dan/skills

dan fb15000877 refactor: restructure for cross-repo deployment

- Rename reviews/ to lenses/ (clearer terminology)
- Add workflows/ for beads proto templates
- Extract code-review proto to workflows/molecules.jsonl
- Update ai-skills.nix module:
  - Add enableLenses option (deploys to ~/.config/lenses/)
  - Add enableWorkflows option (deploys to ~/.beads/molecules.jsonl)
  - Derive repoRoot from skillsPath for sibling directories
- Update lens paths in proto to use deployed location

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2025-12-26 01:18:19 -05:00

1.4 KiB

Raw Blame History

Lenses

Focused prompts for multi-perspective code analysis.

Philosophy

Each lens examines code through one specific concern. Multiply lenses × models for diverse perspectives.

Usage

Single lens, multiple models:

orch consensus "$(cat ~/.config/lenses/bloat.md)" flash gemini gpt --file src/target.py

Pipe file content:

cat src/target.py | orch consensus "$(cat ~/.config/lenses/smells.md)" flash gemini

Convergent review (multiple passes):

for lens in bloat smells dead-code; do
  echo "=== $lens ==="
  orch chat "$(cat ~/.config/lenses/$lens.md)" --model gemini --file src/target.py
done

Available Lenses

Lens	Focus
`bloat.md`	File size, function length, complexity metrics
`smells.md`	Code smells, readability, naming issues
`dead-code.md`	Unused exports, zombie code, unreachable paths
`redundancy.md`	Duplicate systems, YAGNI, consolidation opportunities

Planned Lenses

coverage.md - Test gaps, untested critical paths
coupling.md - Tight coupling, leaky abstractions
security.md - OWASP, injection, auth
perf.md - Bottlenecks, N+1 queries
architecture.md - Boundaries, data flow, trade-offs

Output Convention

All lenses output findings in a consistent format:

[TAG] <severity:HIGH|MED|LOW> <file:line>
Issue: <description>
Suggest: <action>

This enables parsing and automated beads creation.

1.4 KiB Raw Blame History Unescape Escape