Skills for Real Engineers. Straight from my .agents directory.
chisle-review
Agent skill fromJayPokale/Chisle
Review a diff or file through the Chisle lens: flag over-engineering, speculative abstractions, reinvented stdlib, and verbose code that a lazier approach would shrink. One finding per line, no praise. Use when the user says "chisle review", "review this for bloat", or invokes /chisle-review.
How to install chisle-review
npx skills add JayPokale/Chisle# or add only this skill to Claude Code: copy the folder
skills/chisle-review/
# into
~/.claude/skills/chisle-review/ (all projects)
.claude/skills/chisle-review/ (one project)
1# Chisle review23Review the diff/file for **what could be deleted or simplified**, not for style nits.45## What to flag67- Abstraction with one implementation (interface/factory/wrapper for a single case)8- Reinvented stdlib (hand-rolled debounce, deep-clone, groupBy, date math)9- New dependency for what a few lines or an installed dep already does10- Config/option that never varies11- Speculative "for later" scaffolding with no current caller12- Verbose code where a native platform feature (CSS, DB constraint, `<input type>`) does it1314## What NOT to flag1516- Input validation at trust boundaries17- Error handling that prevents data loss18- Security / accessibility code19- Anything the task explicitly required2021## Output format2223One finding per line. No preamble, no praise.2425```26path:line: <what's over-built>. <the lazier replacement>.27```2829Example:3031```32cache.js:12: ApiCacheManager class for one call site. Replace with lru_cache / a Map.33search.js:40: hand-rolled debounce util. setTimeout+clearTimeout inline is enough.34```3536End with a one-line verdict: `N findings. Est. <X> lines removable.`
Excerpt shown under the repository's MIT license.
More skills in Chisle
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
