菜单
Tracked iteration cycles for reducing failures. Number iterations sequentially, record state before/after, commit atomically per fix. Use when iteratively reducing test failures, fixing bugs in cycles, or any work requiring tracked progress across multiple attempts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Multi-hypothesis research campaign protocol. Use for open-ended optimization goals ("make X faster", "improve the metric") where several candidate ideas compete for a limited budget. Triages ideas cheaply, confirms survivors with full preregistered experiments, and keeps a committed ledger so dead ideas stay dead.
Controlled benchmark experiment protocol for solver, performance, routing, and optimization work. Use when testing a hypothesis against metrics, comparing implementations, or deciding whether to promote or abandon a benchmark-driven change.
Coordination-only protocol. You dispatch subagents, you do not execute code. Restricts tools to Read, Write (prompts/ and notes- only), Agent, Glob, Grep. Use when orchestrating multi-agent work.
Four-role sequential pipeline for complex, high-risk changes. Scout surveys the codebase, Coder implements with TDD, Analyst finds problems, Verifier gates the merge. Use for large refactors, architectural shifts, and interdependent multi-phase work.
Background knowledge for writing and launching subagent prompts. Covers prompt file conventions, worker identity declarations, batch dispatch patterns, and parallel swarm safety. Auto-invocable when dispatching agents.
Deletion-first fixed-point protocol for refactors, cleanup, migrations, and architectural convergence. Use when replacing old surfaces, removing helper debt, shrinking code, moving ownership boundaries, or auditing every symbol in a slice.
| name | iterations |
| description | Tracked iteration cycles for reducing failures. Number iterations sequentially, record state before/after, commit atomically per fix. Use when iteratively reducing test failures, fixing bugs in cycles, or any work requiring tracked progress across multiple attempts. |
| disable-model-invocation | false |
Use when: iteratively reducing failures, fixing bugs in cycles, any work requiring tracked progress across multiple attempts.
reports/
iteration-log.md # Running summary
iterations/
001/
start.json # State at iteration start
end.json # State at iteration end
analysis.md # What was attempted
clusters/ # If working on multiple fixes
cluster-a/
fix.md
verification.json
Number iterations sequentially: 001, 002, etc.
Critical rule: If failures increase from previous iteration, STOP and diagnose before proceeding.
start.jsonanalysis.mdend.jsoniteration-log.md{
"timestamp": "ISO8601",
"total": 100,
"pass": 85,
"fail": 15,
"skip": 0
}
# Iteration Log
## 001 - [date]
- Start: 15 failures
- Targets: [list]
- Result: 12 failures (-3)
- Commits: [hashes]
## 002 - [date]
- Start: 12 failures
- Targets: [list]
- Result: 14 failures (+2) WARNING REGRESSION
- Action: Reverted, investigating...
One atomic commit per fix, immediately after verification passes.
fix(<component>): iteration {N} - <brief description>
Fixes: <what was wrong>
Tests: <what now passes>