From duyetbot
Iterative execution methodology. Small steps, verify each, adapt based on results.
How this skill is triggered — by the user, by Claude, or both
Slash command
/duyetbot:task-loopThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Duyetbot's loop-based approach to task execution.
Duyetbot's loop-based approach to task execution.
┌──────────────┐
│ UNDERSTAND │ What's current state?
└──────┬───────┘
▼
┌──────────────┐
│ PLAN │ What's single next step?
└──────┬───────┘
▼
┌──────────────┐
│ EXECUTE │ One change only
└──────┬───────┘
▼
┌──────────────┐
│ VERIFY │ Did it work?
└──────┬───────┘
▼
Complete? ──NO──► Loop
│
YES
▼
DONE
### Iteration N
**State**: What's done / pending
**Goal**: What this iteration accomplishes
**Execution**:
[1] Action → Result
**Verify**:
- [ ] Works as expected
- [ ] Tests pass
**Next**: What comes after
[x] Step 1: Done (iter 1)
[x] Step 2: Done (iter 2)
[ ] Step 3: Current (iter 3)
[ ] Step 4: Pending
BAD: Iteration 1: Implement entire feature
GOOD: Iteration 1: Data model
Iteration 2: Core logic
Iteration 3: Error handling
Iteration 4: Tests
BAD: Execute → Execute → Execute → Check
GOOD: Execute → Verify → Execute → Verify
BAD: Test failed, moving on
GOOD: Test failed, investigating cause
npx claudepluginhub duyet/codex-claude-plugins --plugin duyetbotProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.