agentleFS
stevehansenstevehansen/eidet/.claude/skills/quality/SKILL.md

quality

Skill4 starsChanged 54 days agoMITView on GitHub

Prime on Eidet's quality and benchmarking surfaces before changing them — QualityService's check battery and QualityReport behind /api/eidet/quality, the deterministic retrieval scorecard (BenchmarkRunner's fused-vs-flat-baseline arms, RetrievalMetrics, AmaCapability headings, the CI-asserted docs/benchmark.md), and the SWE Context Bench harness in tools/Eidet.Bench with its LeaderboardGuard. Use when the task touches a quality check, a retrieval metric, the gold dataset, eidet bench, or a benchmark number. Not for the ranking pipeline itself (see recall), not for the integrity auditor (see writepath).

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use tasks, report and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • genomewalkerSkill

    tasks

    Browse and resume tasks, threads, and background jobs across sessions

    Also in 3 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 4 projects that use this

  • AnthropicSkill

    analyze

    Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.

    Also in 3 projects that use this

  • AnthropicSkill

    debug

    Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

    Also in 4 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 5 projects that use this

The file

Files
SKILL.md

Quality & benchmarking — priming

Canonical spec: docs/domains/quality.md — read it for the check battery, the harness shape, all invariants, key files, and gotchas. Generated artifacts: docs/benchmark.md, docs/swe-context-bench.md.

Two questions: "is this repo's memory healthy?" (QualityService, advisory and read-only) and "does our ranking actually beat the baseline?" (deterministic scorecard + the SWE Context Bench harness).

Core invariants (get these right)

  • A leaderboard-shaped number may only come from the real dataset. LeaderboardGuard refuses for fixtures, and the rendered fixture report carries a "not a leaderboard" banner.
  • ToMarkdown is pure (no timestamps/environment) so CI can assert docs/benchmark.md byte-equal. Regenerate via the documented env var; never hand-edit.
  • Both arms run over the same candidate pools — the baseline must differ by ranking alone.
  • Report un-scoreable capabilities as not-evaluated, with the reason — never fabricate.
  • Metrics define edge cases out of existence: empty gold → 0, k clamps, duplicates can't exceed 1.0, everything finite in [0,1].
  • The benchmark calls RecallScoring.Fuse directly, which is exactly why production trust/ROI policy stays outside Fuse.
  • The quality report never mutates anything — it surfaces what other domains recorded.
  • The analysed sample is bounded (TotalMemories vs AnalyzedCount), and the integrity auditor is optional — a clean report isn't proof of a clean corpus.

Key files / reuse

  • src/Eidet.Core/Services/QualityService.cs — add a check to the fixed battery in AnalyzeAsync.
  • src/Eidet.Core/Benchmark/{BenchmarkRunner,RetrievalMetrics,Scorecard}.cs — the scorecard.
  • tools/Eidet.Bench/ — the SWE Context Bench harness, its four ports, and LeaderboardGuard.
  • tests/Eidet.Benchmark.Tests/GoldDataset.cs — extend this to add cases.

Gotchas

  • tools/Eidet.Bench lives outside src/ — a src/**-scoped sweep misses it.
  • docs/benchmark.md and docs/swe-context-bench.md are test-asserted; hand-edits fail CI.
  • The scorecard sync test skips silently off a non-checkout — green ≠ current.
  • The overall quality score is a heuristic aggregate; the individual issues are the signal.
  • The bundled fixture dataset is tiny and unrepresentative by design.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.