[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78EB06AND4RMBM4PWBHS95T":3,"skill-same:01M78EB06AND4RMBM4PWBHS95T":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":46},"01M78EB06AND4RMBM4PWBHS95T","interrogate",null,"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.","mikeyobrien\u002Fpi-tidy-tools","mikeyobrien","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F11792047?v=4","01M78EA4XJ7CY5SB8V7EPB1581","Mikey O'Brien","01M78EA4YD4ECB9199H176CNQY",63,"MIT","https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finterrogate\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: interrogate\ndescription: \"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.\"\ndisable-model-invocation: true\n---\n\n# Interrogate\n\nSpawn one reviewer per configured model to adversarially review code changes. Each model gets the same prompt and rubric. The adversarial signal comes from model diversity, not assigned personas.\n\nThe deliverable is a synthesized verdict. Do NOT auto-apply changes.\n\n## Step 1, Determine Scope\n\nIdentify what to review from context:\n\n- If the user points at specific files or a diff, use that\n- If on a feature branch, run `git diff main...HEAD` (or the appropriate base branch) for the full changeset\n- If the user's message references recent work, gather the relevant files\n\nPackage the diff (or file contents) plus any surrounding context files the reviewers need to understand the code.\n\n## Step 2, State the Intent\n\nBefore spawning reviewers, state the intent explicitly. Derive this from:\n\n- The user's message\n- Commit messages\n- PR description if one exists\n- The code itself\n\nWrite one clear paragraph. If you're unsure about the intent, ask the user before proceeding.\n\n## Step 3, Spawn Reviewers\n\nLaunch all reviewers in a single message using the Task tool.\n\n**Other harnesses.** The spawns in this skill use Cursor's `Task` tool. In another harness, use its subagent tool: `Agent` in Claude Code (`subagent_type: general-purpose`), `task` in OpenCode (`subagent_type: general`), `spawn_agent` in Codex. Keep the prompt and the model. Drop parameters your tool doesn't have. If your harness has no subagent tool, as in Pi without an extension, run each reviewer yourself, one after another.\n\nUse the `interrogate reviewers` list from the pstack settings file when present (`~\u002F.cursor\u002Frules\u002Fpstack-models.mdc` in Cursor, `~\u002F.agents\u002Fpstack-models.md` in other harnesses), one reviewer per entry, extending or shrinking the Reviewer A\u002FB\u002FC\u002FD labels below to the configured entry count. Otherwise use the table defaults.\n\n| Subagent | Default model |\n|----------|---------------|\n| Reviewer A | `claude-fable-5-1-thinking-max` |\n| Reviewer B | `gpt-5.6-sol-max` |\n| Reviewer C | `grok-4.6-fast-xhigh` |\n| Reviewer D | `claude-opus-5-thinking-xhigh` |\n\nFor each reviewer:\n- `subagent_type`: `generalPurpose`\n- `model`: the configured `interrogate reviewers` entry, or the table default with no configured line\n- `readonly`: `true`\n\nIf a model slug is rejected as unresolvable when you try to spawn the subagent, check the valid slugs in the subagent tool's error message or your harness's model list, pick the closest equivalent (prefer the highest-reasoning tier of the same family), spawn with the valid slug, and open a separate PR to update the configured value or default table. Do not block the review on the slug issue. If the configured value is `inherit-parent` or `auto`, omit `model` instead. Never treat those aliases as broken slugs or enter this fallback for them.\n\nRead `references\u002Freviewer-prompt.md` and fill in the template with:\n1. The stated intent\n2. The diff or file contents\n3. The review rubric from `references\u002Frubric.md`\n4. The code-quality lens from `references\u002Fcode-quality-review.md`\n\nThe same filled template goes to all reviewers, so every model applies the code-quality lens.\n\n## Step 4, Synthesize\n\nAs results come back, build a unified picture:\n\n1. **Parse all findings** from the reviewers\n2. **Identify consensus**. Findings raised by 2+ models independently are highest signal.\n3. **Identify lone-model findings**. Still worth reading, but weight accordingly.\n4. **Deduplicate**. Different models may describe the same issue differently. Merge these and note which models raised it.\n5. **Note disagreements**. If one model flags something and another explicitly says the opposite, that's useful context for the verdict.\n\n## Step 5, Lead Judgment\n\nYou are the lead reviewer, a pragmatic senior engineer, not a neutral aggregator.\n\nRead `references\u002Flead-judgment.md` for the full framework.\n\nCategorize every finding using these buckets:\n\n- **Act on**. Real issues affecting correctness, security, or maintainability given the actual goals. These would block a real PR.\n- **Consider**. Legitimate points, but you're not sure they outweigh the cost of addressing them right now. Worth the user's attention.\n- **Noted**. Technically valid but not actionable. Context-dependent, premature optimization, or low-impact given the current stage.\n- **Dismissed**. Wrong, nitpicky, or missing context. Brief explanation why.\n\nFor each finding, include:\n- Which model(s) raised it\n- The category (act on \u002F consider \u002F noted \u002F dismissed)\n- A one-line rationale for the categorization\n\n## Output Format\n\nPresent the verdict in this structure:\n\n### Intent\n> [The stated intent paragraph from Step 2]\n\n### Reviewers\n- Reviewer [label]: [model name], [N findings] (one bullet per reviewer)\n\n### Act On\n[Findings that should be addressed. For each: description, which models raised it, why it matters.]\n\n### Consider\n[Findings worth thinking about. For each: description, which models raised it, tradeoff involved.]\n\n### Noted\n[Valid but low-priority. Brief list.]\n\n### Dismissed\n[Rejected findings with brief rationale.]\n\n### Agreement Map\n[Where did models agree, where did they diverge, and what does the pattern of agreement\u002Fdisagreement tell us?]\n","# Interrogate\n\nSpawn one reviewer per configured model to adversarially review code changes. Each model gets the same prompt and rubric. The adversarial signal comes from model diversity, not assigned personas.\n\nThe deliverable is a synthesized verdict. Do NOT auto-apply changes.\n\n## Step 1, Determine Scope\n\nIdentify what to review from context:\n\n- If the user points at specific files or a diff, use that\n- If on a feature branch, run `git diff main...HEAD` (or the appropriate base branch) for the full changeset\n- If the user's message references recent work, gather the relevant files\n\nPackage the diff (or file contents) plus any surrounding context files the reviewers need to understand the code.\n\n## Step 2, State the Intent\n\nBefore spawning reviewers, state the intent explicitly. Derive this from:\n\n- The user's message\n- Commit messages\n- PR description if one exists\n- The code itself\n\nWrite one clear paragraph. If you're unsure about the intent, ask the user before proceeding.\n\n## Step 3, Spawn Reviewers\n\nLaunch all reviewers in a single message using the Task tool.\n\n**Other harnesses.** The spawns in this skill use Cursor's `Task` tool. In another harness, use its subagent tool: `Agent` in Claude Code (`subagent_type: general-purpose`), `task` in OpenCode (`subagent_type: general`), `spawn_agent` in Codex. Keep the prompt and the model. Drop parameters your tool doesn't have. If your harness has no subagent tool, as in Pi without an extension, run each reviewer yourself, one after another.\n\nUse the `interrogate reviewers` list from the pstack settings file when present (`~\u002F.cursor\u002Frules\u002Fpstack-models.mdc` in Cursor, `~\u002F.agents\u002Fpstack-models.md` in other harnesses), one reviewer per entry, extending or shrinking the Reviewer A\u002FB\u002FC\u002FD labels below to the configured entry count. Otherwise use the table defaults.\n\n| Subagent | Default model |\n|----------|---------------|\n| Reviewer A | `claude-fable-5-1-thinking-max` |\n| Reviewer B | `gpt-5.6-sol-max` |\n| Reviewer C | `grok-4.6-fast-xhigh` |\n| Reviewer D | `claude-opus-5-thinking-xhigh` |\n\nFor each reviewer:\n- `subagent_type`: `generalPurpose`\n- `model`: the configured `interrogate reviewers` entry, or the table default with no configured line\n- `readonly`: `true`\n\nIf a model slug is rejected as unresolvable when you try to spawn the subagent, check the valid slugs in the subagent tool's error message or your harness's model list, pick the closest equivalent (prefer the highest-reasoning tier of the same family), spawn with the valid slug, and open a separate PR to update the configured value or default table. Do not block the review on the slug issue. If the configured value is `inherit-parent` or `auto`, omit `model` instead. Never treat those aliases as broken slugs or enter this fallback for them.\n\nRead `references\u002Freviewer-prompt.md` and fill in the template with:\n1. The stated intent\n2. The diff or file contents\n3. The review rubric from `references\u002Frubric.md`\n4. The code-quality lens from `references\u002Fcode-quality-review.md`\n\nThe same filled template goes to all reviewers, so every model applies the code-quality lens.\n\n## Step 4, Synthesize\n\nAs results come back, build a unified picture:\n\n1. **Parse all findings** from the reviewers\n2. **Identify consensus**. Findings raised by 2+ models independently are highest signal.\n3. **Identify lone-model findings**. Still worth reading, but weight accordingly.\n4. **Deduplicate**. Different models may describe the same issue differently. Merge these and note which models raised it.\n5. **Note disagreements**. If one model flags something and another explicitly says the opposite, that's useful context for the verdict.\n\n## Step 5, Lead Judgment\n\nYou are the lead reviewer, a pragmatic senior engineer, not a neutral aggregator.\n\nRead `references\u002Flead-judgment.md` for the full framework.\n\nCategorize every finding using these buckets:\n\n- **Act on**. Real issues affecting correctness, security, or maintainability given the actual goals. These would block a real PR.\n- **Consider**. Legitimate points, but you're not sure they outweigh the cost of addressing them right now. Worth the user's attention.\n- **Noted**. Technically valid but not actionable. Context-dependent, premature optimization, or low-impact given the current stage.\n- **Dismissed**. Wrong, nitpicky, or missing context. Brief explanation why.\n\nFor each finding, include:\n- Which model(s) raised it\n- The category (act on \u002F consider \u002F noted \u002F dismissed)\n- A one-line rationale for the categorization\n\n## Output Format\n\nPresent the verdict in this structure:\n\n### Intent\n> [The stated intent paragraph from Step 2]\n\n### Reviewers\n- Reviewer [label]: [model name], [N findings] (one bullet per reviewer)\n\n### Act On\n[Findings that should be addressed. For each: description, which models raised it, why it matters.]\n\n### Consider\n[Findings worth thinking about. For each: description, which models raised it, tradeoff involved.]\n\n### Noted\n[Valid but low-priority. Brief list.]\n\n### Dismissed\n[Rejected findings with brief rationale.]\n\n### Agreement Map\n[Where did models agree, where did they diverge, and what does the pattern of agreement\u002Fdisagreement tell us?]\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","b253d1504091e48e3d60ebab19535bf0d1cec363",".claude\u002Fskills\u002Finterrogate",3,"https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools","https:\u002F\u002Fgithub.com\u002Fmikeyobrien","mobrienv.dev","Sr. SDE @ Amazon. Austin, TX. AI Enthusiast. \r\n","2026-10-13 08:29:57",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":24},[36,39,42],{"tool":37,"command":38},"npx","npx skills add mikeyobrien\u002Fpi-tidy-tools --skill interrogate",{"tool":40,"command":41},"bunx","bunx skills add mikeyobrien\u002Fpi-tidy-tools --skill interrogate",{"tool":43,"command":44},"pnpm","pnpm dlx skills add mikeyobrien\u002Fpi-tidy-tools --skill interrogate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finterrogate\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcode-quality-review.md","REFERENCE","参考文档",5372,"https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finterrogate\u002Freferences\u002Fcode-quality-review.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Flead-judgment.md",3465,"https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finterrogate\u002Freferences\u002Flead-judgment.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Freviewer-prompt.md",2756,"https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finterrogate\u002Freferences\u002Freviewer-prompt.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frubric.md",5096,"https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finterrogate\u002Freferences\u002Frubric.md",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M78EEXKEADXTNBVN3096T211","pi-tidy-bots-cli","Drive the pi-tidy-bots fleet runtime from an agent — init, daemonized start, status, stop, hot bot onboarding, and the HTTP+WS machine API (messages, transcripts, compaction, question cards) — all non-interactive with checked exit codes and --json shapes.","https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002Fskills\u002Fpi-tidy-bots-cli\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M78EES9YE4WYNC6NJZNZD628","qa-loop","Run a human-gated QA and repair loop for pi-tidy-tools.","https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fqa-loop\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M78EEP74RPPZYAZYEJRJ2DXK","pi-tidy-tools-ethos","Narrative guardrails for @mobrienv\u002Fpi-tidy-tools. Use when designing, implementing, reviewing, or documenting non-release changes to that package.","https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fpi-tidy-tools-ethos\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M78EEJAAK2GZ2FXR8PT6SPSY","npm-release","Releases one @mobrienv\u002Fpi-tidy-* workspace through GitHub and npm Trusted Publishing. Use when asked to prepare changelog entries, cut, publish, or monitor a patch, minor, major, or explicit-version release.","https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fnpm-release\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M78EEEWYRACQEPDPC039DEK0","build-loop","Build and independently verify one ready implementation ticket through a human-gated repair loop.","https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fbuild-loop\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M78EEA9XNRCCR1SKEFSPXPTC","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.","https:\u002F\u002Fgithub.com\u002Fmikeyobrien\u002Fpi-tidy-tools\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwhy\u002FSKILL.md",[],[]]