dan/skills
1
0
Fork 0
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity

bd daemon export: 2026-01-18 08:14:48

Browse source
This commit is contained in:
dan 2026-01-18 08:14:48 -08:00
parent de6d94f724
commit d19ae873d5
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.beads/issues.jsonl
View file

@ -218,7 +218,7 @@
{"id":"skills-n6zf","title":"Add error handling for heartbeat thread startup","description":"[ERROR] MED heartbeat.nim:41,70-80 - No error handling for thread startup. openBusDb can fail (crashes thread silently), createThread could fail. Add try/except in thread body, return success indicator.","status":"closed","priority":2,"issue_type":"bug","created_at":"2026-01-10T19:54:44.891259041-08:00","created_by":"dan","updated_at":"2026-01-10T20:24:43.776180211-08:00","closed_at":"2026-01-10T20:24:43.776180211-08:00","close_reason":"Fixed: added try/except for openBusDb in heartbeatWorker thread"}
{"id":"skills-n8ck","title":"HQ: Revised core loop (SYNC-TRIAGE-REVIEW-UNBLOCK-DISPATCH)","description":"**Raised by:** gemini\n\n**Problem:**\nCurrent core loop is too passive. Doesn't prioritize merging approved work or detecting stalled workers proactively.\n\n**gemini:**\n\u003e \"The current loop is too passive. It should be:\n\u003e 1. SYNC: Refresh state from git/bd (detect stalled workers)\n\u003e 2. TRIAGE: Merge 'APPROVED' work immediately (reduce conflict windows)\n\u003e 3. REVIEW: Check 'IN_REVIEW' work (prioritize passing tests)\n\u003e 4. UNBLOCK: Provide feedback to 'STUCK' workers\n\u003e 5. DISPATCH: Spawn new work only if capacity allows\"\n\n**Current loop:**\n1. ASSESS → 2. PLAN → 3. DELEGATE → 4. MONITOR → 5. ITERATE → 6. COMPLETE\n\n**Key differences:**\n- SYNC first (detect stale)\n- TRIAGE prioritizes merging to reduce conflict window\n- DISPATCH is last, gated by capacity\n- More action-oriented verbs\n\n**Action:** Evaluate and potentially update the core loop in SKILL.md","status":"open","priority":3,"issue_type":"task","created_at":"2026-01-12T09:24:10.618287351-08:00","created_by":"dan","updated_at":"2026-01-12T09:24:10.618287351-08:00"}
{"id":"skills-njb","title":"worklog: clarify or remove semantic compression references","description":"SKILL.md references 'semantic compression is a planned workflow' multiple times but it's not implemented. Speculative generality - adds cognitive load for non-existent feature. Either implement or move to design notes. Found by smells lens review.","status":"closed","priority":4,"issue_type":"task","created_at":"2025-12-25T02:03:25.387405002-05:00","updated_at":"2025-12-27T10:11:48.169923742-05:00","closed_at":"2025-12-27T10:11:48.169923742-05:00","close_reason":"Closed"}
{"id":"skills-npwv","title":"Design a spec-driven planning/tasks framework","description":"# Goal\n\nDesign a lightweight spec-driven planning framework for AI coding workflows. Steal the best ideas from existing tools and create a simpler, more pragmatic version.\n\n## Research Summary\n\n### GitHub Spec-Kit\n- **4-phase approach**: Specify → Plan → Tasks → Implement\n- Specifications as \"single source of truth\"\n- constitution.md for non-negotiable project principles\n- Slash commands: /specify, /plan, /tasks\n- Gated phases with checkpoints\n- 40k+ GitHub stars since Aug 2025\n\n### Amazon Kiro\n- Two modes: \"vibe mode\" (quick prototype) vs \"spec mode\" (structured)\n- Specs generate: user stories → technical design → implementation tasks\n- Agent Hooks: event-driven automations (on save, create, delete)\n- Steering files for project-specific agent behavior\n- Solves \"unmaintainable vibe code\" problem\n\n### AGENTS.md Standard\n- Linux Foundation stewardship, 60k+ OSS projects\n- Hierarchical: subproject AGENTS.md overrides parent\n- Supported by: Codex, Cursor, Gemini, VSCode, etc.\n- Complements README with agent-specific context\n- Can symlink to tool-specific files (CLAUDE.md, .cursorrules)\n\n### RFCs/ADRs (Traditional)\n- RFC = Request for Comments (collecting feedback)\n- ADR = Architecture Decision Record (documenting decisions)\n- Natural flow: RFC → accepted → multiple ADRs\n- Lightweight templates for small scope, heavyweight for org-wide\n- Companies: Uber, Spotify, Airbnb all use variants\n\n### MetaGPT\n- Role-based: PM, Architect, Engineer, QA\n- SOPs (Standard Operating Procedures) encoded\n- Requirements → Architecture → Code → Tests\n\n## Key Ideas to Borrow\n\n1. **Phase gates** - Don't jump to code without a plan\n2. **Specs as prompts** - Well-crafted specs = better AI output\n3. **Task decomposition** - Small, testable, reviewable units\n4. **Constitution/rules** - Non-negotiable project constraints\n5. **Human checkpoints** - Iterate on specs before coding\n6. **Hierarchical context** - Project-level + subproject-level rules\n\n## Design Questions\n\n- How lightweight can we make this while retaining value?\n- Integration with existing beads workflow?\n- File format: markdown? YAML frontmatter?\n- Where do specs live? `.specs/`? `docs/specs/`?\n- How to track spec → task → implementation lineage?\n- Balance between structure and flexibility?\n\n## References\n\n- https://github.com/github/spec-kit\n- https://kiro.dev/\n- https://agents.md\n- https://newsletter.pragmaticengineer.com/p/rfcs-and-design-docs\n- https://github.com/joelparkerhenderson/architecture-decision-record","status":"open","priority":2,"issue_type":"feature","owner":"dan@delpad","created_at":"2026-01-18T08:01:47.79963934-08:00","created_by":"dan","updated_at":"2026-01-18T08:01:47.79963934-08:00"}
{"id":"skills-npwv","title":"Design a spec-driven planning/tasks framework","description":"# Goal\n\nDesign a lightweight spec-driven planning framework for AI coding workflows. Steal the best ideas from existing tools and create a simpler, more pragmatic version.\n\n## Research Summary\n\n### GitHub Spec-Kit\n- **4-phase approach**: Specify → Plan → Tasks → Implement\n- Specifications as \"single source of truth\"\n- constitution.md for non-negotiable project principles\n- Slash commands: /specify, /plan, /tasks\n- Gated phases with checkpoints\n- 40k+ GitHub stars since Aug 2025\n\n### Amazon Kiro\n- Two modes: \"vibe mode\" (quick prototype) vs \"spec mode\" (structured)\n- Specs generate: user stories → technical design → implementation tasks\n- Agent Hooks: event-driven automations (on save, create, delete)\n- Steering files for project-specific agent behavior\n- Solves \"unmaintainable vibe code\" problem\n\n### AGENTS.md Standard\n- Linux Foundation stewardship, 60k+ OSS projects\n- Hierarchical: subproject AGENTS.md overrides parent\n- Supported by: Codex, Cursor, Gemini, VSCode, etc.\n- Complements README with agent-specific context\n- Can symlink to tool-specific files (CLAUDE.md, .cursorrules)\n\n### RFCs/ADRs (Traditional)\n- RFC = Request for Comments (collecting feedback)\n- ADR = Architecture Decision Record (documenting decisions)\n- Natural flow: RFC → accepted → multiple ADRs\n- Lightweight templates for small scope, heavyweight for org-wide\n- Companies: Uber, Spotify, Airbnb all use variants\n\n### MetaGPT\n- Role-based: PM, Architect, Engineer, QA\n- SOPs (Standard Operating Procedures) encoded\n- Requirements → Architecture → Code → Tests\n\n## Key Ideas to Borrow\n\n1. **Phase gates** - Don't jump to code without a plan\n2. **Specs as prompts** - Well-crafted specs = better AI output\n3. **Task decomposition** - Small, testable, reviewable units\n4. **Constitution/rules** - Non-negotiable project constraints\n5. **Human checkpoints** - Iterate on specs before coding\n6. **Hierarchical context** - Project-level + subproject-level rules\n\n## Design Questions\n\n- How lightweight can we make this while retaining value?\n- Integration with existing beads workflow?\n- File format: markdown? YAML frontmatter?\n- Where do specs live? `.specs/`? `docs/specs/`?\n- How to track spec → task → implementation lineage?\n- Balance between structure and flexibility?\n\n## References\n\n- https://github.com/github/spec-kit\n- https://kiro.dev/\n- https://agents.md\n- https://newsletter.pragmaticengineer.com/p/rfcs-and-design-docs\n- https://github.com/joelparkerhenderson/architecture-decision-record","status":"closed","priority":2,"issue_type":"feature","owner":"dan@delpad","created_at":"2026-01-18T08:01:47.79963934-08:00","created_by":"dan","updated_at":"2026-01-18T08:14:48.101639457-08:00","closed_at":"2026-01-18T08:14:48.101639457-08:00","close_reason":"Research complete, epic created: skills-oh8m"}
{"id":"skills-nscx","title":"Build 'spec tasks' command (beads integration)","description":"CLI command to create beads issues from spec tasks.\n\n## Usage\n```bash\nspec tasks spec-001 # Create beads from tasks\nspec tasks spec-001 --dry-run # Show what would be created\nspec tasks spec-001 --link # Also update spec with bead IDs\n```\n\n## Behavior\n- Parse Tasks section from spec\n- Create bead issue for each unchecked task\n- Link issues back to spec\n- Set up dependencies if specified\n\n## Implementation\n- Parse markdown checkboxes\n- Call bd create for each\n- Update spec frontmatter with bead IDs","status":"open","priority":2,"issue_type":"task","owner":"dan@delpad","created_at":"2026-01-18T08:13:58.499816272-08:00","created_by":"dan","updated_at":"2026-01-18T08:13:58.499816272-08:00","dependencies":[{"issue_id":"skills-nscx","depends_on_id":"skills-oh8m","type":"blocks","created_at":"2026-01-18T08:14:32.68566829-08:00","created_by":"dan"},{"issue_id":"skills-nscx","depends_on_id":"skills-4ecn","type":"blocks","created_at":"2026-01-18T08:14:45.031399725-08:00","created_by":"dan"}]}
{"id":"skills-nto","title":"Prototype: End-to-end cross-agent workflow","description":"Build a working prototype of cross-agent quality gate.\n\n## Scenario\n1. Worker agent (any) does task\n2. Posts status to message layer\n3. Reviewer agent (any) checks work\n4. Posts approval/issues to memory layer\n5. Gate checks memory, allows/blocks completion\n\n## Test Matrix\n\n| Orchestrator | Worker | Reviewer | Enforcement |\n|--------------|--------|----------|-------------|\n| Claude | Claude | Gemini | Hook |\n| Claude | Gemini | Claude | Hook |\n| OpenCode | Claude | Gemini | Orchestrator |\n| Manual | OpenCode | Claude | Protocol |\n\n## Components to Build\n1. Message layer interface (post/read status)\n2. Memory layer interface (review state)\n3. Gate check CLI (for hooks and manual)\n4. Reviewer skill/prompt\n\n## Success Criteria\n- At least 2 agent combinations working\n- Gate actually blocks when review fails\n- State persists across agent boundaries","status":"closed","priority":2,"issue_type":"task","created_at":"2026-01-09T19:32:57.579195169-08:00","created_by":"dan","updated_at":"2026-01-09T20:39:24.013666826-08:00","closed_at":"2026-01-09T20:39:24.013666826-08:00","close_reason":"Prototype complete: review-gate CLI with hooks.json, adversarial reviewer prompt, and dual-publish structure"}
{"id":"skills-oes","title":"Define skill manifest format","description":"Skills need to declare their interface so beads can validate.\n\nManifest should include:\n- Required inputs (args, env vars)\n- Optional inputs with defaults\n- Expected outputs (files, artifacts)\n- Preconditions (tools, repos, permissions)\n\nLocation: SKILL.md frontmatter or separate manifest.yaml\n\nEnables: Proto validation before spawning, better error messages.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-23T19:49:30.673372413-05:00","updated_at":"2025-12-23T20:55:04.427620449-05:00","closed_at":"2025-12-23T20:55:04.427620449-05:00","close_reason":"ADRs revised with orch consensus feedback"}