suggest
Skill893 starsChanged yesterdayBSD-3-ClauseView on GitHub
Review the codebase and suggest improvements, without making edits. Use when asked for a review, an audit, or ideas for what to improve.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- HurricaHjz/SecondSelftheir own version, first seen Nov 15, 2026
- HurricaHjz/second-yourselftheir own version, first seen Nov 15, 2026
- intelligentcode-ai/skillstheir own version, first seen Nov 15, 2026
- mkrz/skillstheir own version, first seen Nov 15, 2026
- blinkboxhq/Blinkboxtheir own version, first seen Nov 8, 2026
- belt-sh/skillstheir own version, first seen Sep 27, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- brave/brave-search-skills★ 182same name
- HurricaHjz/second-yourself★ 150same name
- HurricaHjz/SecondSelf★ 150same name
- sergeeey/Claude-cod-top-2026★ 9same name
- blinkboxhq/Blinkbox★ 4same name
- belt-sh/skills★ 2same name
- mkrz/skills★ 2same name
- intelligentcode-ai/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
If the user provided additional context with the prompt, treat it as a focus area (e.g.
- Distinctive: line 13
Read AGENTS.md to understand the project structure.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Find concrete improvements and flag things worth tracking for future work. Respect the existing style; don't over-engineer. Report findings only — do not make edits. The user will choose which suggestions to implement.
If the user provided additional context with the prompt, treat it as a focus area (e.g. "focus on TypeScript types", "performance only").
Steps
- Read
AGENTS.mdto understand the project structure. - Survey the codebase, paying particular attention to:
- Package/dependency manifests (
package.json, etc.) - Compiler/type-checker config (
tsconfig.json, etc.) - Runtime/bundler config (
bunfig.toml, etc.) - Build and tooling scripts
README— how the project presents itself
- Package/dependency manifests (
Categories to evaluate
Skip categories where things look fine. Don't invent problems.
Correctness / Bugs — wrong config values, broken scripts, typos in user-facing output
Code Quality — outdated practices, duplicated logic, unnecessary indirection, misleading comments, obvious simplifications
Performance — unnecessary looping, extra copies, redundant calls, known slow browser APIs
TypeScript (if used) — imprecise types, overuse of any/unknown, untyped third-party modules, irrelevant tsconfig.json options
Testing — coverage gaps, tests that don't actually verify what they claim
Runtime / tooling (Bun-specific entries apply if used) — node:* APIs where Bun-native equivalents exist, npm/yarn artifacts in scripts, dependencies Bun now handles natively
Data / Schema — data/ category files that drift from the JSON schemas in schema/, validation gaps in the build scripts, config/ files that disagree with each other
Developer Experience — missing or misleading package.json scripts, incomplete .gitignore/.gitattributes, missing docs or source comments
Architecture / Technical Debt — signs that complexity is accumulating: growing god-objects, framework or library choices that are becoming a liability, inconsistent patterns across similar code, coupling that makes changes harder than they should be, conventions the project has outgrown
How to respond
Group findings by category. Number each suggestion sequentially across all categories (1, 2, 3…) so the user can refer to them by number. For each finding:
- 🔥 Actionable issue (bug, broken) — should be fixed soon
- 👉 Improvement (best practice, clarity) — worth doing
- 💡 Suggestion (optional, bigger change) — idea to track for future work
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.

