\n  campaign\", \"give me the dashboard for the recent sweep\", or\n  \"which issues still fail across pool runs\". Also as a\n  pre-release check on whether the EOL pool has dropped, and\n  as a periodic health-of-the-backlog view.\ncapability: capability:stats\nlicense: Apache-2.0\n---\n\n\u003C!-- SPDX-License-Identifier: Apache-2.0\n     https:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0 -->\n\n\u003C!-- Placeholder convention (see ..\u002F..\u002FAGENTS.md#placeholder-convention-used-in-skill-files):\n     \u003Cproject-config>          → adopter's project-config directory\n     \u003Cissue-tracker>           → URL of the project's general-issue tracker\n     \u003Cissue-tracker-project>   → project key within the tracker\n     \u003Cupstream>                → adopter's public source repo\n     \u003Cdefault-branch>          → upstream's default branch\n     Substitute these with concrete values from the adopting\n     project's \u003Cproject-config>\u002F before running any command below. -->\n\n# issue-reassess-stats\n\nRead-only dashboard skill over the `verdict.json` artefacts\nproduced by [`issue-reassess`](..\u002Fissue-reassess\u002FSKILL.md)\ncampaigns. Surfaces a health rating, classification distribution,\nthe `still-fails-*` action tail, partial-fix surfaces, new-issue\ncandidates from cross-family probes, and per-component breakdowns.\n\nThe skill is the read-only counterpart to\n[`issue-reassess`](..\u002Fissue-reassess\u002FSKILL.md) — both consume the\nsame on-disk artefacts. Where reassess **writes** verdicts (one\nper candidate) and a `report.md`, this skill **renders** an at-a-\nglance dashboard for the maintainer to scan.\n\nModelled on [`pr-management-stats`](..\u002Fpr-management-stats\u002FSKILL.md).\n\n---\n\n## Golden rules\n\n**Golden rule 1 — read-only on tracker AND on campaign\nartefacts.** This skill reads `verdict.json` files and emits HTML.\nIt does **not** modify any campaign artefact, does **not** post to\n`\u003Cissue-tracker>`, does **not** re-invoke `issue-reproducer`.\n\n**Golden rule 2 — HTML by default.** The dashboard is designed for\nthe *\"what should I do today\"* glance. Markdown and tables-only\nfallbacks are available for terminal pipelines (`--markdown`,\n`--tables-only`).\n\n**Golden rule 3 — surface action candidates first.** The dashboard\nopens with the still-failing-bug count and the new-issue\ncandidates from probes — these are where work happens. The bulk\nfixed-on-master \u002F cannot-run-* counts come second.\n\n**Golden rule 4 — fresh read on every invocation.** The dashboard\nre-reads `verdict.json` files on every run; no in-memory caching.\nThis makes the dashboard a coherent snapshot of the campaign\nstate at the moment of invocation.\n\n**Golden rule 5 — multi-campaign reads are explicit.** When the\nuser points the skill at a directory that contains multiple\ncampaign subdirectories, it asks which one — never silently\naggregates across campaigns.\n\n---\n\n## Adopter overrides\n\nBefore running the default behaviour documented below, this skill\nconsults\n[`.apache-magpie-local\u002Fissue-reassess-stats.md`](..\u002F..\u002Fdocs\u002Fsetup\u002Fagentic-overrides.md) (personal, gitignored) and [`.apache-magpie-overrides\u002Fissue-reassess-stats.md`](..\u002F..\u002Fdocs\u002Fsetup\u002Fagentic-overrides.md) (committed, project-wide)\nin the adopter repo if it exists, and applies any agent-readable\noverrides it finds. See\n[`docs\u002Fsetup\u002Fagentic-overrides.md`](..\u002F..\u002Fdocs\u002Fsetup\u002Fagentic-overrides.md)\nfor the contract.\n\n**Hard rule**: agents NEVER modify the snapshot under\n`\u003Cadopter-repo>\u002F.apache-magpie\u002F`. Local modifications go in the\noverride file.\n\n---\n\n## Snapshot drift\n\nAlso at the top of every run, this skill compares the gitignored\n`.apache-magpie.local.lock` (per-machine fetch) against the\ncommitted `.apache-magpie.lock` (the project pin). On mismatch\nthe skill surfaces the gap and proposes\n[`\u002Fmagpie-setup upgrade`](..\u002Fsetup\u002Fupgrade.md).\n\n---\n\n## Prerequisites\n\n- A campaign directory exists at the path the user supplies (or\n  the project's default per\n  [`\u003Cproject-config>\u002Freproducer-conventions.md`](..\u002F..\u002Fprojects\u002F_template\u002Freproducer-conventions.md)).\n- That directory contains `\u003CKEY>\u002Fverdict.json` files for the\n  campaign's candidates (at least one).\n\nNo tracker access required — the skill operates entirely on\non-disk artefacts.\n\n---\n\n## Inputs\n\n| Selector | Resolves to |\n|---|---|\n| `stats \u003Ccampaign-dir>` (default) | path to a campaign directory |\n| `--markdown` | emit markdown instead of HTML |\n| `--tables-only` | emit terminal-rendered tables only (no hero cards, no recommendations) |\n| `--output \u003Cfile>` | write to a file instead of stdout |\n| `--component \u003Cname>` | filter the dashboard to one component |\n\nThe default output is HTML to stdout; the user pipes it to a file\nor opens it directly.\n\n---\n\n## Step 0 — Pre-flight\n\n1. **Campaign directory exists** at the supplied path.\n2. **At least one `verdict.json`** present under the directory.\n3. **Override consultation** — see *Adopter overrides* above.\n4. **Drift check** — see *Snapshot drift* above.\n\nIf the directory has multiple campaign subdirs (e.g., the user\npointed at `\u003Cscratch>\u002F`), prompt which to use.\n\n---\n\n## Step 1 — Fetch the verdicts\n\nRead every `verdict.json` under the campaign directory. Parse and\nschema-validate each per\n[`issue-reproducer\u002Fverdict-composition.md`](..\u002Fissue-reproducer\u002Fverdict-composition.md).\nSkip and report any file that fails to parse; do not aggregate\npartial data.\n\nFull details: [`fetch.md`](fetch.md).\n\n---\n\n## Step 2 — Classify\n\nBucket each verdict by `classification` (10 labels) and orthogonally\nby `nature` (5 labels). Detect multi-case partial fixes from the\n`cases` array. Cross-tabulate classification × nature.\n\nFull details: [`classify.md`](classify.md).\n\n---\n\n## Step 3 — Aggregate\n\nCompute the dashboard's payload:\n\n- Total candidates, breakdown by classification and nature.\n- Health rating (Healthy \u002F Needs attention \u002F Action needed) per\n  the project's thresholds.\n- Action candidates (still-failing tail).\n- Closure candidates (fixed-on-master with strong evidence).\n- New-issue candidates (probe findings).\n- Per-component breakdown.\n\nFull details: [`aggregate.md`](aggregate.md).\n\n---\n\n## Step 4 — Render\n\nEmit the dashboard. Default is HTML with inline CSS (single self-\ncontained file); markdown and tables-only fallbacks honour the\n`--markdown` and `--tables-only` flags.\n\nFull details: [`render.md`](render.md).\n\n---\n\n## Step 5 — Output\n\nWrite to stdout (default), to a file if `--output` was passed, or\npresent in the agent's response if the user invoked the skill\ninteractively.\n\nThe HTML output is self-contained — no external CSS, no JS, no\nimages. A maintainer opens it in any browser without setup.\n\n---\n\n## Step 6 — Hand-back\n\nSurface to the user:\n\n- The path to the rendered output (if file mode).\n- Headline numbers (count of still-failing, count of new-issue\n  candidates).\n- Recommended next actions:\n  - For each still-failing candidate: `\u002Fmagpie-issue-fix-workflow \u003CKEY>`.\n  - For each closure candidate: a manual close via the tracker.\n  - For each new-issue candidate: a manual file via the tracker.\n\nThe skill never executes any of these next actions — it only\nrecommends.\n\n---\n\n## Hard rules\n\n- **Never modify campaign artefacts.** Read-only on the campaign\n  directory; no re-running `issue-reproducer`, no rewriting\n  `verdict.json`.\n- **Never post to `\u003Cissue-tracker>`** — the dashboard is a local\n  view; tracker writes go through other skills.\n- **Never aggregate across campaigns** without an explicit user\n  prompt. Each campaign's verdicts are scoped to one\n  `\u003Ccampaign-id>`.\n- **Never invent counts.** If a `verdict.json` failed to parse,\n  it's surfaced as a parse error, not counted in the totals.\n\n---\n\n## Failure modes\n\n| Symptom | Likely cause | Remediation |\n|---|---|---|\n| Campaign directory contains no `verdict.json` files | Campaign hasn't run yet, or paths are wrong | Invoke `issue-reassess` to populate, or correct the path |\n| `verdict.json` parse error on N files | Schema drift, manual edits, or interrupted campaign run | Surface the failing paths; do not aggregate partial data |\n| All verdicts classified `cannot-run-*` | Pool was shape-D \u002F shape-H heavy, or runtime is broken | Surface in the dashboard's *\"limitations\"* section |\n| Health rating threshold seems wrong for this project | Project's defaults don't match its scale | Override via `.apache-magpie-overrides\u002Fissue-reassess-stats.md` |\n| Age bands don't match the project's pace | \"Recent\" is project-relative; defaults assume a moderately active project | Override the band edges via `.apache-magpie-overrides\u002Fissue-reassess-stats.md` |\n\n---\n\n## References\n\n- [`fetch.md`](fetch.md) — reading verdict files.\n- [`classify.md`](classify.md) — classification + nature bucketing.\n- [`aggregate.md`](aggregate.md) — health rating, action\n  candidates, recommendation rules.\n- [`render.md`](render.md) — HTML layout, markdown fallback,\n  recommendation panel.\n- [`issue-reassess`](..\u002Fissue-reassess\u002FSKILL.md) — producer of\n  the verdicts this skill consumes.\n- [`issue-reproducer\u002Fverdict-composition.md`](..\u002Fissue-reproducer\u002Fverdict-composition.md) —\n  the schema being read.\n- [`pr-management-stats`](..\u002Fpr-management-stats\u002FSKILL.md) — the\n  structural template this skill mirrors.\n- [`tools\u002Fdashboard-generator\u002F`](..\u002F..\u002Ftools\u002Fdashboard-generator\u002F) —\n  reference implementation that produces the same output\n  deterministically (for adopters who want CI-rendered dashboards\n  without invoking the agent).\n- [`docs\u002Fissue-management\u002FREADME.md`](..\u002F..\u002Fdocs\u002Fissue-management\u002FREADME.md) —\n  family overview.\n",{"data":41,"body":46},{"name":4,"family":42,"mode":43,"description":6,"when_to_use":44,"capability":45,"license":25},"issue","Meta","When a maintainer asks \"what's the state of the reassessment\ncampaign\", \"give me the dashboard for the recent sweep\", or\n\"which issues still fail across pool runs\". Also as a\npre-release check on whether the EOL pool has dropped, and\nas a periodic health-of-the-backlog view.\n","capability:stats",{"type":47,"children":48},"root",[49,57,93,131,148,152,159,210,244,254,271,281,284,290,329,347,350,356,388,391,397,431,436,439,445,558,563,566,572,631,644,647,653,677,692,695,701,730,744,747,753,758,791,805,808,814,833,847,850,856,869,874,877,883,888,931,936,939,945,1020,1023,1029,1188,1191,1197],{"type":50,"tag":51,"props":52,"children":54},"element","h1",{"id":53},"issue-reassess-stats",[55],{"type":56,"value":53},"text",{"type":50,"tag":58,"props":59,"children":60},"p",{},[61,63,70,72,83,85,91],{"type":56,"value":62},"Read-only dashboard skill over the ",{"type":50,"tag":64,"props":65,"children":67},"code",{"className":66},[],[68],{"type":56,"value":69},"verdict.json",{"type":56,"value":71}," artefacts\nproduced by ",{"type":50,"tag":73,"props":74,"children":76},"a",{"href":75},"..\u002Fissue-reassess\u002FSKILL.md",[77],{"type":50,"tag":64,"props":78,"children":80},{"className":79},[],[81],{"type":56,"value":82},"issue-reassess",{"type":56,"value":84},"\ncampaigns. Surfaces a health rating, classification distribution,\nthe ",{"type":50,"tag":64,"props":86,"children":88},{"className":87},[],[89],{"type":56,"value":90},"still-fails-*",{"type":56,"value":92}," action tail, partial-fix surfaces, new-issue\ncandidates from cross-family probes, and per-component breakdowns.",{"type":50,"tag":58,"props":94,"children":95},{},[96,98,106,108,114,116,122,124,129],{"type":56,"value":97},"The skill is the read-only counterpart to\n",{"type":50,"tag":73,"props":99,"children":100},{"href":75},[101],{"type":50,"tag":64,"props":102,"children":104},{"className":103},[],[105],{"type":56,"value":82},{"type":56,"value":107}," — both consume the\nsame on-disk artefacts. Where reassess ",{"type":50,"tag":109,"props":110,"children":111},"strong",{},[112],{"type":56,"value":113},"writes",{"type":56,"value":115}," verdicts (one\nper candidate) and a ",{"type":50,"tag":64,"props":117,"children":119},{"className":118},[],[120],{"type":56,"value":121},"report.md",{"type":56,"value":123},", this skill ",{"type":50,"tag":109,"props":125,"children":126},{},[127],{"type":56,"value":128},"renders",{"type":56,"value":130}," an at-a-\nglance dashboard for the maintainer to scan.",{"type":50,"tag":58,"props":132,"children":133},{},[134,136,146],{"type":56,"value":135},"Modelled on ",{"type":50,"tag":73,"props":137,"children":139},{"href":138},"..\u002Fpr-management-stats\u002FSKILL.md",[140],{"type":50,"tag":64,"props":141,"children":143},{"className":142},[],[144],{"type":56,"value":145},"pr-management-stats",{"type":56,"value":147},".",{"type":50,"tag":149,"props":150,"children":151},"hr",{},[],{"type":50,"tag":153,"props":154,"children":156},"h2",{"id":155},"golden-rules",[157],{"type":56,"value":158},"Golden rules",{"type":50,"tag":58,"props":160,"children":161},{},[162,167,169,174,176,181,183,187,189,195,197,201,203,209],{"type":50,"tag":109,"props":163,"children":164},{},[165],{"type":56,"value":166},"Golden rule 1 — read-only on tracker AND on campaign\nartefacts.",{"type":56,"value":168}," This skill reads ",{"type":50,"tag":64,"props":170,"children":172},{"className":171},[],[173],{"type":56,"value":69},{"type":56,"value":175}," files and emits HTML.\nIt does ",{"type":50,"tag":109,"props":177,"children":178},{},[179],{"type":56,"value":180},"not",{"type":56,"value":182}," modify any campaign artefact, does ",{"type":50,"tag":109,"props":184,"children":185},{},[186],{"type":56,"value":180},{"type":56,"value":188}," post to\n",{"type":50,"tag":64,"props":190,"children":192},{"className":191},[],[193],{"type":56,"value":194},"\u003Cissue-tracker>",{"type":56,"value":196},", does ",{"type":50,"tag":109,"props":198,"children":199},{},[200],{"type":56,"value":180},{"type":56,"value":202}," re-invoke ",{"type":50,"tag":64,"props":204,"children":206},{"className":205},[],[207],{"type":56,"value":208},"issue-reproducer",{"type":56,"value":147},{"type":50,"tag":58,"props":211,"children":212},{},[213,218,220,226,228,234,236,242],{"type":50,"tag":109,"props":214,"children":215},{},[216],{"type":56,"value":217},"Golden rule 2 — HTML by default.",{"type":56,"value":219}," The dashboard is designed for\nthe ",{"type":50,"tag":221,"props":222,"children":223},"em",{},[224],{"type":56,"value":225},"\"what should I do today\"",{"type":56,"value":227}," glance. Markdown and tables-only\nfallbacks are available for terminal pipelines (",{"type":50,"tag":64,"props":229,"children":231},{"className":230},[],[232],{"type":56,"value":233},"--markdown",{"type":56,"value":235},",\n",{"type":50,"tag":64,"props":237,"children":239},{"className":238},[],[240],{"type":56,"value":241},"--tables-only",{"type":56,"value":243},").",{"type":50,"tag":58,"props":245,"children":246},{},[247,252],{"type":50,"tag":109,"props":248,"children":249},{},[250],{"type":56,"value":251},"Golden rule 3 — surface action candidates first.",{"type":56,"value":253}," The dashboard\nopens with the still-failing-bug count and the new-issue\ncandidates from probes — these are where work happens. The bulk\nfixed-on-master \u002F cannot-run-* counts come second.",{"type":50,"tag":58,"props":255,"children":256},{},[257,262,264,269],{"type":50,"tag":109,"props":258,"children":259},{},[260],{"type":56,"value":261},"Golden rule 4 — fresh read on every invocation.",{"type":56,"value":263}," The dashboard\nre-reads ",{"type":50,"tag":64,"props":265,"children":267},{"className":266},[],[268],{"type":56,"value":69},{"type":56,"value":270}," files on every run; no in-memory caching.\nThis makes the dashboard a coherent snapshot of the campaign\nstate at the moment of invocation.",{"type":50,"tag":58,"props":272,"children":273},{},[274,279],{"type":50,"tag":109,"props":275,"children":276},{},[277],{"type":56,"value":278},"Golden rule 5 — multi-campaign reads are explicit.",{"type":56,"value":280}," When the\nuser points the skill at a directory that contains multiple\ncampaign subdirectories, it asks which one — never silently\naggregates across campaigns.",{"type":50,"tag":149,"props":282,"children":283},{},[],{"type":50,"tag":153,"props":285,"children":287},{"id":286},"adopter-overrides",[288],{"type":56,"value":289},"Adopter overrides",{"type":50,"tag":58,"props":291,"children":292},{},[293,295,305,307,316,318,327],{"type":56,"value":294},"Before running the default behaviour documented below, this skill\nconsults\n",{"type":50,"tag":73,"props":296,"children":298},{"href":297},"..\u002F..\u002Fdocs\u002Fsetup\u002Fagentic-overrides.md",[299],{"type":50,"tag":64,"props":300,"children":302},{"className":301},[],[303],{"type":56,"value":304},".apache-magpie-local\u002Fissue-reassess-stats.md",{"type":56,"value":306}," (personal, gitignored) and ",{"type":50,"tag":73,"props":308,"children":309},{"href":297},[310],{"type":50,"tag":64,"props":311,"children":313},{"className":312},[],[314],{"type":56,"value":315},".apache-magpie-overrides\u002Fissue-reassess-stats.md",{"type":56,"value":317}," (committed, project-wide)\nin the adopter repo if it exists, and applies any agent-readable\noverrides it finds. See\n",{"type":50,"tag":73,"props":319,"children":320},{"href":297},[321],{"type":50,"tag":64,"props":322,"children":324},{"className":323},[],[325],{"type":56,"value":326},"docs\u002Fsetup\u002Fagentic-overrides.md",{"type":56,"value":328},"\nfor the contract.",{"type":50,"tag":58,"props":330,"children":331},{},[332,337,339,345],{"type":50,"tag":109,"props":333,"children":334},{},[335],{"type":56,"value":336},"Hard rule",{"type":56,"value":338},": agents NEVER modify the snapshot under\n",{"type":50,"tag":64,"props":340,"children":342},{"className":341},[],[343],{"type":56,"value":344},"\u003Cadopter-repo>\u002F.apache-magpie\u002F",{"type":56,"value":346},". Local modifications go in the\noverride file.",{"type":50,"tag":149,"props":348,"children":349},{},[],{"type":50,"tag":153,"props":351,"children":353},{"id":352},"snapshot-drift",[354],{"type":56,"value":355},"Snapshot drift",{"type":50,"tag":58,"props":357,"children":358},{},[359,361,367,369,375,377,387],{"type":56,"value":360},"Also at the top of every run, this skill compares the gitignored\n",{"type":50,"tag":64,"props":362,"children":364},{"className":363},[],[365],{"type":56,"value":366},".apache-magpie.local.lock",{"type":56,"value":368}," (per-machine fetch) against the\ncommitted ",{"type":50,"tag":64,"props":370,"children":372},{"className":371},[],[373],{"type":56,"value":374},".apache-magpie.lock",{"type":56,"value":376}," (the project pin). On mismatch\nthe skill surfaces the gap and proposes\n",{"type":50,"tag":73,"props":378,"children":380},{"href":379},"..\u002Fsetup\u002Fupgrade.md",[381],{"type":50,"tag":64,"props":382,"children":384},{"className":383},[],[385],{"type":56,"value":386},"\u002Fmagpie-setup upgrade",{"type":56,"value":147},{"type":50,"tag":149,"props":389,"children":390},{},[],{"type":50,"tag":153,"props":392,"children":394},{"id":393},"prerequisites",[395],{"type":56,"value":396},"Prerequisites",{"type":50,"tag":398,"props":399,"children":400},"ul",{},[401,418],{"type":50,"tag":402,"props":403,"children":404},"li",{},[405,407,417],{"type":56,"value":406},"A campaign directory exists at the path the user supplies (or\nthe project's default per\n",{"type":50,"tag":73,"props":408,"children":410},{"href":409},"..\u002F..\u002Fprojects\u002F_template\u002Freproducer-conventions.md",[411],{"type":50,"tag":64,"props":412,"children":414},{"className":413},[],[415],{"type":56,"value":416},"\u003Cproject-config>\u002Freproducer-conventions.md",{"type":56,"value":243},{"type":50,"tag":402,"props":419,"children":420},{},[421,423,429],{"type":56,"value":422},"That directory contains ",{"type":50,"tag":64,"props":424,"children":426},{"className":425},[],[427],{"type":56,"value":428},"\u003CKEY>\u002Fverdict.json",{"type":56,"value":430}," files for the\ncampaign's candidates (at least one).",{"type":50,"tag":58,"props":432,"children":433},{},[434],{"type":56,"value":435},"No tracker access required — the skill operates entirely on\non-disk artefacts.",{"type":50,"tag":149,"props":437,"children":438},{},[],{"type":50,"tag":153,"props":440,"children":442},{"id":441},"inputs",[443],{"type":56,"value":444},"Inputs",{"type":50,"tag":446,"props":447,"children":448},"table",{},[449,468],{"type":50,"tag":450,"props":451,"children":452},"thead",{},[453],{"type":50,"tag":454,"props":455,"children":456},"tr",{},[457,463],{"type":50,"tag":458,"props":459,"children":460},"th",{},[461],{"type":56,"value":462},"Selector",{"type":50,"tag":458,"props":464,"children":465},{},[466],{"type":56,"value":467},"Resolves to",{"type":50,"tag":469,"props":470,"children":471},"tbody",{},[472,492,508,524,541],{"type":50,"tag":454,"props":473,"children":474},{},[475,487],{"type":50,"tag":476,"props":477,"children":478},"td",{},[479,485],{"type":50,"tag":64,"props":480,"children":482},{"className":481},[],[483],{"type":56,"value":484},"stats \u003Ccampaign-dir>",{"type":56,"value":486}," (default)",{"type":50,"tag":476,"props":488,"children":489},{},[490],{"type":56,"value":491},"path to a campaign directory",{"type":50,"tag":454,"props":493,"children":494},{},[495,503],{"type":50,"tag":476,"props":496,"children":497},{},[498],{"type":50,"tag":64,"props":499,"children":501},{"className":500},[],[502],{"type":56,"value":233},{"type":50,"tag":476,"props":504,"children":505},{},[506],{"type":56,"value":507},"emit markdown instead of HTML",{"type":50,"tag":454,"props":509,"children":510},{},[511,519],{"type":50,"tag":476,"props":512,"children":513},{},[514],{"type":50,"tag":64,"props":515,"children":517},{"className":516},[],[518],{"type":56,"value":241},{"type":50,"tag":476,"props":520,"children":521},{},[522],{"type":56,"value":523},"emit terminal-rendered tables only (no hero cards, no recommendations)",{"type":50,"tag":454,"props":525,"children":526},{},[527,536],{"type":50,"tag":476,"props":528,"children":529},{},[530],{"type":50,"tag":64,"props":531,"children":533},{"className":532},[],[534],{"type":56,"value":535},"--output \u003Cfile>",{"type":50,"tag":476,"props":537,"children":538},{},[539],{"type":56,"value":540},"write to a file instead of stdout",{"type":50,"tag":454,"props":542,"children":543},{},[544,553],{"type":50,"tag":476,"props":545,"children":546},{},[547],{"type":50,"tag":64,"props":548,"children":550},{"className":549},[],[551],{"type":56,"value":552},"--component \u003Cname>",{"type":50,"tag":476,"props":554,"children":555},{},[556],{"type":56,"value":557},"filter the dashboard to one component",{"type":50,"tag":58,"props":559,"children":560},{},[561],{"type":56,"value":562},"The default output is HTML to stdout; the user pipes it to a file\nor opens it directly.",{"type":50,"tag":149,"props":564,"children":565},{},[],{"type":50,"tag":153,"props":567,"children":569},{"id":568},"step-0-pre-flight",[570],{"type":56,"value":571},"Step 0 — Pre-flight",{"type":50,"tag":573,"props":574,"children":575},"ol",{},[576,586,601,617],{"type":50,"tag":402,"props":577,"children":578},{},[579,584],{"type":50,"tag":109,"props":580,"children":581},{},[582],{"type":56,"value":583},"Campaign directory exists",{"type":56,"value":585}," at the supplied path.",{"type":50,"tag":402,"props":587,"children":588},{},[589,599],{"type":50,"tag":109,"props":590,"children":591},{},[592,594],{"type":56,"value":593},"At least one ",{"type":50,"tag":64,"props":595,"children":597},{"className":596},[],[598],{"type":56,"value":69},{"type":56,"value":600}," present under the directory.",{"type":50,"tag":402,"props":602,"children":603},{},[604,609,611,615],{"type":50,"tag":109,"props":605,"children":606},{},[607],{"type":56,"value":608},"Override consultation",{"type":56,"value":610}," — see ",{"type":50,"tag":221,"props":612,"children":613},{},[614],{"type":56,"value":289},{"type":56,"value":616}," above.",{"type":50,"tag":402,"props":618,"children":619},{},[620,625,626,630],{"type":50,"tag":109,"props":621,"children":622},{},[623],{"type":56,"value":624},"Drift check",{"type":56,"value":610},{"type":50,"tag":221,"props":627,"children":628},{},[629],{"type":56,"value":355},{"type":56,"value":616},{"type":50,"tag":58,"props":632,"children":633},{},[634,636,642],{"type":56,"value":635},"If the directory has multiple campaign subdirs (e.g., the user\npointed at ",{"type":50,"tag":64,"props":637,"children":639},{"className":638},[],[640],{"type":56,"value":641},"\u003Cscratch>\u002F",{"type":56,"value":643},"), prompt which to use.",{"type":50,"tag":149,"props":645,"children":646},{},[],{"type":50,"tag":153,"props":648,"children":650},{"id":649},"step-1-fetch-the-verdicts",[651],{"type":56,"value":652},"Step 1 — Fetch the verdicts",{"type":50,"tag":58,"props":654,"children":655},{},[656,658,663,665,675],{"type":56,"value":657},"Read every ",{"type":50,"tag":64,"props":659,"children":661},{"className":660},[],[662],{"type":56,"value":69},{"type":56,"value":664}," under the campaign directory. Parse and\nschema-validate each per\n",{"type":50,"tag":73,"props":666,"children":668},{"href":667},"..\u002Fissue-reproducer\u002Fverdict-composition.md",[669],{"type":50,"tag":64,"props":670,"children":672},{"className":671},[],[673],{"type":56,"value":674},"issue-reproducer\u002Fverdict-composition.md",{"type":56,"value":676},".\nSkip and report any file that fails to parse; do not aggregate\npartial data.",{"type":50,"tag":58,"props":678,"children":679},{},[680,682,691],{"type":56,"value":681},"Full details: ",{"type":50,"tag":73,"props":683,"children":685},{"href":684},"fetch.md",[686],{"type":50,"tag":64,"props":687,"children":689},{"className":688},[],[690],{"type":56,"value":684},{"type":56,"value":147},{"type":50,"tag":149,"props":693,"children":694},{},[],{"type":50,"tag":153,"props":696,"children":698},{"id":697},"step-2-classify",[699],{"type":56,"value":700},"Step 2 — Classify",{"type":50,"tag":58,"props":702,"children":703},{},[704,706,712,714,720,722,728],{"type":56,"value":705},"Bucket each verdict by ",{"type":50,"tag":64,"props":707,"children":709},{"className":708},[],[710],{"type":56,"value":711},"classification",{"type":56,"value":713}," (10 labels) and orthogonally\nby ",{"type":50,"tag":64,"props":715,"children":717},{"className":716},[],[718],{"type":56,"value":719},"nature",{"type":56,"value":721}," (5 labels). Detect multi-case partial fixes from the\n",{"type":50,"tag":64,"props":723,"children":725},{"className":724},[],[726],{"type":56,"value":727},"cases",{"type":56,"value":729}," array. Cross-tabulate classification × nature.",{"type":50,"tag":58,"props":731,"children":732},{},[733,734,743],{"type":56,"value":681},{"type":50,"tag":73,"props":735,"children":737},{"href":736},"classify.md",[738],{"type":50,"tag":64,"props":739,"children":741},{"className":740},[],[742],{"type":56,"value":736},{"type":56,"value":147},{"type":50,"tag":149,"props":745,"children":746},{},[],{"type":50,"tag":153,"props":748,"children":750},{"id":749},"step-3-aggregate",[751],{"type":56,"value":752},"Step 3 — Aggregate",{"type":50,"tag":58,"props":754,"children":755},{},[756],{"type":56,"value":757},"Compute the dashboard's payload:",{"type":50,"tag":398,"props":759,"children":760},{},[761,766,771,776,781,786],{"type":50,"tag":402,"props":762,"children":763},{},[764],{"type":56,"value":765},"Total candidates, breakdown by classification and nature.",{"type":50,"tag":402,"props":767,"children":768},{},[769],{"type":56,"value":770},"Health rating (Healthy \u002F Needs attention \u002F Action needed) per\nthe project's thresholds.",{"type":50,"tag":402,"props":772,"children":773},{},[774],{"type":56,"value":775},"Action candidates (still-failing tail).",{"type":50,"tag":402,"props":777,"children":778},{},[779],{"type":56,"value":780},"Closure candidates (fixed-on-master with strong evidence).",{"type":50,"tag":402,"props":782,"children":783},{},[784],{"type":56,"value":785},"New-issue candidates (probe findings).",{"type":50,"tag":402,"props":787,"children":788},{},[789],{"type":56,"value":790},"Per-component breakdown.",{"type":50,"tag":58,"props":792,"children":793},{},[794,795,804],{"type":56,"value":681},{"type":50,"tag":73,"props":796,"children":798},{"href":797},"aggregate.md",[799],{"type":50,"tag":64,"props":800,"children":802},{"className":801},[],[803],{"type":56,"value":797},{"type":56,"value":147},{"type":50,"tag":149,"props":806,"children":807},{},[],{"type":50,"tag":153,"props":809,"children":811},{"id":810},"step-4-render",[812],{"type":56,"value":813},"Step 4 — Render",{"type":50,"tag":58,"props":815,"children":816},{},[817,819,824,826,831],{"type":56,"value":818},"Emit the dashboard. Default is HTML with inline CSS (single self-\ncontained file); markdown and tables-only fallbacks honour the\n",{"type":50,"tag":64,"props":820,"children":822},{"className":821},[],[823],{"type":56,"value":233},{"type":56,"value":825}," and ",{"type":50,"tag":64,"props":827,"children":829},{"className":828},[],[830],{"type":56,"value":241},{"type":56,"value":832}," flags.",{"type":50,"tag":58,"props":834,"children":835},{},[836,837,846],{"type":56,"value":681},{"type":50,"tag":73,"props":838,"children":840},{"href":839},"render.md",[841],{"type":50,"tag":64,"props":842,"children":844},{"className":843},[],[845],{"type":56,"value":839},{"type":56,"value":147},{"type":50,"tag":149,"props":848,"children":849},{},[],{"type":50,"tag":153,"props":851,"children":853},{"id":852},"step-5-output",[854],{"type":56,"value":855},"Step 5 — Output",{"type":50,"tag":58,"props":857,"children":858},{},[859,861,867],{"type":56,"value":860},"Write to stdout (default), to a file if ",{"type":50,"tag":64,"props":862,"children":864},{"className":863},[],[865],{"type":56,"value":866},"--output",{"type":56,"value":868}," was passed, or\npresent in the agent's response if the user invoked the skill\ninteractively.",{"type":50,"tag":58,"props":870,"children":871},{},[872],{"type":56,"value":873},"The HTML output is self-contained — no external CSS, no JS, no\nimages. A maintainer opens it in any browser without setup.",{"type":50,"tag":149,"props":875,"children":876},{},[],{"type":50,"tag":153,"props":878,"children":880},{"id":879},"step-6-hand-back",[881],{"type":56,"value":882},"Step 6 — Hand-back",{"type":50,"tag":58,"props":884,"children":885},{},[886],{"type":56,"value":887},"Surface to the user:",{"type":50,"tag":398,"props":889,"children":890},{},[891,896,901],{"type":50,"tag":402,"props":892,"children":893},{},[894],{"type":56,"value":895},"The path to the rendered output (if file mode).",{"type":50,"tag":402,"props":897,"children":898},{},[899],{"type":56,"value":900},"Headline numbers (count of still-failing, count of new-issue\ncandidates).",{"type":50,"tag":402,"props":902,"children":903},{},[904,906],{"type":56,"value":905},"Recommended next actions:\n",{"type":50,"tag":398,"props":907,"children":908},{},[909,921,926],{"type":50,"tag":402,"props":910,"children":911},{},[912,914,920],{"type":56,"value":913},"For each still-failing candidate: ",{"type":50,"tag":64,"props":915,"children":917},{"className":916},[],[918],{"type":56,"value":919},"\u002Fmagpie-issue-fix-workflow \u003CKEY>",{"type":56,"value":147},{"type":50,"tag":402,"props":922,"children":923},{},[924],{"type":56,"value":925},"For each closure candidate: a manual close via the tracker.",{"type":50,"tag":402,"props":927,"children":928},{},[929],{"type":56,"value":930},"For each new-issue candidate: a manual file via the tracker.",{"type":50,"tag":58,"props":932,"children":933},{},[934],{"type":56,"value":935},"The skill never executes any of these next actions — it only\nrecommends.",{"type":50,"tag":149,"props":937,"children":938},{},[],{"type":50,"tag":153,"props":940,"children":942},{"id":941},"hard-rules",[943],{"type":56,"value":944},"Hard rules",{"type":50,"tag":398,"props":946,"children":947},{},[948,971,986,1003],{"type":50,"tag":402,"props":949,"children":950},{},[951,956,958,963,965,970],{"type":50,"tag":109,"props":952,"children":953},{},[954],{"type":56,"value":955},"Never modify campaign artefacts.",{"type":56,"value":957}," Read-only on the campaign\ndirectory; no re-running ",{"type":50,"tag":64,"props":959,"children":961},{"className":960},[],[962],{"type":56,"value":208},{"type":56,"value":964},", no rewriting\n",{"type":50,"tag":64,"props":966,"children":968},{"className":967},[],[969],{"type":56,"value":69},{"type":56,"value":147},{"type":50,"tag":402,"props":972,"children":973},{},[974,984],{"type":50,"tag":109,"props":975,"children":976},{},[977,979],{"type":56,"value":978},"Never post to ",{"type":50,"tag":64,"props":980,"children":982},{"className":981},[],[983],{"type":56,"value":194},{"type":56,"value":985}," — the dashboard is a local\nview; tracker writes go through other skills.",{"type":50,"tag":402,"props":987,"children":988},{},[989,994,996,1002],{"type":50,"tag":109,"props":990,"children":991},{},[992],{"type":56,"value":993},"Never aggregate across campaigns",{"type":56,"value":995}," without an explicit user\nprompt. Each campaign's verdicts are scoped to one\n",{"type":50,"tag":64,"props":997,"children":999},{"className":998},[],[1000],{"type":56,"value":1001},"\u003Ccampaign-id>",{"type":56,"value":147},{"type":50,"tag":402,"props":1004,"children":1005},{},[1006,1011,1013,1018],{"type":50,"tag":109,"props":1007,"children":1008},{},[1009],{"type":56,"value":1010},"Never invent counts.",{"type":56,"value":1012}," If a ",{"type":50,"tag":64,"props":1014,"children":1016},{"className":1015},[],[1017],{"type":56,"value":69},{"type":56,"value":1019}," failed to parse,\nit's surfaced as a parse error, not counted in the totals.",{"type":50,"tag":149,"props":1021,"children":1022},{},[],{"type":50,"tag":153,"props":1024,"children":1026},{"id":1025},"failure-modes",[1027],{"type":56,"value":1028},"Failure modes",{"type":50,"tag":446,"props":1030,"children":1031},{},[1032,1053],{"type":50,"tag":450,"props":1033,"children":1034},{},[1035],{"type":50,"tag":454,"props":1036,"children":1037},{},[1038,1043,1048],{"type":50,"tag":458,"props":1039,"children":1040},{},[1041],{"type":56,"value":1042},"Symptom",{"type":50,"tag":458,"props":1044,"children":1045},{},[1046],{"type":56,"value":1047},"Likely cause",{"type":50,"tag":458,"props":1049,"children":1050},{},[1051],{"type":56,"value":1052},"Remediation",{"type":50,"tag":469,"props":1054,"children":1055},{},[1056,1088,1111,1142,1165],{"type":50,"tag":454,"props":1057,"children":1058},{},[1059,1071,1076],{"type":50,"tag":476,"props":1060,"children":1061},{},[1062,1064,1069],{"type":56,"value":1063},"Campaign directory contains no ",{"type":50,"tag":64,"props":1065,"children":1067},{"className":1066},[],[1068],{"type":56,"value":69},{"type":56,"value":1070}," files",{"type":50,"tag":476,"props":1072,"children":1073},{},[1074],{"type":56,"value":1075},"Campaign hasn't run yet, or paths are wrong",{"type":50,"tag":476,"props":1077,"children":1078},{},[1079,1081,1086],{"type":56,"value":1080},"Invoke ",{"type":50,"tag":64,"props":1082,"children":1084},{"className":1083},[],[1085],{"type":56,"value":82},{"type":56,"value":1087}," to populate, or correct the path",{"type":50,"tag":454,"props":1089,"children":1090},{},[1091,1101,1106],{"type":50,"tag":476,"props":1092,"children":1093},{},[1094,1099],{"type":50,"tag":64,"props":1095,"children":1097},{"className":1096},[],[1098],{"type":56,"value":69},{"type":56,"value":1100}," parse error on N files",{"type":50,"tag":476,"props":1102,"children":1103},{},[1104],{"type":56,"value":1105},"Schema drift, manual edits, or interrupted campaign run",{"type":50,"tag":476,"props":1107,"children":1108},{},[1109],{"type":56,"value":1110},"Surface the failing paths; do not aggregate partial data",{"type":50,"tag":454,"props":1112,"children":1113},{},[1114,1125,1130],{"type":50,"tag":476,"props":1115,"children":1116},{},[1117,1119],{"type":56,"value":1118},"All verdicts classified ",{"type":50,"tag":64,"props":1120,"children":1122},{"className":1121},[],[1123],{"type":56,"value":1124},"cannot-run-*",{"type":50,"tag":476,"props":1126,"children":1127},{},[1128],{"type":56,"value":1129},"Pool was shape-D \u002F shape-H heavy, or runtime is broken",{"type":50,"tag":476,"props":1131,"children":1132},{},[1133,1135,1140],{"type":56,"value":1134},"Surface in the dashboard's ",{"type":50,"tag":221,"props":1136,"children":1137},{},[1138],{"type":56,"value":1139},"\"limitations\"",{"type":56,"value":1141}," section",{"type":50,"tag":454,"props":1143,"children":1144},{},[1145,1150,1155],{"type":50,"tag":476,"props":1146,"children":1147},{},[1148],{"type":56,"value":1149},"Health rating threshold seems wrong for this project",{"type":50,"tag":476,"props":1151,"children":1152},{},[1153],{"type":56,"value":1154},"Project's defaults don't match its scale",{"type":50,"tag":476,"props":1156,"children":1157},{},[1158,1160],{"type":56,"value":1159},"Override via ",{"type":50,"tag":64,"props":1161,"children":1163},{"className":1162},[],[1164],{"type":56,"value":315},{"type":50,"tag":454,"props":1166,"children":1167},{},[1168,1173,1178],{"type":50,"tag":476,"props":1169,"children":1170},{},[1171],{"type":56,"value":1172},"Age bands don't match the project's pace",{"type":50,"tag":476,"props":1174,"children":1175},{},[1176],{"type":56,"value":1177},"\"Recent\" is project-relative; defaults assume a moderately active project",{"type":50,"tag":476,"props":1179,"children":1180},{},[1181,1183],{"type":56,"value":1182},"Override the band edges via ",{"type":50,"tag":64,"props":1184,"children":1186},{"className":1185},[],[1187],{"type":56,"value":315},{"type":50,"tag":149,"props":1189,"children":1190},{},[],{"type":50,"tag":153,"props":1192,"children":1194},{"id":1193},"references",[1195],{"type":56,"value":1196},"References",{"type":50,"tag":398,"props":1198,"children":1199},{},[1200,1213,1226,1239,1252,1265,1278,1291,1306],{"type":50,"tag":402,"props":1201,"children":1202},{},[1203,1211],{"type":50,"tag":73,"props":1204,"children":1205},{"href":684},[1206],{"type":50,"tag":64,"props":1207,"children":1209},{"className":1208},[],[1210],{"type":56,"value":684},{"type":56,"value":1212}," — reading verdict files.",{"type":50,"tag":402,"props":1214,"children":1215},{},[1216,1224],{"type":50,"tag":73,"props":1217,"children":1218},{"href":736},[1219],{"type":50,"tag":64,"props":1220,"children":1222},{"className":1221},[],[1223],{"type":56,"value":736},{"type":56,"value":1225}," — classification + nature bucketing.",{"type":50,"tag":402,"props":1227,"children":1228},{},[1229,1237],{"type":50,"tag":73,"props":1230,"children":1231},{"href":797},[1232],{"type":50,"tag":64,"props":1233,"children":1235},{"className":1234},[],[1236],{"type":56,"value":797},{"type":56,"value":1238}," — health rating, action\ncandidates, recommendation rules.",{"type":50,"tag":402,"props":1240,"children":1241},{},[1242,1250],{"type":50,"tag":73,"props":1243,"children":1244},{"href":839},[1245],{"type":50,"tag":64,"props":1246,"children":1248},{"className":1247},[],[1249],{"type":56,"value":839},{"type":56,"value":1251}," — HTML layout, markdown fallback,\nrecommendation panel.",{"type":50,"tag":402,"props":1253,"children":1254},{},[1255,1263],{"type":50,"tag":73,"props":1256,"children":1257},{"href":75},[1258],{"type":50,"tag":64,"props":1259,"children":1261},{"className":1260},[],[1262],{"type":56,"value":82},{"type":56,"value":1264}," — producer of\nthe verdicts this skill consumes.",{"type":50,"tag":402,"props":1266,"children":1267},{},[1268,1276],{"type":50,"tag":73,"props":1269,"children":1270},{"href":667},[1271],{"type":50,"tag":64,"props":1272,"children":1274},{"className":1273},[],[1275],{"type":56,"value":674},{"type":56,"value":1277}," —\nthe schema being read.",{"type":50,"tag":402,"props":1279,"children":1280},{},[1281,1289],{"type":50,"tag":73,"props":1282,"children":1283},{"href":138},[1284],{"type":50,"tag":64,"props":1285,"children":1287},{"className":1286},[],[1288],{"type":56,"value":145},{"type":56,"value":1290}," — the\nstructural template this skill mirrors.",{"type":50,"tag":402,"props":1292,"children":1293},{},[1294,1304],{"type":50,"tag":73,"props":1295,"children":1297},{"href":1296},"..\u002F..\u002Ftools\u002Fdashboard-generator\u002F",[1298],{"type":50,"tag":64,"props":1299,"children":1301},{"className":1300},[],[1302],{"type":56,"value":1303},"tools\u002Fdashboard-generator\u002F",{"type":56,"value":1305}," —\nreference implementation that produces the same output\ndeterministically (for adopters who want CI-rendered dashboards\nwithout invoking the agent).",{"type":50,"tag":402,"props":1307,"children":1308},{},[1309,1319],{"type":50,"tag":73,"props":1310,"children":1312},{"href":1311},"..\u002F..\u002Fdocs\u002Fissue-management\u002FREADME.md",[1313],{"type":50,"tag":64,"props":1314,"children":1316},{"className":1315},[],[1317],{"type":56,"value":1318},"docs\u002Fissue-management\u002FREADME.md",{"type":56,"value":1320}," —\nfamily overview.",{"items":1322,"total":1473},[1323,1341,1355,1366,1379,1392,1410,1421,1431,1442,1452,1462],{"slug":1324,"name":1324,"fn":1325,"description":1326,"org":1327,"tags":1328,"stars":1338,"repoUrl":1339,"updatedAt":1340},"datafusion-python","write Apache DataFusion Python code","Use when the user is writing datafusion-python (Apache DataFusion Python bindings) DataFrame or SQL code. Covers imports, data loading, DataFrame operations, expression building, SQL-to-DataFrame mappings, idiomatic patterns, and common pitfalls.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1329,1332,1335],{"name":1330,"slug":1331,"type":15},"Data Analysis","data-analysis",{"name":1333,"slug":1334,"type":15},"Python","python",{"name":1336,"slug":1337,"type":15},"SQL","sql",593,"https:\u002F\u002Fgithub.com\u002Fapache\u002Fdatafusion-python","2026-07-12T08:36:04.957626",{"slug":1342,"name":1342,"fn":1343,"description":1344,"org":1345,"tags":1346,"stars":1352,"repoUrl":1353,"updatedAt":1354},"bydbql","generate and execute BanyanDB BydbQL queries","Generate, validate, and optionally execute read-only BanyanDB BydbQL for STREAM, MEASURE, TRACE, and PROPERTY resources. Use when the user asks to query BanyanDB, translate natural language to BydbQL, inspect BanyanDB schema or data, validate BydbQL, or fetch raw BanyanDB records.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1347,1348,1351],{"name":20,"slug":21,"type":15},{"name":1349,"slug":1350,"type":15},"Database","database",{"name":1336,"slug":1337,"type":15},344,"https:\u002F\u002Fgithub.com\u002Fapache\u002Fskywalking-banyandb","2026-07-12T08:31:01.294423",{"slug":1356,"name":1356,"fn":1357,"description":1358,"org":1359,"tags":1360,"stars":1352,"repoUrl":1353,"updatedAt":1365},"compiling","compile and build BanyanDB projects","Compile and build the SkyWalking BanyanDB project. Use when the user asks to compile, build, or generate code for this project.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1361,1364],{"name":1362,"slug":1363,"type":15},"Build","build",{"name":17,"slug":18,"type":15},"2026-07-12T08:31:06.373309",{"slug":1367,"name":1367,"fn":1368,"description":1369,"org":1370,"tags":1371,"stars":1352,"repoUrl":1353,"updatedAt":1378},"gh-pull-request","create GitHub pull requests for BanyanDB","Create a GitHub pull request for SkyWalking BanyanDB. Use when the user asks to create a PR, submit changes, or open a pull request.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1372,1375],{"name":1373,"slug":1374,"type":15},"GitHub","github",{"name":1376,"slug":1377,"type":15},"Pull Requests","pull-requests","2026-07-12T08:31:03.792415",{"slug":1380,"name":1380,"fn":1381,"description":1382,"org":1383,"tags":1384,"stars":1352,"repoUrl":1353,"updatedAt":1391},"vendor-update","update Go and Node.js vendor dependencies","Upgrade Go\u002FNode.js vendor dependencies and sync tool versions. Use whenever the user says \"upgrade dependencies\", \"update vendors\", \"vendor update\", \"run vendor-upgrade\", \"bump dependencies\", \"update packages\", or asks to run the `vendor-update` Make target. This skill also checks `scripts\u002Fbuild\u002Fversion.mk` after upgrading to see if any tracked tool versions need updating too, and removes stale binaries from `bin\u002F` when versions change.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1385,1388],{"name":1386,"slug":1387,"type":15},"Go","go",{"name":1389,"slug":1390,"type":15},"Node.js","node-js","2026-07-12T08:31:02.555555",{"slug":1393,"name":1393,"fn":1394,"description":1395,"org":1396,"tags":1397,"stars":1407,"repoUrl":1408,"updatedAt":1409},"cayenne-cgen","generate Cayenne entity Java classes","Use this skill whenever the user wants to (re)generate Cayenne entity Java classes from a DataMap. Trigger on phrases like 'generate Java classes', 'regenerate entities', 'run cgen', 'create the entity classes', 'why is the Artist class missing fields', 'where did the `_Abstract*` classes come from', 'sync the entity classes with the model', or any request to materialize Java from the DataMap. Also trigger as a follow-up after modeling changes (someone added an entity, attribute, or relationship and now the Java side is stale). This skill exclusively uses the `mcp__cayenne__cgen_run` MCP tool — it does NOT use `mvn cayenne:cgen` or the Gradle cgen task.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1398,1401,1404],{"name":1399,"slug":1400,"type":15},"Data Modeling","data-modeling",{"name":1402,"slug":1403,"type":15},"Java","java",{"name":1405,"slug":1406,"type":15},"ORM","orm",343,"https:\u002F\u002Fgithub.com\u002Fapache\u002Fcayenne","2026-07-12T08:32:33.575211",{"slug":1411,"name":1411,"fn":1412,"description":1413,"org":1414,"tags":1415,"stars":1407,"repoUrl":1408,"updatedAt":1420},"cayenne-db-import","import database schema into Cayenne DataMaps","Use this skill when the user wants to import database schema metadata into a Cayenne DataMap — the *model\u002Fmapping only*, not names or Java classes. Trigger on phrases like 'reverse engineer the database', 'import the schema', 'generate a DataMap from my DB', 'add the new tables from the DB into the model', 'import the customer table', 'create entities from these tables', or any request to read database metadata to populate or update a DataMap's XML. This is for *full schema* or *bulk table* import; one-off a-la-carte entity additions belong in the cayenne-modeling skill. IMPORTANT — scope: this imports the mapping ONLY; it does not clean up the Object-layer names or (re)generate Java classes. When the user wants their whole project brought in line with the DB ('sync my project with the database', 'my schema changed, update everything', 'update my entities\u002Fclasses from the DB'), that is the end-to-end `cayenne-full-db-sync` skill, which runs this import and then name cleanup and class generation. To regenerate classes alone use `cayenne-cgen`. The skill runs reverse engineering directly via the `mcp__cayenne__dbimport_run` MCP tool when a DBConnector is already configured; otherwise it opens the CayenneModeler GUI via `mcp__cayenne__open_project` to configure the connection first.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1416,1417,1418,1419],{"name":1349,"slug":1350,"type":15},{"name":1402,"slug":1403,"type":15},{"name":1405,"slug":1406,"type":15},{"name":1336,"slug":1337,"type":15},"2026-07-19T05:40:33.655062",{"slug":1422,"name":1422,"fn":1423,"description":1424,"org":1425,"tags":1426,"stars":1407,"repoUrl":1408,"updatedAt":1430},"cayenne-full-db-sync","synchronize Cayenne projects with database","Use this skill when the user wants to bring their WHOLE Cayenne project in line with the database in one shot — the mapping, the Object-layer names, and the generated Java classes together. This is the end-to-end 'sync with the DB' workflow, and it orchestrates three skills in order: `cayenne-db-import` (import schema metadata into the DataMap) → `cayenne-model-naming` (polish the just-imported names) → `cayenne-cgen` (regenerate Java classes). Trigger on holistic phrases like 'sync my project with the database', 'sync with the DB', 'my schema changed, update everything', 'update my entities\u002Fclasses from the database', 'reverse engineer and regenerate the classes', 'import the new tables and rebuild the entities', 'full DB sync', 'bring the model and classes up to date with the DB'. The distinguishing signal is scope: the user wants the whole project (mapping + names + Java code), not just one stage. For the *model\u002Fmapping only* (no name cleanup, no class generation) use `cayenne-db-import`; to (re)generate classes alone use `cayenne-cgen`; to clean names alone use `cayenne-model-naming`. Uses the `mcp__cayenne__dbimport_run` and `mcp__cayenne__cgen_run` MCP tools via the sub-skills; does NOT use Maven or Gradle goals.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1427,1428,1429],{"name":1349,"slug":1350,"type":15},{"name":1402,"slug":1403,"type":15},{"name":1405,"slug":1406,"type":15},"2026-07-19T06:03:49.112969",{"slug":1432,"name":1432,"fn":1433,"description":1434,"org":1435,"tags":1436,"stars":1407,"repoUrl":1408,"updatedAt":1441},"cayenne-model-naming","clean up Cayenne object-layer names","Use this skill to clean up Object-layer names in a Cayenne DataMap — ObjEntity, ObjAttribute, and ObjRelationship names, plus DbRelationship names (the first-class unit of relationship cleanup — every FK has one whether or not an ObjRelationship was generated; the ObjRelationship name is synced to it when one exists) — so they read as descriptive, consistent Java. Trigger on phrases like 'clean up the model names', 'fix the entity names', 'these names look ugly', 'make the names descriptive', 'normalize the ObjEntity\u002Fattribute\u002Frelationship names', 'why is this relationship called team1', 'rename entities to be consistent', 'the import produced Gametype instead of GameType'. Invoke it on an explicit user request, or as a manual follow-up after a `cayenne-db-import` to polish the just-imported additions — it is never triggered automatically. IMPORTANT: this is a LIGHT polish pass — CayenneModeler's reverse-engineering already produces good names for the common case; only improve the specific things its deterministic algorithm cannot (run-together names with no separators like `gametype`, meaningless numbered names like `team1` from multiple relationships between two tables, and a common entity prefix that leaks into relationship names like `aaOrders`). Do NOT rewrite names that are already correct. This is Obj-layer naming polish; for structural model edits use `cayenne-modeling`, and for regenerating classes afterward use `cayenne-cgen`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1437,1438,1439,1440],{"name":1399,"slug":1400,"type":15},{"name":1349,"slug":1350,"type":15},{"name":1402,"slug":1403,"type":15},{"name":1405,"slug":1406,"type":15},"2026-07-22T05:35:32.342548",{"slug":1443,"name":1443,"fn":1444,"description":1445,"org":1446,"tags":1447,"stars":1407,"repoUrl":1408,"updatedAt":1451},"cayenne-modeler","manage Cayenne projects with CayenneModeler","Use this skill when the user explicitly wants to open CayenneModeler (the GUI) on a Cayenne project, or when the modeling task is inherently visual — reverse engineering (delegated to cayenne-db-import), bulk relationship layout, multi-entity visual refactoring. Trigger on phrases like 'open the Modeler', 'open in CayenneModeler', 'launch the GUI', 'edit visually', 'show me the project in the Modeler'. Do NOT trigger as a fallback for ordinary a-la-carte XML edits — those belong in the cayenne-modeling skill, which is faster and doesn't require the user to context-switch.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1448,1449,1450],{"name":1399,"slug":1400,"type":15},{"name":1402,"slug":1403,"type":15},{"name":1405,"slug":1406,"type":15},"2026-07-12T08:32:37.199428",{"slug":1453,"name":1453,"fn":1454,"description":1455,"org":1456,"tags":1457,"stars":1407,"repoUrl":1408,"updatedAt":1461},"cayenne-modeling","edit and extend Cayenne ORM models","Use this skill whenever the user wants to edit, inspect, or extend the Cayenne ORM model in a project — adding or modifying entities, attributes, relationships, embeddables, named queries, stored procedures, or DataNodes. Trigger on phrases like 'add an ObjEntity', 'add a DbEntity', 'add a relationship', 'expose this column as an attribute', 'create a new DataMap', 'add a named query', 'create an embeddable', 'add a stored procedure', 'change the attribute type', 'mark this column as nullable', 'rename this entity', or any mention of a Cayenne `*.map.xml` or `cayenne-*.xml` file. Also trigger when the user references modeling concepts (ObjEntity, DbEntity, ObjAttribute, DbAttribute, ObjRelationship, DbRelationship, Embeddable, dbEntityName, deleteRule, db-attribute-path, db-relationship-path, defaultPackage) in the context of a Cayenne-using app. This is the *primary* skill for a-la-carte ORM model manipulation — direct XML edits, not the Modeler GUI.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1458,1459,1460],{"name":1349,"slug":1350,"type":15},{"name":1402,"slug":1403,"type":15},{"name":1405,"slug":1406,"type":15},"2026-07-19T05:40:32.6889",{"slug":1463,"name":1463,"fn":1464,"description":1465,"org":1466,"tags":1467,"stars":1407,"repoUrl":1408,"updatedAt":1472},"cayenne-query","write and modify Cayenne database queries","Use this skill whenever the user wants to write or modify a Cayenne query — fetching entities by criteria, joining, prefetching to avoid N+1, ordering, paginating, aggregating, or running raw SQL through Cayenne. Trigger on phrases like 'query for X', 'fetch all artists where ...', 'write an ObjectSelect', 'use SQLSelect', 'use SelectById', 'add a prefetch', 'get distinct values', 'count rows', 'find by ID', 'load by primary key', 'build a Cayenne expression', 'why am I getting N+1', 'how do I paginate', 'select a single column', 'select columns into a DTO', 'named query in the DataMap'. Do NOT trigger for modeling changes (use cayenne-modeling) or runtime bootstrap (use cayenne-runtime).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1468,1469,1470,1471],{"name":1349,"slug":1350,"type":15},{"name":1402,"slug":1403,"type":15},{"name":1405,"slug":1406,"type":15},{"name":1336,"slug":1337,"type":15},"2026-07-12T08:32:35.072322",108,{"items":1475,"total":1572},[1476,1491,1507,1521,1537,1549,1559],{"slug":1477,"name":1477,"fn":1478,"description":1479,"org":1480,"tags":1481,"stars":22,"repoUrl":23,"updatedAt":1490},"generate-cve-json","generate CVE JSON documents","Generate a CVE 5.x JSON document from an \u003Ctracker> tracking\nissue, ready to paste into the Vulnogram `#source` tab of the ASF CVE tool\nat https:\u002F\u002Fcveprocess.apache.org\u002Fcve5\u002F\u003CCVE-ID>#source. The conversion is\ndeterministic: same issue in, same JSON bytes out. Handles multiple\ncredits (one per line) and multiple references (URLs extracted from the\nissue's \"Public advisory URL\" and \"PR with the fix\" fields; the\n\"Security mailing list thread\" field is treated as internal-only and\nnever exported).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1482,1485,1487],{"name":1483,"slug":1484,"type":15},"Compliance","compliance",{"name":1486,"slug":32,"type":15},"Security",{"name":1488,"slug":1489,"type":15},"Technical Writing","technical-writing","2026-07-12T08:35:41.218722",{"slug":1492,"name":1492,"fn":1493,"description":1494,"org":1495,"tags":1496,"stars":22,"repoUrl":23,"updatedAt":1506},"magpie-audit-finding-fix","fix findings from code audit tools","For a batch of findings from a non-security audit tool\n(`\u003Caudit-tool>` — ruff \u002F flake8 \u002F mypy \u002F pylint \u002F CodeQL \u002F\nApache Verum \u002F Apache Caer \u002F equivalent; full list in the body)\nagainst `\u003Cupstream>`, draft the smallest fix for each finding.\nRe-runs the tool after each batch to confirm the findings are\ncleared. Produces a commit and a hand-back artefact; never opens\na PR on autopilot or merges.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1497,1500,1503],{"name":1498,"slug":1499,"type":15},"Audit","audit",{"name":1501,"slug":1502,"type":15},"Code Analysis","code-analysis",{"name":1504,"slug":1505,"type":15},"Debugging","debugging","2026-07-12T08:35:13.930479",{"slug":1508,"name":1508,"fn":1509,"description":1510,"org":1511,"tags":1512,"stars":22,"repoUrl":23,"updatedAt":1520},"magpie-ci-runner-audit","audit GitHub Actions workflow runner compatibility","Read-only audit of GitHub Actions workflow runner compatibility\nfor one repository, an explicit repository set, one Apache project\nwith multiple repositories, or the full Apache GitHub org. Finds\nobsolete GitHub-hosted runner labels and macOS runner\u002Ftool\narchitecture mismatches. Produces TSV evidence files; never edits\nworkflows, opens PRs, or posts comments.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1513,1514,1517],{"name":1498,"slug":1499,"type":15},{"name":1515,"slug":1516,"type":15},"CI\u002FCD","ci-cd",{"name":1518,"slug":1519,"type":15},"GitHub Actions","github-actions","2026-07-12T08:34:30.320965",{"slug":1522,"name":1522,"fn":1523,"description":1524,"org":1525,"tags":1526,"stars":22,"repoUrl":23,"updatedAt":1536},"magpie-committer-onboarding","onboard Apache project committers","Post-vote committer and PMC onboarding for Apache projects.\nWalks the nominator through every step from ICLA check to\nwelcome announcement for both incubating podlings and\ngraduated top-level projects.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1527,1530,1533],{"name":1528,"slug":1529,"type":15},"Management","management",{"name":1531,"slug":1532,"type":15},"Operations","operations",{"name":1534,"slug":1535,"type":15},"Process Documentation","process-documentation","2026-07-12T08:33:35.628029",{"slug":1538,"name":1538,"fn":1539,"description":1540,"org":1541,"tags":1542,"stars":22,"repoUrl":23,"updatedAt":1548},"magpie-contributor-activity-sweep","generate contributor activity reports","Read-only GitHub activity card for a named contributor on \u003Cupstream>.\nFetches PR authorship, code-review activity, issues, and PR\u002Fissue\ncomments over a configurable window. Limited to GitHub-visible\nactivity — the body documents the off-GitHub tracks the nominator\nmust supply separately. No readiness verdict is produced; use\ncontributor-nomination for a full nomination brief.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1543,1544,1545],{"name":20,"slug":21,"type":15},{"name":1373,"slug":1374,"type":15},{"name":1546,"slug":1547,"type":15},"Reporting","reporting","2026-07-12T08:33:41.715859",{"slug":1550,"name":1550,"fn":1551,"description":1552,"org":1553,"tags":1554,"stars":22,"repoUrl":23,"updatedAt":1558},"magpie-contributor-nomination","generate contributor nomination briefs","Read-only nomination brief for a named GitHub contributor on\n\u003Cupstream>. Aggregates GitHub activity across all contribution\ntracks plus maintainer-supplied off-GitHub signal, and flags\nvendor-neutrality context — the evidence a PMC needs to open\na committer or PMC nomination thread.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1555,1556,1557],{"name":17,"slug":18,"type":15},{"name":1373,"slug":1374,"type":15},{"name":1546,"slug":1547,"type":15},"2026-07-12T08:33:39.211745",{"slug":1560,"name":1560,"fn":1561,"description":1562,"org":1563,"tags":1564,"stars":22,"repoUrl":23,"updatedAt":1571},"magpie-contributor-sentiment","measure contributor sentiment on GitHub repositories","Measures contributor-sentiment signals on \u003Cupstream> over a\nconfigurable window: thread tone (first-response classification),\ntime-to-first-reply (median hours), first-PR retention\n(second-PR rate), and reviewer load (Gini coefficient). Compares\neach signal against a pre-adoption baseline and produces a\nstructured gate report used to decide whether a skill family is\nready to advance from experimental to stable.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1565,1566,1569,1570],{"name":20,"slug":21,"type":15},{"name":1567,"slug":1568,"type":15},"Communications","communications",{"name":17,"slug":18,"type":15},{"name":1373,"slug":1374,"type":15},"2026-07-12T08:34:09.204167",71]