Commit graph

31 commits

Author SHA1 Message Date
dan e366343dd7 docs: worklog for wayland desktop automation session 2025-12-17 14:32:20 -08:00
dan 906f2bc7ee beads: add seeing problem benchmark tasks
- skills-ebl: vision model UI understanding benchmark
- skills-bww: AT-SPI overhead/coverage benchmark
- Updated skills-kg7 epic with hybrid approach
2025-12-17 14:13:51 -08:00
dan 0b971558a5 beads: add AT-SPI findings (skills-pdg) 2025-12-17 14:00:10 -08:00
dan 19e0750693 beads: close skills-d87 2025-12-16 18:46:30 -08:00
dan 45067b07c8 fix(orch): update docs for globally installed CLI
orch is now installed via home-manager, no longer needs to be
run from source directory with uv run.
2025-12-16 18:45:19 -08:00
dan 0349d48ef2 fix(spec-review): fail fast on missing files, add severity labels
- 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>
2025-12-15 14:08:27 -08:00
dan 437265b916 feat: add spec-review skill and ai-tools-doctor docs
spec-review: Multi-model review of spec-kit artifacts using orch
- SKILL.md with progressive disclosure pattern
- Review processes: spec, plan, tasks, gate-check
- Prompts for critique, review, and go/no-go decisions

ai-tools-doctor: RFC and implementation report for diagnostics skill

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

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2025-12-15 00:43:52 -08:00
dan 90e72f1095 fix(use-skills): prevent stderr from corrupting symlink targets
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>
2025-12-14 12:42:26 -08:00
dan 67f6d69cc7 feat: add apiKeys lib for direnv/sops single source of truth
- 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.
2025-12-04 20:45:48 -08:00
dan def212bc5b docs: complete worklog for doc-review design session
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>
2025-12-04 17:54:05 -08:00
dan 139a521a89 doc-review: design session complete, spun off to ~/proj/doc-review
- Added use_api_keys to .envrc for orch access
- Worklog documents full design process
- Beads closed: skills-bcu, skills-1ig, skills-53k, skills-d6r
- Architecture: Vale + LLM hybrid (deterministic + semantic)
- Implementation continues in dedicated repo
2025-12-04 16:44:49 -08:00
dan 148f219887 chore: replace STATIC_DATA.md with upstream, add session worklog
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>
2025-12-03 20:43:51 -08:00
dan 8902a4f4a6 fix(bd-issue-tracking): replace condensed files with full upstream
WebFetch returned summarized content, not raw markdown.
Replaced 7/8 files with actual upstream versions:

- SKILL.md: 644 lines (was 122)
- CLI_REFERENCE.md: 559 lines (was 158)
- BOUNDARIES.md: 469 lines (was 82)
- DEPENDENCIES.md: 747 lines (was 141)
- WORKFLOWS.md: 548 lines (was 178)
- ISSUE_CREATION.md: 139 lines (was 104)
- RESUMABILITY.md: 207 lines (was 171)
- STATIC_DATA.md: kept ours (59 vs 54)

Source: github.com/steveyegge/beads/examples/claude-code-skill

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-03 20:19:56 -08:00
dan a74d0a2f26 bd sync: 2025-12-03 20:10:26 2025-12-03 20:11:27 -08:00
dan 7e7fdee292 feat: add bd-issue-tracking skill
Based on upstream beads Claude Code skill with adaptations:
- YAML frontmatter for skill system
- Temporal layering guidance (TodoWrite + bd)
- Reference docs: CLI, dependencies, workflows, boundaries

Source: https://github.com/steveyegge/beads/tree/main/examples/claude-code-skill

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-03 20:08:32 -08:00
dan 54a51ecdea refactor(orch): replace Anthropic models with Qwen/DeepSeek
- Remove claude/sonnet/opus/haiku aliases
- Add qwen (qwen3-8b), deepseek (v3), r1 (deepseek-r1)
- Add Model Selection guidance section
- Update GPT aliases to gpt-5.1, flash to preview version

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-01 19:08:32 -08:00
dan 24679f6cd6 bd sync: 2025-12-01 18:28:15 2025-12-01 18:28:15 -08:00
dan 0f010d3924 feat(orch): add multi-model consensus skill
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>
2025-11-30 15:48:31 -08:00
dan 35a357eb9d feat: add separate skill lists per target (claudeCodeSkills, openCodeSkills) 2025-11-30 15:16:30 -08:00
dan ec5386cf57 refactor(use-skills): simplify execution flow
- Add set -euo pipefail for safer defaults
- Remove conditional directory logic - always create both
- Remove undocumented SKILLS_CLAUDE/SKILLS_OPENCODE env vars
- Add fail-fast error handling throughout
- Capture nix build stderr for better error messages

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-30 15:00:46 -08:00
dan e921fd96df feat: add per-repo skill deployment pattern
- Add bin/use-skills.sh helper with use_skill and load_skills_from_manifest
- Add .skills manifest pattern for declarative skill configuration
- Fix ai-skills.nix: remove broken npm plugin code, update skill list
- Add update-opencode, web-search, web-research to flake.nix availableSkills
- Add RFC and documentation for team adoption

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-30 14:47:02 -08:00
dan 0e098ba0bb bd sync: 2025-11-30 14:43:53 2025-11-30 14:43:53 -08:00
dan 26a6469604 feat: add web-research skill and automate deployment
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
2025-11-23 23:18:32 -08:00
dan 99187460b1 feat(update-opencode): add skill for automating OpenCode version updates in Nix
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.
2025-11-15 13:35:58 -08:00
dan 9e544cd03a docs(worklog): final update with all commits 2025-11-10 15:09:13 -08:00
dan 8414ca773c docs(tufte-press): add clear invocation instructions for users
- 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.
2025-11-10 15:08:58 -08:00
dan 819ec78b33 docs(worklog): update with guardrails commit 2025-11-10 15:06:17 -08:00
dan df02264c3f docs(tufte-press): add guardrails and self-check rubric to agent instructions
- Add guardrails for under-specified requests (scaffold with clarifications)
- Add self-check rubric for content quality validation
- Ensures agent validates accuracy, clarity, annotation utility, balance, and print suitability
- Matches tufte-press project's latest LLM authoring prompt

These sections guide the agent to produce high-quality educational content
and handle unclear requests gracefully by asking for clarification.
2025-11-10 15:05:54 -08:00
dan ec8dba8097 docs(worklog): update commit count for tufte-press evolution session 2025-11-10 15:03:57 -08:00
dan 5fea49b7c0 feat(tufte-press): evolve skill to complete workflow with JSON generation and build automation
- Transform tufte-press from reference guide to conversation-aware generator
- Add JSON generation from conversation context following strict schema
- Create build automation scripts with Nix environment handling
- Integrate CUPS printing with duplex support
- Add comprehensive workflow documentation

Scripts added:
- skills/tufte-press/scripts/generate-and-build.sh (242 lines)
- skills/tufte-press/scripts/build-card.sh (23 lines)

Documentation:
- Updated SKILL.md with complete workflow instructions (370 lines)
- Updated README.md with usage examples (340 lines)
- Created SKILL-DEVELOPMENT-STRATEGY-tufte-press.md (450 lines)
- Added worklog: 2025-11-10-tufte-press-skill-evolution.org

Features:
- Agent generates valid JSON from conversation
- Schema validation before build (catches errors early)
- Automatic Nix shell entry for dependencies
- PDF build via tufte-press toolchain
- Optional print with duplex support
- Self-contained margin notes enforced
- Complete end-to-end testing

Workflow: Conversation → JSON → Validate → Build → Print

Related: niri-window-capture, screenshot-latest, worklog skills
2025-11-10 15:03:44 -08:00
dan d8c2e92f0a Initial commit: Agentic coding skills repository
- Add comprehensive documentation (README, WORKFLOW, DEPLOYMENT)
- Add skill template for creating new skills
- Port worklog skill from dotfiles (org-mode session documentation)
- Port update-spec-kit skill from dotfiles (ecosystem updates)
- Include spec-kit framework for structured development
- Add OpenCode commands for spec-kit workflow integration

Repository provides unified skill development for both Claude Code and OpenCode agents.
2025-11-08 10:55:15 -08:00