From kimchi
Iteratively refines development plans by scoring completeness, clarity, testability, independence, and task size; improves lowest areas until quality threshold, diminishing returns, or max loops. Kimchi pipeline stage producing PLAN-DRAFT.md.
How this skill is triggered — by the user, by Claude, or both
Slash command
/kimchi:refineThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<command_purpose>
<command_purpose> Iteratively evaluate and improve the plan until quality is sufficient. Exits on: quality threshold reached, diminishing returns, regression, or max loops. </command_purpose>
Read .kimchi/PLAN-REVIEWED.md (preferred) or .kimchi/PLAN.md (if review was skipped).
Parse $ARGUMENTS for --loops N option (default: 3).
Score the plan on 5 criteria (each 0-20, total 100):
| Criterion | Score 20 | Score 10 | Score 0 |
|---|---|---|---|
| Completeness | All v1 requirements covered | Most covered | Gaps exist |
| Clarity | Every task unambiguous | Minor ambiguity | Vague descriptions |
| Testability | Each task has verifiable criteria | Some criteria vague | Missing criteria |
| Independence | Parallel where possible | Unnecessary dependencies | Serial when could be parallel |
| Size | All tasks S or M | One L task | Multiple L tasks |
for each iteration (up to max_loops):
1. Score the plan
2. Check exit conditions:
- Score >= 90 → exit "quality_reached"
- Score improvement < 5 from last → exit "diminishing_returns"
- Score decreased → revert, exit "regression"
- Max loops reached → exit "max_loops"
3. Identify lowest-scoring criterion
4. Apply targeted improvement:
- Completeness: Add missing tasks for uncovered requirements
- Clarity: Rewrite ambiguous task descriptions
- Testability: Add/improve acceptance criteria
- Independence: Break unnecessary dependencies
- Size: Split L tasks into S/M tasks
5. Record what changed
Write .kimchi/PLAN-DRAFT.md:
# Draft Plan: [Feature Name]
**Refined:** [today's date]
**Source:** .kimchi/PLAN-REVIEWED.md
## Refinement History
| Iteration | Score | Lowest Criterion | Changes Made | Exit Reason |
|-----------|-------|-----------------|--------------|-------------|
| 1 | [N]/100 | [criterion] | [what changed] | - |
| 2 | [N]/100 | [criterion] | [what changed] | - |
| 3 | [N]/100 | - | - | [exit reason] |
## Draft Plan
[Complete refined plan with all improvements applied]
Report: "Refinement complete (exit: [reason], score: [N]/100). Saved to .kimchi/PLAN-DRAFT.md"
Suggest: "Run /kimchi:plan-revise for cross-model analysis, or /kimchi:beads to convert directly."
npx claudepluginhub tromml/kimchi --plugin kimchiOrchestrates parallel architecture and experience reviews of implementation plans, scores findings across dimensions like data flow and UX, consolidates ranked fixes for user approval and auto-application. Use after planning, before non-trivial coding.
Runs a Claude↔Codex convergence loop: Codex reviews a plan, Claude applies fixes, repeats until ALLOW or max-iter. For auto-reviewed plan refinement without manual copypaste.
Refines an existing Strikethroo plan by resolving the plan ID, running project hooks, pressure-testing for gaps and contradictions, and updating the plan in-place.