efficiency-audit
Skill0 starsChanged 4 months agoLicence not identifiedView on GitHub
Ruthlessly audit a codebase for its 1-3 most serious EFFICIENCY problems — the hot paths that dominate latency, cost, or resource use — then verify each with a concrete cost analysis (complexity, query count, allocation, growth path) and a fix. Use whenever the user invokes /efficiency-audit or asks to "find the performance bottlenecks", "why is this slow", "audit this for efficiency", "what's burning CPU/memory/money here", "find the N+1 queries", or wants a sharp, high-signal performance review that stops at the top few offenders rather than an exhaustive list. Spins up a small, capped multi-agent workflow of Sonnet agents to trace hot paths and prove cost. For security vulnerabilities use security-audit instead.
In this repository26 other files it gives its agents.
- add-ansible-roleSkill
- assign-mr-reviewersSkill
- audit-agent-diffSkill
- brief-agentSkill
- debug-lemonadeSkill
- diagnose-failureSkill
- independent-reviewSkill
- land-changeSkill
- match-ui-to-referenceSkill
- plan-experimentSkill
- port-changesSkill
- pre-commit-setupSkill
- react-ts-setupSkill
- release-setupSkill
- research-optionsSkill
- resolve-design-decisionsSkill
- rigsSkill
- run-experimentSkill
- rust-setupSkill
- sanity-check-numbersSkill
- security-auditSkill
- senior-frontend-refactorSkill
- uv-developSkill
- uv-setupSkill
- watchlistSkill
- write-evidence-reportSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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.