Agent skill
worklog
Add timestamped work log entries to track progress and decisions. Use for documenting work, decisions, gotchas, and handoffs between agents.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/worklog
SKILL.md
/worklog
Add structured JSON entries to track work, decisions, and learnings.
Usage
/worklog yourbench YB-2 "Added login button to header"
/worklog yourbench YB-2 --decision "Using Clerk for auth"
/worklog yourbench YB-2 --gotcha "Token refresh needs cleanup"
/worklog coordinatr 003 --handoff code-reviewer "Ready for review"
/worklog yourbench YB-2 --state # Show current state
/worklog yourbench YB-2 --migrate # Migrate from WORKLOG.md
Directory Structure
ideas/yourbench/issues/YB-2-auth/
├── TASK.md
├── PLAN.md
└── worklog/
├── _state.json # Current state (quick context load)
├── 001-phase-init.json # Entry files
└── 002-handoff-review.json
Entry Types
| Type | Flag | Use Case |
|---|---|---|
| Manual | (default) | General progress update |
| Decision | --decision |
Document architectural choice |
| Gotcha | --gotcha |
Capture lesson learned |
| Handoff | --handoff TO |
Agent transition |
| Phase | --phase NUM |
Phase completion |
| Blocker | --blocker |
Record impediment |
| Resolution | --resolve ID |
Resolve blocker |
Execution Flow
1. Parse Arguments
/worklog PROJECT ISSUE_ID [--type] "message"
2. Locate Worklog Directory
ideas/[project]/issues/[issue_id]-*/worklog/
mkdir -p [path] if missing
3. Get Next Sequence Number
ls worklog/*.json | grep -v _state | wc -l
# Next = count + 1
4. Create Entry File
Filename: {sequence:03d}-{type}-{slug}.json
Required fields:
$schema: "worklog-entry-v1"id: "ISSUE-SEQ"sequence: numbertimestamp: ISO 8601type: entry typeauthor: { agent: string | null, human: string | null }summary: description
5. Update _state.json
After every entry:
- Update
last_entry - Update
last_updated - Increment
entries_count - Add to
key_decisionsif decision - Update
blockersif blocker/resolution
Viewing State
/worklog yourbench YB-2 --state
Outputs:
Issue: YB-2 - Initialize Next.js project
Status: in_progress (Phase 3)
Progress: 5/5 phases complete
Key Decisions: ...
Blockers: none
Schema Reference
See references/schema.md for full JSON schema specification.
Best Practices
- Be specific: Include enough context for future AI
- Tag consistently: Use established tag taxonomy
- Capture gotchas immediately: Don't wait until end
- Handoff explicitly: Create handoff entry when switching agents
- Update state:
_state.jsonshould always reflect current reality
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?