interrogate
Use for "interrogate", "adversarial review", "independent 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
- 所属仓库
- am-will/gooey-pi
- 最近更新
- 2026-10-25
- Stars
- ★ 974
- Forks
- 87
01 前言 Front Matter
- name
- interrogate
- description
- Use for "interrogate", "adversarial review", "independent 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.md5.2 KB
- 参考文档references/lead-judgment.md3.4 KB
- 参考文档references/reviewer-prompt.md2.7 KB
- 参考文档references/rubric.md5.0 KB
03 SKILL.md 正文
Interrogate
Spawn independent reviewers with different review focus: correctness, security boundaries, failure recovery, and maintainability. Each inherits the current session model. Compare concrete evidence and counterexamples; agreement alone does not establish correctness.
The deliverable is a synthesized verdict. Do NOT auto-apply changes.
Step 1, Determine 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) plus any surrounding context files the reviewers need to understand the code.
Step 2, State the Intent
Before spawning reviewers, state the intent explicitly. What is this code trying to accomplish? Derive this from:
- The user's message
- Commit messages
- PR description if one exists
- The code itself
Write one clear paragraph. Reviewers challenge whether the work achieves the intent well, not whether the intent itself is correct. If you're unsure about the intent, ask the user before proceeding.
Step 3, Spawn Reviewers
Launch a task-appropriate panel of independent reviewers in a single message, normally two to four. Assign each a distinct focus while preserving the shared intent and rubric. Omit model so each reviewer inherits the current session; override only when the human explicitly chooses a model for this invocation. Do not discover or substitute another model to fill the panel.
| Reviewer | Primary focus |
|---|---|
| A | Correctness and state transitions |
| B | Security and authorization boundaries |
| C | Concurrency, failure recovery, and performance |
| D | Maintainability, API contracts, and test gaps |
For each reviewer use subagent_type: generalPurpose and readonly: true where those tool options are available.
Read references/reviewer-prompt.md and fill in the template with:
- The stated intent
- The diff or file contents
- The review rubric from
references/rubric.md - The code-quality lens from
references/code-quality-review.md
The same filled template goes to all reviewers, so every reviewer applies the code-quality lens.
Each reviewer produces structured findings as described in the prompt template.
Step 4, Synthesize
As results come back, build a unified picture:
- Parse all findings from the reviewers
- Identify consensus. Findings raised by two or more reviewers independently are highest signal.
- Identify single-reviewer findings. Still worth reading, but weight accordingly.
- Deduplicate. Different reviewers may describe the same issue differently. Merge these and note which reviewers raised it.
- Note disagreements. If one reviewer flags something and another explicitly says the opposite, that's useful 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. Reviewers only see a slice of the codebase. You have the full context (the goal, the constraints, the timeline, which tradeoffs were already considered). Use that context aggressively.
Categorize every finding using these buckets:
- Act on. Real issues affecting correctness, security, or maintainability given the actual goals. These would block a real PR.
- Consider. Legitimate points, but you're not sure they outweigh the cost of addressing them right now. Worth the user's attention.
- Noted. Technically valid but not actionable. Context-dependent, premature optimization, or low-impact given the current stage.
- Dismissed. Wrong, nitpicky, or missing context. Brief explanation why.
For each finding, include:
- Which reviewer(s) raised it
- The category (act on / consider / noted / dismissed)
- A one-line rationale for the categorization
Output Format
Present the verdict in this structure:
Intent
[The stated intent paragraph from Step 2]
Reviewers
- Reviewer [label]: [review focus], [N findings] (one bullet per reviewer)
Act On
[Findings that should be addressed. For each: description, which reviewers raised it, why it matters.]
Consider
[Findings worth thinking about. For each: description, which reviewers raised it, tradeoff involved.]
Noted
[Valid but low-priority. Brief list.]
Dismissed
[Rejected findings with brief rationale. This shows the user what was filtered out and why, so they can override your judgment if they disagree.]
Agreement Map
[Where did models agree, where did they diverge, and what does the pattern of agreement/disagreement tell us?]
04 同仓库更多 Skills
prime-work-schedules
Create, inspect, edit, pause, resume, run, and delete durable GooeyPi scheduled tasks. Use when the user asks to schedule recurring or one-time work in the current project or thread. Use rlm-heartbeat instead for temporary internal polling while actively working.
prime-work-browser
Drive the GooeyPi in-app browser for this thread with the browser_* tools - open tabs, navigate, read pages, click, type, scroll, screenshot, and extract data. Use when the user asks to open, test, inspect, or interact with a website or a local dev server inside GooeyPi.
gooeypi-computer-use
Drive native applications on macOS, Windows, or Linux through the separately installed TryCUA driver CLI.
verify-gooeypi
Launch and drive the GooeyPi desktop (Electron) app to prove user-facing behavior — sidebar navigation, Settings, and Capabilities — capturing screenshots and ARIA snapshots. Reach for this when verifying a GooeyPi UI change or confirming the app still works end to end.
review-pr-viability
Review a pull request or issue for value, implementation quality, maintainability, regression risk, and reliance on upstream changes.
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.