[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71EM4874ZW8G6H6XNGR3SW8":3,"skill-same:01M71EM4874ZW8G6H6XNGR3SW8":80},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":14,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M71EM4874ZW8G6H6XNGR3SW8","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.","patinaproject\u002Fskills","patinaproject","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F229996889?v=4","01M71E58JKTDNY1138WYZK44TR","Patina Project","01M71E58K5GH4K16MV6A8BQ6NZ",1,"MIT","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Finterrogate\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"stress test","adversarial","changes","for","multi","stress","spots","multi-model","use","review","challenge","find","model","code","adversarial review","test","2026-11-10 10:12:30",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.\"\n---\n\n# Interrogate\n\nOn Codex, read the [platform mapping](..\u002Fpatina-mode\u002Freferences\u002Fcodex-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, read the [platform mapping](..\u002Fpatina-mode\u002Freferences\u002Fcopilot-tools.md), including its per-skill notes, before following this skill.\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 `Agent` tool. Use the `interrogate reviewers` line in the `pstack-models.md` override sheet (`\u002Fsetup-pstack` lists its path per runtime), one reviewer per entry, extending or shrinking the Reviewer labels below to the configured entry count. If the sheet or that line is missing, use the table defaults.\n\n| Subagent | Default model |\n|----------|---------------|\n| Reviewer A | `opus` |\n| Reviewer B | `fable` |\n| Reviewer C | `sonnet` |\n| Reviewer D | `haiku` |\n\nFor each reviewer:\n\n- `subagent_type`: `patina-reader`\n- `model`: the configured `interrogate reviewers` entry, or the table default with no configured line. For an `auto` or `inherit-parent` entry, omit `model` so that reviewer runs on the parent model.\n- `readonly`: `true`\n\nIf the `Agent` tool rejects a configured entry, run that reviewer on the table default of its family and say so. Families go by model name, such as Opus, Fable, or Sonnet. With no family match, use Reviewer A's default. If it rejects a table default, check the valid slugs in the `Agent` tool's error message, pick the closest equivalent (prefer the same family and reasoning tier), spawn with it, and open a separate PR to update the default table. Do not block the review on the slug issue. Never treat an alias entry as a rejected slug or apply either fallback to it.\n\nRead `references\u002Freviewer-prompt.md` and fill in the template with:\n\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\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>\n> [The stated intent paragraph from Step 2]\n\n### Reviewers\n\n- Reviewer [label]: [model name], [N findings] (one bullet per reviewer)\n\n### Act On\n\n[Findings that should be addressed. For each: description, which models raised it, why it matters.]\n\n### Consider\n\n[Findings worth thinking about. For each: description, which models raised it, tradeoff involved.]\n\n### Noted\n\n[Valid but low-priority. Brief list.]\n\n### Dismissed\n\n[Rejected findings with brief rationale.]\n\n### Agreement Map\n\n[Where did models agree, where did they diverge, and what does the pattern of agreement\u002Fdisagreement tell us?]\n\n## Reasoning effort\n\nA role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. `session` sets no effort, so the dispatch is the usual one. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. On Claude Code, a level picks the effort agent from the `subagent_type` you would otherwise use. `patina-agent` becomes `subagent_type: \"patina-agent-\u003Clevel>\"`. `patina-reader` becomes `subagent_type: \"patina-reader-\u003Clevel>\"`. `general-purpose`, or no `subagent_type`, becomes `subagent_type: \"effort-\u003Clevel>\"`. The effort agents set only `effort`, so the model you pass still decides the model. On Codex, pass the level as `spawn_agent`'s `reasoning_effort` and keep the usual instructions.\n","# Interrogate\n\nOn Codex, read the [platform mapping](..\u002Fpatina-mode\u002Freferences\u002Fcodex-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, read the [platform mapping](..\u002Fpatina-mode\u002Freferences\u002Fcopilot-tools.md), including its per-skill notes, before following this skill.\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 `Agent` tool. Use the `interrogate reviewers` line in the `pstack-models.md` override sheet (`\u002Fsetup-pstack` lists its path per runtime), one reviewer per entry, extending or shrinking the Reviewer labels below to the configured entry count. If the sheet or that line is missing, use the table defaults.\n\n| Subagent | Default model |\n|----------|---------------|\n| Reviewer A | `opus` |\n| Reviewer B | `fable` |\n| Reviewer C | `sonnet` |\n| Reviewer D | `haiku` |\n\nFor each reviewer:\n\n- `subagent_type`: `patina-reader`\n- `model`: the configured `interrogate reviewers` entry, or the table default with no configured line. For an `auto` or `inherit-parent` entry, omit `model` so that reviewer runs on the parent model.\n- `readonly`: `true`\n\nIf the `Agent` tool rejects a configured entry, run that reviewer on the table default of its family and say so. Families go by model name, such as Opus, Fable, or Sonnet. With no family match, use Reviewer A's default. If it rejects a table default, check the valid slugs in the `Agent` tool's error message, pick the closest equivalent (prefer the same family and reasoning tier), spawn with it, and open a separate PR to update the default table. Do not block the review on the slug issue. Never treat an alias entry as a rejected slug or apply either fallback to it.\n\nRead `references\u002Freviewer-prompt.md` and fill in the template with:\n\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\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>\n> [The stated intent paragraph from Step 2]\n\n### Reviewers\n\n- Reviewer [label]: [model name], [N findings] (one bullet per reviewer)\n\n### Act On\n\n[Findings that should be addressed. For each: description, which models raised it, why it matters.]\n\n### Consider\n\n[Findings worth thinking about. For each: description, which models raised it, tradeoff involved.]\n\n### Noted\n\n[Valid but low-priority. Brief list.]\n\n### Dismissed\n\n[Rejected findings with brief rationale.]\n\n### Agreement Map\n\n[Where did models agree, where did they diverge, and what does the pattern of agreement\u002Fdisagreement tell us?]\n\n## Reasoning effort\n\nA role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. `session` sets no effort, so the dispatch is the usual one. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. On Claude Code, a level picks the effort agent from the `subagent_type` you would otherwise use. `patina-agent` becomes `subagent_type: \"patina-agent-\u003Clevel>\"`. `patina-reader` becomes `subagent_type: \"patina-reader-\u003Clevel>\"`. `general-purpose`, or no `subagent_type`, becomes `subagent_type: \"effort-\u003Clevel>\"`. The effort agents set only `effort`, so the model you pass still decides the model. On Codex, pass the level as `spawn_agent`'s `reasoning_effort` and keep the usual instructions.\n",{"name":5,"description":7},"main","e6ee720f466a8344a52abd87679191fadde3b63f","plugins\u002Fcode\u002Fskills\u002Finterrogate","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills","https:\u002F\u002Fgithub.com\u002Fpatinaproject","https:\u002F\u002Fwww.patinaproject.com","The best way to pick your next pair of boots or shoes.","2026-11-12 00:44:02",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add patinaproject\u002Fskills --skill interrogate",{"tool":54,"command":55},"bunx","bunx skills add patinaproject\u002Fskills --skill interrogate",{"tool":57,"command":58},"pnpm","pnpm dlx skills add patinaproject\u002Fskills --skill interrogate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Finterrogate\u002FSKILL.md",true,[62,68,72,76],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fcode-quality-review.md","REFERENCE","参考文档",5217,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Finterrogate\u002Freferences\u002Fcode-quality-review.md",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Flead-judgment.md",3466,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Finterrogate\u002Freferences\u002Flead-judgment.md",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Freviewer-prompt.md",2495,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Finterrogate\u002Freferences\u002Freviewer-prompt.md",{"path":77,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Frubric.md",5025,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Finterrogate\u002Freferences\u002Frubric.md",[81,89,117,129,152,176],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":88},"01M72KDQJR99954NE224VB3KZ2","code-review","Review the changes since a fixed point (commit, branch, tag, or merge-base) along five axes: Standards (does the code follow this repo's documented coding standards?), Spec (does the code match what the originating issue\u002Fspec asked for?), Evidence (does each claim in the pull request have evidence that shows it?), Bugs (does the changed code have logic errors, unhandled states, races, or regressions?), and Security (does the change open injection, auth, secret, input, or CI workflow holes?). Runs the reviews in parallel sub-agents, tags every finding Important, Nit, or Pre-existing, and reports them side by side with what blocks merge. Given an earlier reviewed head and its findings, it reviews only the newer commits, rechecks the earlier findings, and never repeats one. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fcode-review\u002FSKILL.md",[],[],"2026-11-10 22:39:42",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":105,"publishedAt":35},"01M71ESEDVHD9EXN6787XHP7HD","writing-for-pstack","Write or tighten an operator prompt for a patina-mode run. Use when the operator asks to write, revise, or review a prompt that will be passed to patina-mode.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwriting-for-pstack\u002FSKILL.md",[95,100],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[22,106,107,108,28,109,110,111,112,27,113,114,115,116],"pstack","writing","writing for pstack","run","mode","write","operator","tighten","prompt","when","revise",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":125,"publishedAt":35},"01M71ESCJ0SSJFFENF8HYDKBTJ","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[123,124],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},[126,22,107,127,27,128,115],"writing for agents","editing","documents",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":35},"01M71ESA1NN9WVMD2HA5Z1RRDY","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwizard\u002FSKILL.md",[],[131,136,137,138,139,140,115,141,142,143,144,145,27,146,147,148,22,149,150,151],"interactive","can","credentials","one","Bash","invoke","dashboard","generate","human","secrets","provisioning infrastructure","ci","up","setting","running","only",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":35},"01M71ES8FAN567N3JEPG8W6AS1","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[154,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,137,175,139],"more","true","decision","session","time","chunk","as","shared","map","tickets","destination","at","tracker","plan","work","agent session","one at a time",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":35},"01M71ES6PWJPKBW8R24YFH4PY6","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[183,184,185,186,187,188,189,190,160,191],"wait","wait what","stop","it","land","re","pitch","message","last"]