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
- arxdsilva/ai-loopstheir own version, first seen Nov 16, 2026
- qualitymd/quality.mdtheir own version, first seen Nov 15, 2026
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tooltheir own version, first seen Nov 8, 2026
- menot-you/n-soultheir own version, first seen Nov 1, 2026
- ansvisor/ansvisortheir own version, first seen Nov 1, 2026
- DataWithBaraa/claude-code-data-engineering-skillstheir own version, first seen Nov 1, 2026
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.
genomewalkerSkilltasks
Browse and resume tasks, threads, and background jobs across sessions
Also in 3 projects that use this
MicrosoftSkillreport
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
AnthropicSkillanalyze
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
AnthropicSkilldebug
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
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 4 projects that use this
SentrySkillreview
Fixture review skill.
Also in 5 projects that use this
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- google-gemini/gemini-cli★ 109ksame name
- H-mmer/pentest-agents★ 815same name
- boostsecurityio/poutine★ 535same name
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- ansvisor/ansvisor★ 241same name
- DataWithBaraa/claude-code-data-engineering-skills★ 84same name
- tam159/next-role★ 67same name
- qualitymd/quality.md★ 33same name
- ariaxhan/kernel-claude★ 15same name
- websublime/mister-anderson★ 3same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- canonSkill
- enrichmentSkill
- intakeSkill
- looseendsSkill
- maintenanceSkill
- memorySkill
- memorytoolSkill
- portalSkill
- recallSkill
- sharingSkill
- writepathSkill
The file
Files
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.
LeaderboardGuardrefuses for fixtures, and the rendered fixture report carries a "not a leaderboard" banner. ToMarkdownis pure (no timestamps/environment) so CI can assertdocs/benchmark.mdbyte-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,
kclamps, duplicates can't exceed 1.0, everything finite in[0,1]. - The benchmark calls
RecallScoring.Fusedirectly, which is exactly why production trust/ROI policy stays outsideFuse. - The quality report never mutates anything — it surfaces what other domains recorded.
- The analysed sample is bounded (
TotalMemoriesvsAnalyzedCount), 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 inAnalyzeAsync.src/Eidet.Core/Benchmark/{BenchmarkRunner,RetrievalMetrics,Scorecard}.cs— the scorecard.tools/Eidet.Bench/— the SWE Context Bench harness, its four ports, andLeaderboardGuard.tests/Eidet.Benchmark.Tests/GoldDataset.cs— extend this to add cases.
Gotchas
tools/Eidet.Benchlives outsidesrc/— asrc/**-scoped sweep misses it.docs/benchmark.mdanddocs/swe-context-bench.mdare 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.
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
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.

