Agent skill
decision-archaeology
Investigate why code was written a certain way. Use when tracing decision history through git blame, commit logs, PRs, and issues to understand the reasoning behind code changes.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/decision-archaeology
SKILL.md
Decision Archaeology Skill
Rules
Read-only operations only.
For gh api: GET requests only. No -X POST/PUT/PATCH/DELETE or -f/-F flags.
Workflow
- Identify code - Target file, lines, or function
- Find commit -
git blame→ introducing commit - Trace PR/Issue - Check commit message for
#123references - Summarize rationale - Output findings
For detailed commands: See references/commands.md
Key Commands
git blame -L <start>,<end> <file> # Find who changed lines
git log -S "code" --oneline # Find when code was added
gh pr list --search "<sha>" --state all # Find PR for commit
Output Format
## Decision Archaeology Report
### Target
- File: [path/to/file]
- Lines: [XX-YY]
### Timeline
#### [Date] Commit: [short-sha]
- Author: [name]
- Message: [commit message]
- PR: #[number] [title]
- Related Issue: #[number]
### Decision Rationale
[Summary of why, based on PR discussions, issue context, commit messages]
### Key References
- PR #[number]: [URL]
- Issue #[number]: [URL]
- Commit: [sha]
Tips
- Start with
git blameto find introducing commit - Check commit message for
#123references - PR descriptions and review comments contain the "why"
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?