Skills for Real Engineers. Straight from my .agents directory.
debugging-patterns
Agent skill froma5c-ai/babysitter
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.
How to install debugging-patterns
npx skills add a5c-ai/babysitter# or add only this skill to Claude Code: copy the folder
library/methodologies/cc10x/skills/debugging-patterns/
# into
~/.claude/skills/debugging-patterns/ (all projects)
.claude/skills/debugging-patterns/ (one project)
1## Pattern-Based Diagnosis23- Check patterns.md for known gotchas matching the error4- Cross-reference with common patterns: null pointer, race condition, resource leak, config error5- Rate root cause confidence (>=80% to proceed with fix)67## Evidence Collection89- Stack traces with full call chain10- Error messages with context11- Exit codes from reproduction attempts12- Git blame/log for change correlation13- Environment differences (if applicable)1415## When to Use1617- During DEBUG workflow investigation phase18- When BUILD tests fail unexpectedly19- When reviewing error handling gaps2021## Agents Used2223- `bug-investigator` (primary consumer)24- `silent-failure-hunter` (pattern reference)
Excerpt shown under the repository's MIT license.
More skills in babysitter
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
