networkidle times out on heavy sites like nytimes.com.
domcontentloaded + wait parameter is more reliable.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- visit.py CLI with subcommands: screenshot, text, html, pdf
- Uses system chromium on NixOS (no browser download)
- Fresh profile each run (no cookies/history)
- flake.nix provides playwright devShell
- Options: --wait, --full-page
Useful for JS-heavy sites where WebFetch fails.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Current simpler approach working well:
- Skills as standalone entrypoints
- Agent judgment sufficient for invocation
- Molecules not actively used
Revisit when complex orchestration is needed.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Human-facing documentation with:
- Prerequisites and installation
- Usage examples
- Backend options (web-research)
- Cross-references between related skills
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Context changed - Claude Code now has built-in WebSearch/WebFetch.
Decisions:
- Keep two separate skills (web-search, web-research)
- web-search: OpenCode only (Claude Code has native search)
- web-research: Both (deep research beyond built-in capability)
- Source filtering via WebSearch allowed_domains, not skill feature
- Summaries by default, not raw links
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace verbose 2-skill list with table of all skills.
Shows deployed (5), available (8), and development (1) skills.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Built-in agents: Build (full access) and Plan (read-only)
- Custom agents support prompts, model overrides, tool control
- Skills are global, agents access via skill() tool
- Permission control per-agent via opencode.json
- OpenCode supports Claude-compatible skill paths
Closes skills-czz
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add dependency checks for niri, jq, logger at script startup
- Validate and create screenshot directory if missing
- Improve error handling for niri command failures
- Add audit logging to capture-all-windows.sh
- Use variable for screenshot directory path
- Cache window list query in capture-all-windows.sh
Addresses recommendations from code review (skills-m21)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 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>
