跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

mathlib-quality

Mathlib code quality and style enforcement for Lean 4

CBirkbeck · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add CBirkbeck/mathlib-quality --skill mathlib-quality

技能说明


name: mathlib-quality description: Mathlib code quality and style enforcement for Lean 4 trigger: filePatterns: - "*.lean" keywords: - mathlib - style - cleanup - golf - PR - submit - bump - upgrade - update - status - progress - bottleneck - stuck - frontier - blueprint - unformalise - unformalize - leanblueprint - latex - dep-graph - prose - sketch - render - mathlibable - mathlib-fit - mathlib-ready - generality - generalise - generalize

Mathlib Quality Skill

Activation Triggers

This skill activates when:

  • Working with .lean files intended for mathlib contribution
  • User mentions "mathlib style", "cleanup", "golf", "PR submission", or "pre-submit"
  • User asks to fix reviewer feedback on a mathlib PR
  • User wants to check code against mathlib conventions
  • User asks "what's the project status?", "where are we stuck?", "what's the bottleneck?", "what's the worker doing?", "show me progress" → run /project-status

Overview

This skill helps bring Lean 4 code up to mathlib standards by:

  1. Enforcing style rules (line length, formatting, indentation)
  2. Checking naming conventions
  3. Ensuring proper documentation
  4. Golfing proofs to be shorter and cleaner
  5. Preparing code for PR submission

Available Commands

CommandDescription
/developPlanning only, with binding methodical-decomposition pre-work. Phases 1a–1d: gather context, study references, search mathlib, design API. Phase 1e (binding pre-work): for each top-level result, write the prose proof, decompose into ordered lemmas, physically state every lemma as := by sorry in the project's Lean files (Step 2.5 — skeleton must lake build clean), then tension against the references with a verbatim source quote per leaf and a Lean ↔ source match paragraph (Step 3). Verify every leaf is discharged from mathlib (cited + verified) or already-developed project code — gaps become explicit API-gap sub-trees. Save decomposition.md. Only after every leaf is verified across (Lean declaration + verbatim quote + citation) does ticket creation (1g) proceed. Then ChatGPT validation (1h) and user approval (1i). Workers run via /beastmode. Flag --decompose runs ONLY Phase 1e and stops — for iterating on the skeleton / decomposition / source quotes before committing to a ticket board.
/beastmodeMarathon execution. Stops at nothing — but stays on-target. Pick a ticket, finish the goal no matter how deep the path goes. Spawn sub-tickets in /develop's template format; replan via /develop --continue when a sketch is wrong; no recursion cap, no time budget. Continuously checks on-target before each sub-ticket and step (serves the plan? stays in the project's mathematical area? a refinement not a divergence?). Welcomes scope growth that stays on target — a "two lemmas" step turning into ten is great news, not a stop signal. Super Saiyan ethos: the harder the work, the more energy goes in. Mandatory post-proof cleanup (Phase 6.5): after gates pass and before mark-done, invokes Skill(mathlib-quality:cleanup) on every new declaration — full 11-phase workflow, no phase-skipping (enforced via /cleanup's own phase checklist), including the 6.5 simplify and 6.6 buzz (performance) hand-offs; decompose flags spawn /decompose-proof sub-tickets, rename queue drained inside /cleanup's Phase 5b. Only stops: DONE / SCOPE-DEFINITION ERROR / OFF-TRACK (drift outside the project's mathematical scope, with concrete evidence) / BROKEN BASELINE. "This is multi-session work" is NOT a stop — it is the target signal. Beastmode exists to collapse multi-session work into one continuous run.
/cleanupStyle audit + cleanup + golf (whole file or single declaration). 11-phase methodical workflow: doctor (baseline build) → prepare → audit punch-list → file-level fixes → per-declaration deep golf with diff gates → refactoring (5a non-rename + 5b rename pass) → final gates + cumulative checks → built-in /simplify pass → /buzz performance pass → report. Absorbed: /check-style (Phase 2 audit), /check-mathlib (Phase 4 item 13 — five-method search + six strict rules + common-equivalents lookup), the inline mechanical pass of /generalise (Phase 4 item 18), and shouyi-style diff gates (Phase 4 + 6). Phase 6.5 hand-off to the built-in /simplify skill catches holistic issues the rule-driven pass missed; Phase 6.6 hand-off to /buzz gets every declaration under the elaboration budget (deferrals feed /decompose-proof).
/cleanup-allOrchestrator-worker pattern for project-wide cleanup. Main session is the orchestrator: enumerates files, buckets by size, dispatches batched Agent calls with a ~1200-char verbatim prompt (working dir + branch + build + file list + target), narrates progress in one-line scoreboards between dispatches. Workers do the file reading, LSP, edits, Phase-4 sub-worker dispatch, and build verification in fresh contexts. Orchestrator never reads/edits/builds. The pattern that sustained a 28-day, 9000-message marathon.
/decompose-proofBreak long proofs into helper lemmas
/buzzProfile → trace → fix slow declarations (target <1s each). One profiled compile per file → per-decl timing table → trace-driven diagnosis against the eight-cause taxonomy in references/profiling.md → measured fixes, with same-issue propagation across the remaining slow decls. Statements byte-identical; limit raises forbidden (existing maxHeartbeats removed); profiling scaffolding gate-checked out. PR mode by default; also <file>, <file> <decl>, --all, --budget <ms>. Runs automatically as /cleanup Phase 6.6.
/overviewProject survey + per-decl mathlibable assessment. Inventory + cross-file analyses (mathlib API audit, duplications, generalisation, missing API, junk) + **
阅读完整来源 ↗