Slim shadow of mathlib-quality — same workflows, minimal instructions, trusts frontier-model judgement
Plugin mqslim from marketplace mqslim-plugins in CBirkbeck/MQSlim. Commands read from the repo's manifest — 1 month ago.
mqslimSlim shadow of the mathlib-quality plugin. Same workflows (cleanup, mathlib-fit assessment, proof decomposition, project development, marathon execution) but trusts frontier-model judgement instead of over-specifying. Use when working with `.lean` files, mathlib contributions, proof golfing, or code
/mqslim:bstmodeSlim shadow of mathlib-quality's /beastmode. Marathon work session — pick a ticket, finish the goal, stop at nothing. Spawn sub-tickets for missing infrastructure; replan via /devel --continue when the sketch is wrong; mandatory /clnup on every completed proof before mark-done. Trusts the model on t
/mqslim:clnupSlim shadow of mathlib-quality's /cleanup. Audit + golf + style + mathlib-replacement on a Lean file (or single declaration). Trusts the model to apply the conventions in skills/mqslim/SKILL.md and to use `lean_diagnostic_messages` / `lean_loogle` / `lean_leansearch` / `lean_local_search` for the au
/mqslim:decoproofSlim shadow of mathlib-quality's /decompose-proof. Break long Lean proofs (>50 lines) into focused helper lemmas. Two passes: analysis (identify candidates + write decomposition plans) → decompose (extract helpers, golf them, update the main proof). Five-item helper-hygiene curation per extracted he
/mqslim:develSlim shadow of mathlib-quality's /develop. Plan a mathematical development — search mathlib, design the API, decompose the proof from the source, write a ticket board. Planning-only; workers run via /bstmode. Source-faithful: every leaf must be discharged from a verbatim source quote OR an explicit
/mqslim:mthlblSlim shadow of mathlib-quality's /mathlibable. Decide whether a Lean declaration belongs in mathlib. Runs the exhaustive literature + mathlib + composition check, then produces one of five verdict buckets with evidence. Trusts the model to do the search work without per-row required-artifact tables.
AGNTCY/Outshift Internet-of-Cognition runtime integration — SLIM secure transport, CASA intent-scoped tool authorization, and AGNTCY identity/observability spans (ADR-380); optional, removable augmentation per ADR-150
1 skill
Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, simplify, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check command, and pre-commit hook. All stdlib-only.
1 skill · 1 command · 1 agent
Structured Lean 4 proof writing and library design following Mathlib conventions
1 skill
Audits or prunes agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong or guidance needs slimming. Not for application bugs or PR review.
1 skill · 3 agents
Quality gates for AI-assisted codebases. Provides refit onboarding, the swab/scour/buff/sail remediation loop, and barnacle friction reporting as a Claude skill and slash commands.
1 skill · 6 commands
MCP server for structural health analysis — 14 dimensions graded A-F, dependency cycles, coupling, dead code, test coverage, and quality gates
1 skill · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.