Structured, user-invoked standing prompts for long runs on any project: /design-scoreboard chooses what to climb and what must not get worse, /improve and /optimize climb it against the repo's AGENTS.md sections, and /trim-agents-md keeps that hub short. Each keeps state in files and reports what needs the owner first
Plugin improvement-loops from marketplace fb-claude-skills in fblissjr/fb-claude-skills. Commands read from the repo's manifest — 10 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
design-scoreboardDesigns what an improvement or optimizer loop should climb for a given project and goal, and what must not get worse while it does: goal metrics measured on the real path, guardrails, and counter-checks aimed at the cheapest way to fake each gain, so no single number can be reward-hacked. Proves eac
improveRuns one improvement pass over a project in the direction its north star points, without breaking what it does today: faster in real use, less code, a truer account of what it does, rules that now run as checks. Works with the repo's AGENTS.md sections (North star, Measurement, Reporting, Loop state
optimizeSpeeds up a codebase as far as it will go in one session, against a hard target (every primary benchmark at least 1.2x faster than the base commit by default) without regressing correctness, output quality or safety. Works with the repo's AGENTS.md sections (North star, Measurement, Loop state); bas
trim-agents-mdTightens a repository's always-loaded agent instructions (AGENTS.md, CLAUDE.md, unconditional rules): every line must prevent a mistake, and each one that doesn't is moved to the narrowest home that loads when it matters (a path-scoped rule, a skill, a hook or test, the status doc, the user-level fi
loop-graderGrades a finished improvement-loops run against its done list. Given the done list, the run record, the report and the project's north star, it returns only what is unmet and any change that pulls against the north star. Spawned once at the end of /improve and /optimize; reads files only.
loop-reviewerRead-only reviewer for an improvement-loops run. Given one lens, the base commit and its time, it returns at most five ranked ideas, each cited to a file and line; in review mode it checks a run's diff against its ledger. Spawned by /improve and /optimize, one per lens; not a general code reviewer.
python3
MECE decomposition for breaking work into mutually exclusive, collectively exhaustive parts. A skill you invoke when decomposing something -- it ships no SessionStart hook, because the method is needed at a decision point the model can recognise, not before the first action of every session.
5 skills · 1 MCP server
The audit family: evidence-grounded postmortems of finished work with a browsable index, a test-suite audit (does each green test still mean anything), a controls audit (census and live-fire over hooks, validators, and reminders), and the adversarial-verify primitive with its control-builder agent that the audits dispatch to
5 skills · 1 agent
Skills for how the agent writes and explains: an American plain-language house style, voice matching, replacing prose with compact visuals, and re-pitching a message that did not land
4 skills · 1 command
Hand a task to Gemini and get a structured answer back -- video and audio analysis, perceptual image comparison, or any ad-hoc question with model, thinking level, and schema set per call. Explicit, auditable, one run directory per call.
1 skill · 2 commands · hooks
On-demand references for what a repo cannot state by being read: the house Python pinning policy and the two mistakes behind most Pydantic/Pyright diagnostic walls; documentation conventions (last-updated dates, where unshared notes and session logs live, how dependency changes are recorded, no decorative counts in prose); and a uv and bun dependency CVE audit, transitives included. No hooks or ambient injection: conventions belong in each repo's own always-loaded files.
3 skills
Tools for analyzing, polishing, and managing Claude Code plugins
1 skill · 2 agents
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.