interrogate
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
- License 许可
- MIT
- 最近更新
- 2026-10-24
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- interrogate
- description
- Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
- disable-model-invocation
- true
02 资源文件 4
- 参考文档references/code-quality-review.md5.1 KB
- 参考文档references/lead-judgment.md3.4 KB
- 参考文档references/reviewer-prompt.md2.2 KB
- 参考文档references/rubric.md4.7 KB
03 SKILL.md 正文
Interrogate
Spawn one reviewer per configured model to adversarially review code changes. The adversarial signal comes from model diversity, not assigned personas. The deliverable is a synthesized verdict. Do NOT auto-apply changes.
Step 1, Scope
Identify what to review from context:
- If the user points at specific files or a diff, use that.
- If on a feature branch, run
git diff main...HEAD(or the appropriate base branch) for the full changeset. - If the user's message references recent work, gather the relevant files.
Package the diff or file contents with any surrounding context files the reviewers need to understand the code.
Step 2, Intent
Before spawning reviewers, state the intent in one clear paragraph from the user's message, commit messages, the PR description if one exists, and the code. If you're unsure about the intent, ask the user before proceeding.
Step 3, Spawn Reviewers
Launch fresh pi_worker reviewers without waiting between launches. Use interrogate reviewers, one reviewer per configured entry, labeled Reviewer A, B, and so on. Otherwise use the table defaults. Retrieve every full report before synthesis.
| Subagent | Default model |
|---|---|
| Reviewer A | inherit-parent |
| Reviewer B | inherit-parent |
Each reviewer uses interrogate reviewers, its configured model, and tools read, grep, find, and ls, plus specifically required read-only research tools. Instruct it to inspect only and not modify files. Omit model for an auto or inherit-parent entry.
If an explicit model selector is unavailable, inspect bb provider models pi on the execution host and use only the recovery route permitted by model-routing. Do not select a family sibling or substitute an unrestricted worker. An auto or inherit-parent entry copies the resolved parent model and reasoning.
Read references/reviewer-prompt.md and fill in the same template for every reviewer with the stated intent, the diff or file contents, the rubric from references/rubric.md, and the code-quality lens from references/code-quality-review.md. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the poteto-mode skill.
Step 4, Synthesize
As results come back, build a unified picture. Parse every reviewer's findings. Merge findings that describe the same issue differently, and note which models raised each one. Findings two or more models raised independently are the highest signal. Read a lone model's finding, but weight it accordingly. Note disagreements. If one model flags something and another explicitly says the opposite, that is context for the verdict.
Step 5, Lead Judgment
You are the lead reviewer, a pragmatic senior engineer, not a neutral aggregator. Read references/lead-judgment.md for the full framework. Put every finding in one of four buckets, with the model(s) that raised it and a one-line rationale.
- Act on. Real issues affecting correctness, security, or maintainability given the actual goals. They would block a real PR.
- Consider. Legitimate, but you're not sure they outweigh the cost of addressing them now. Worth the user's attention.
- Noted. Technically valid but not actionable. Context-dependent, premature optimization, or low-impact at this stage.
- Dismissed. Wrong, nitpicky, or missing context, with a brief reason.
Output Format
Intent
[The stated intent paragraph from Step 2]
Reviewers
- Reviewer [label]: [model name], [N findings] (one bullet per reviewer)
Act On
[Each: description, which models raised it, why it matters.]
Consider
[Each: description, which models raised it, the tradeoff.]
Noted
[Brief list.]
Dismissed
[Each with a brief rationale.]
Agreement Map
[Where models agreed and diverged, and what that pattern tells us.]
04 同仓库更多 Skills
sidekick-browser
Use the pinned local AXI launcher for explicit, isolated browser verification in a Sidekick child.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
unslop
Cut AI tells from any writing.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /skill:technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
teach
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.