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

bd sync: 2026-01-10 15:08:58

Browse source
This commit is contained in:
dan 2026-01-10 15:08:58 -08:00
parent 83b126719d
commit bc4f2e85cf
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

@ -122,7 +122,7 @@
{"id":"skills-lzk","title":"Simplify branch name generation in create-new-feature.sh","description":"File: .specify/scripts/bash/create-new-feature.sh (lines 137-181)\n\nIssues:\n- 3 nested loops/conditionals\n- Complex string transformations with multiple sed operations\n- Stop-words list and filtering logic hard to maintain\n\nFix:\n- Extract to separate function\n- Simplify word filtering logic\n- Add input validation\n\nSeverity: MEDIUM","status":"closed","priority":3,"issue_type":"task","created_at":"2025-12-24T02:51:14.286951249-05:00","updated_at":"2026-01-03T12:13:27.083639201-08:00","closed_at":"2026-01-03T12:13:27.083639201-08:00","close_reason":"Simplifed generate_branch_name logic, added main() function, and BASH_SOURCE guard for testability."}
{"id":"skills-m21","title":"Apply niri-window-capture code review recommendations","description":"CODE-REVIEW-niri-window-capture.md identifies action items: add dependency checks to scripts, improve error handling for niri failures, add screenshot directory validation, implement rate limiting. See High/Medium priority sections.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-11-30T11:58:24.648846875-08:00","updated_at":"2025-12-28T20:16:53.914141949-05:00","closed_at":"2025-12-28T20:16:53.914141949-05:00","close_reason":"Implemented all 4 high-priority recommendations from code review: dependency checks, directory validation, error handling, audit logging"}
{"id":"skills-mjf","title":"Design: Portable adversarial reviewer","description":"Design a reviewer agent/skill that can run on any capable model.\n\nalice is Claude Opus with specific tools. We need:\n- Model-agnostic reviewer prompt/instructions\n- Tool requirements (read-only: Read, Grep, Glob, Bash)\n- Integration with orch for multi-model consensus\n- Decision format (APPROVED/ISSUES)\n- Issue filing (beads or tissue)\n\nKey principles from alice:\n- Work for the USER, not the agent\n- Assume errors exist, find them\n- Steel-man then attack\n- Seek second opinions\n\nOutput: Reviewer skill spec that works across agents","status":"closed","priority":3,"issue_type":"task","created_at":"2026-01-09T17:14:20.778647076-08:00","created_by":"dan","updated_at":"2026-01-09T19:59:37.80146821-08:00","closed_at":"2026-01-09T19:59:37.80146821-08:00","close_reason":"Covered in architecture design doc - adversarial reviewer section"}
{"id":"skills-ms5","title":"Design: Local message passing layer","description":"Local message passing layer with phased complexity growth.\n\n## Principle\nStart simple, grow as needed. Any agent that can read/write files can participate.\n\n## Phase 1: Simple JSONL (Now)\n.worker-state/messages/*.jsonl\n\nFormat:\n{\"ts\": \"...\", \"from\": \"worker-auth\", \"type\": \"done\", \"data\": {...}}\n\nOperations:\n- Write: echo '{...}' \u003e\u003e messages/worker-auth.jsonl\n- Read: cat messages/*.jsonl | jq -s 'sort_by(.ts)'\n- Watch: tail -f messages/*.jsonl\n\nGood enough for prototype. No dependencies.\n\n## Phase 2: JWZ-like Features (When Needed)\nAdd when conversations get complex or files get large:\n- Threading (parent message linking)\n- SQLite cache for fast queries\n- Git context (commit, branch, dirty)\n- Rich identity (sender, model, role)\n\nConsider adopting JWZ directly or building compatible format.\n\n## Phase 3: Talu or Service Layer (Future)\nWhen we need:\n- Rich querying across projects\n- Persistence beyond filesystem\n- Graph relationships between messages\n- Real service layer\n\nTalu (~/proj/talu) is graph-based PKM that could model:\n- Agents as nodes\n- Messages as edges\n- Tasks with relationships\n\n## Research Sources\n- JWZ (emes): JSONL + SQLite, topic-based, git context\n- Gastown: Git worktrees as mailboxes (overcomplicated)\n- OpenHands: Git branches for coordination","design":"docs/design/message-passing-layer.md","notes":"Design complete. Compared against Beads and Tissue - see docs/design/message-passing-comparison.md. Key differences: We add heartbeats (they don't), flock locking (Tissue trusts git), staging for crash safety (Beads uses SQLite txn), blob storage (Beads uses compaction). Learned: consider hash-based IDs, file hash validation, FTS5 in Phase 2.","status":"open","priority":2,"issue_type":"task","created_at":"2026-01-10T13:24:21.597509853-08:00","created_by":"dan","updated_at":"2026-01-10T15:00:41.839430491-08:00","dependencies":[{"issue_id":"skills-ms5","depends_on_id":"skills-s6y","type":"blocks","created_at":"2026-01-10T13:24:36.033492407-08:00","created_by":"dan"}]}
{"id":"skills-ms5","title":"Design: Local message passing layer","description":"Local message passing layer with phased complexity growth.\n\n## Principle\nStart simple, grow as needed. Any agent that can read/write files can participate.\n\n## Phase 1: Simple JSONL (Now)\n.worker-state/messages/*.jsonl\n\nFormat:\n{\"ts\": \"...\", \"from\": \"worker-auth\", \"type\": \"done\", \"data\": {...}}\n\nOperations:\n- Write: echo '{...}' \u003e\u003e messages/worker-auth.jsonl\n- Read: cat messages/*.jsonl | jq -s 'sort_by(.ts)'\n- Watch: tail -f messages/*.jsonl\n\nGood enough for prototype. No dependencies.\n\n## Phase 2: JWZ-like Features (When Needed)\nAdd when conversations get complex or files get large:\n- Threading (parent message linking)\n- SQLite cache for fast queries\n- Git context (commit, branch, dirty)\n- Rich identity (sender, model, role)\n\nConsider adopting JWZ directly or building compatible format.\n\n## Phase 3: Talu or Service Layer (Future)\nWhen we need:\n- Rich querying across projects\n- Persistence beyond filesystem\n- Graph relationships between messages\n- Real service layer\n\nTalu (~/proj/talu) is graph-based PKM that could model:\n- Agents as nodes\n- Messages as edges\n- Tasks with relationships\n\n## Research Sources\n- JWZ (emes): JSONL + SQLite, topic-based, git context\n- Gastown: Git worktrees as mailboxes (overcomplicated)\n- OpenHands: Git branches for coordination","design":"docs/design/message-passing-layer.md","notes":"DESIGN UPDATED v2: SQLite as primary storage (not JSONL+flock). After orch consensus (3 models unanimous), aligned with Beads approach. Key change: SQLite with BEGIN IMMEDIATE for atomic writes, WAL mode for concurrency. JSONL becomes read-only export for debugging. See docs/design/message-passing-layer.md and message-passing-comparison.md.","status":"open","priority":2,"issue_type":"task","created_at":"2026-01-10T13:24:21.597509853-08:00","created_by":"dan","updated_at":"2026-01-10T15:08:53.648694891-08:00","dependencies":[{"issue_id":"skills-ms5","depends_on_id":"skills-s6y","type":"blocks","created_at":"2026-01-10T13:24:36.033492407-08:00","created_by":"dan"}]}
{"id":"skills-mx3","title":"spec-review: Define consensus thresholds and decision rules","description":"'Use judgment' for mixed results leads to inconsistent decisions.\n\nDefine:\n- What constitutes consensus (2/3? unanimous?)\n- How to handle NEUTRAL votes\n- Tie-break rules\n- When human override is acceptable and how to document it","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-15T00:23:24.121175736-08:00","updated_at":"2025-12-15T13:58:04.339283238-08:00","closed_at":"2025-12-15T13:58:04.339283238-08:00"}
{"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-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"}