菜单
Use when an iteration has just finished and you need to verify behavior evidence quality in three tiers — deep evidence for current stories, impacted behavior for touched scenarios, and sentinel corpus for high-value regression detection.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/prime-radiant-inc/iterative-development --skill auditing-progress命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Use when executing a batch of TDD-sized tasks inside a running-an-iteration call — dispatches an implementer subagent per task following red-green-refactor discipline and returns per-task completion status.
Use when executing the next pending iteration from an iterative-development roadmap — picks the iteration, decomposes into code and evidence tasks, runs sentinel corpus baseline, dispatches implementing-tasks, runs impacted + sentinel scenarios, and updates artifacts.
Use when implementing a project with a large, comprehensive, or ambiguous spec — extracts requirements with proof obligations, defines a walking skeleton with its first journey scenario, then loops through audited sprints that continuously build a behavior evidence corpus. Completion means passing evidence, not just finished stories.
基于 SOC 职业分类
| name | auditing-progress |
| description | Use when an iteration has just finished and you need to verify behavior evidence quality in three tiers — deep evidence for current stories, impacted behavior for touched scenarios, and sentinel corpus for high-value regression detection. |
Runs after every iteration as part of the planning cycle. Verifies behavior evidence quality in three tiers using parallel adversarial review (PAR) — two paired auditor subagents evaluate the same work in parallel with competitive framing.
The audit answers: "Does durable, reusable evidence exist at the correct seam for every externally observable behavior this iteration touched?"
Invoked by iterative-development after every running-an-iteration call, before picking the next iteration.
Read the per-epic requirement files in docs/superpowers/iterations/requirements/, docs/superpowers/iterations/behavior-scenarios.md, and docs/superpowers/iterations/behavior-corpus.md:
done:ITER-<current> and scenarios added or updated in this iteration. Audit every AC and its proof obligation thoroughly.sentinel in the behavior corpus. Compare against the pre-iteration baseline from running-an-iteration step 3.Following the PAR methodology in :
skills/shared/parallel-adversarial-review.mdauditor-subagent-prompt.md. Include ALL THREE tiers:
skills/shared/par-reviewer-wrapper.mdFollowing PAR aggregation rules:
requirements/ (status pending) or flip existing stories back from done to pendingroadmap.md to add a follow-up iteration for the gapsReturn the audit result (clean or gaps) to the orchestrator. The orchestrator decides whether to loop or terminate.
| Tier | What it checks | Failure means |
|---|---|---|
| Deep evidence | Every AC + proof obligation for current iteration | Story not done, evidence too weak |
| Impacted behavior | Scenarios whose surfaces were touched | Stale or broken scenario |
| Sentinel corpus | High-value journey scenarios | Regression in previously-working behavior |
| Reads | Writes | Dispatches |
|---|---|---|
requirements/, behavior-scenarios.md, behavior-corpus.md, product code/tests | requirements/ (gaps), roadmap.md (new iteration) if gaps, behavior-scenarios.md (stale flags) | Two auditor subagents in parallel (PAR) |
skills/shared/parallel-adversarial-review.md — PAR methodologyskills/shared/par-reviewer-wrapper.md — competitive framing wrapperskills/shared/behavior-evidence-formats.md — scenario and proof obligation formatsauditor-subagent-prompt.md — auditor-specific prompt template