- 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>
- ADR-002: Skill manifest format with JSON Schema, path bases, preconditions
- ADR-003: Versioning with Nix store paths, lockfiles, interface contracts
- ADR-004: Trace security with HMAC redaction, entropy detection, trace modes
Refined based on orch consensus feedback from GPT and Gemini.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove find fallbacks, error if expected spec/plan/tasks missing
- Add BLOCKER/SUGGESTION labels to critique prompts
- Add multi-device sync, service coordination to NFR checklist
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove 2>&1 from nix build capture. When repo is dirty, nix emits
warnings to stderr which were being merged into $out and used as
symlink targets, creating broken symlinks like:
orch -> warning: Git tree '...' is dirty\n/nix/store/...
Now stderr goes to terminal, only stdout (store path) captured.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- apiKeys: list of API key names (openai, google, anthropic, openrouter)
- mkDirenvStdlib: generates use_api_keys() bash function
- mkSopsSecrets: generates sops-nix secrets attribute set
Consumers (ops-dev, dotfiles) can now import from skills.lib
instead of maintaining duplicate key lists.
Adds Vale discovery, spin-off decision, migration details,
and updated session metrics to the design session worklog.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Code review found upstream STATIC_DATA.md was better quality despite
being 5 lines shorter. Added comprehensive session worklog.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Enables agents to query multiple AI models for:
- Second opinions on reasoning
- Architectural decisions
- Devil's advocate analysis
- Brainstorming and critique
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Includes:
- New 'web-search' skill
- New 'web-research' skill with multi-backend support (claude, llm, kagi)
- Automated deployment in bin/deploy-skill.sh
- Sops-nix integration for Kagi API key
- Documentation updates
Implement complete workflow for checking and applying OpenCode updates:
- check-version.sh: Compare current vs latest GitHub release
- fetch-sha256.sh: Fetch SHA256 hash using nix-prefetch-url
- update-nix-file.sh: Update Nix package definition with dry-run support
- verify-update.sh: Verify installed version matches expectation
Includes comprehensive documentation (SKILL.md for agents, README.md for users)
and full spec in specs/002-update-opencode/ with user stories and acceptance criteria.
Eliminates manual Nix file editing and hash lookups for OpenCode updates.
- Add Quick Start section with simple trigger phrase examples
- Add detailed 'How to Invoke This Skill' section explaining:
- Natural language trigger phrases
- Conversation-based card generation
- Detail specification (pages, depth, content preferences)
- What the agent understands and how it responds
Makes it clear to users they just need to ask naturally:
'Create a study card about [topic]' - no special commands needed.
