generate-find-bugs

Solid

Generates a project-specific /find-bugs skill with stack-specific security and correctness checklists. Run once per project. Usage: /generate-find-bugs

AI & Automation 30 stars 1 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 83/100

Stars 20%
50
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Skill: /generate-find-bugs # Generate Project-Specific /find-bugs Skill Detects the project's tech stack and appends language-specific security and correctness checklists to the generic `/find-bugs` skill. --- ## DISCOVERY STEPS ### Step 1 — Detect stack ```bash ls package.json go.mod requirements.txt Cargo.toml 2>/dev/null | head -5 ``` ### Step 2 — Read CLAUDE.md architecture section ```bash cat CLAUDE.md 2>/dev/null | head -80 ``` ### Step 3 — Find existing fragile areas ```bash grep -rn "TODO\|FIXME\|HACK\|unsafe" . \ --include="*.go" --include="*.ts" --include="*.tsx" \ --exclude-dir=node_modules --exclude-dir=.git \ 2>/dev/null | head -15 ``` --- ## OUTPUT Write to `.claude/skills/find-bugs/SKILL.md`. Keep Phases 1–5 and the output format intact. Add a **Stack-Specific Checklists** section after Phase 3, tailored to detected stack: **Go:** ```markdown ### Go Checklist - [ ] Goroutine leaks — all goroutines bounded by context or timeout? - [ ] Nil interface vs nil pointer — returning interface wrapping nil concrete? - [ ] Context propagation — request contexts passed to all blocking operations? - [ ] Mutex scope — mutex unlocked in the same scope it was locked? - [ ] SSE headers — WriteHeader called exactly once, before any body writes? - [ ] Request size limits — applied before decoding JSON from untrusted input? - [ ] Response body close — deferred after nil check? ``` **React/TypeScript:** ```markdown ### React / TypeScript Checklist - [ ] Stale...

Details

Author
valpere
Repository
valpere/session-indexer
Created
2 months ago
Last Updated
today
Language
Go
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category