[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ESSRTWT8YAXQ5EH8CGF14C":3,"skill-same:01M7ESSRTWT8YAXQ5EH8CGF14C":49},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7ESSRTWT8YAXQ5EH8CGF14C","skill-review-response",null,"Use when a reviewer, CI bot, or another AI leaves feedback to address","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fskill-review-response\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-review-response\ndisable-model-invocation: true\ndescription: \"Use when a reviewer, CI bot, or another AI leaves feedback to address\"\ntrigger: |\n  EXPLICITLY USE when:\n  - Receiving code review feedback (PR comments, review agent output)\n  - Processing suggestions from \u002Focto:review or \u002Focto:staged-review\n  - Responding to CI failure feedback\n  - Handling changes-requested status on a PR\npaths:\n  - \".git\u002F**\"\n---\n\n# Receiving Code Review\n\n## Core Principle\n\nCode review requires technical evaluation, not performative agreement.\n\n**Never blindly implement review feedback.** Verify it's correct for THIS codebase before changing anything.\n\n## The Response Pattern\n\n```\nWHEN receiving code review feedback:\n\n1. READ    — Complete feedback without reacting\n2. RESTATE — Summarize the requirement in your own words\n3. VERIFY  — Check against actual codebase state\n4. EVALUATE — Is this technically sound for THIS context?\n5. RESPOND — Technical acknowledgment OR reasoned pushback\n6. IMPLEMENT — One item at a time, verify each change\n```\n\n## Forbidden Responses\n\n**NEVER say:**\n- \"You're absolutely right!\" (without verification)\n- \"Great catch!\" (before confirming it IS a catch)\n- \"I'll fix that right away!\" (before evaluating whether it needs fixing)\n- \"Done!\" (without running verification — see skill-verification-gate)\n\n**These are social performance, not technical evaluation.** They lead to:\n- Implementing wrong suggestions\n- Introducing bugs to \"fix\" non-issues\n- Wasting time on style preferences disguised as bugs\n\n## Evaluation Checklist\n\nFor each piece of feedback:\n\n| Question | If YES | If NO |\n|----------|--------|-------|\n| Is the issue real? (verify in code) | Continue evaluation | Push back with evidence |\n| Does the suggested fix work here? | Continue evaluation | Propose alternative |\n| Does fixing this break something else? | Fix both or push back | Implement the fix |\n| Is this a style preference or a real problem? | Acknowledge, deprioritize | Fix it |\n| Was this already considered and rejected? | Explain the trade-off | Implement |\n\n## How to Push Back\n\nWhen feedback is wrong or doesn't apply:\n\n```markdown\n> Reviewer: \"This function should handle null input\"\n>\n> Response: \"Checked — this function is only called from `processUser()`\n> (line 47) which validates non-null before dispatch. Adding null handling\n> here would be dead code. The caller contract guarantees non-null.\"\n```\n\nProvide:\n1. What you checked\n2. Why the suggestion doesn't apply\n3. Evidence (line numbers, call sites, tests)\n\n## Multi-Provider Review Context\n\nIn Claude Octopus workflows, review feedback comes from multiple sources:\n\n- **Codex review** — tends toward enterprise patterns, may over-engineer\n- **Antigravity review** — tends toward ecosystem conformity, may suggest unnecessary dependencies\n- **Claude review** — tends toward elegance, may under-engineer error handling\n- **Sonnet review** — tends toward thoroughness, may flag low-priority issues\n\nWhen providers disagree:\n- Check which provider's suggestion matches the ACTUAL codebase conventions\n- The codebase's existing patterns win over any provider's preferences\n- If two providers flag the same issue, it's probably real\n\n## Handling Feedback Loops\n\nWhen a reviewer flags an issue and you fix it:\n\n1. Make the fix\n2. **Run verification** (skill-verification-gate) — prove the fix works\n3. **Re-read the original feedback** — did you address the root cause or just the symptom?\n4. If the reviewer re-reviews and finds new issues, that's normal — don't get frustrated\n5. Each round should have FEWER issues, not different ones\n\nIf the same issue keeps coming back:\n- You're fixing symptoms, not the root cause\n- Stop and re-read the feedback from scratch\n- Ask the reviewer to clarify if the issue is ambiguous\n\n## When Review Feedback Conflicts with Requirements\n\nIf a reviewer suggests something that contradicts the spec\u002Frequirements:\n\n1. Note the conflict explicitly\n2. Check if the spec is wrong (it might be)\n3. If spec is correct: implement the spec, note the reviewer's concern for future consideration\n4. If spec is wrong: flag to the user before changing anything\n\n**Requirements trump review suggestions. User intent trumps both.**\n","# Receiving Code Review\n\n## Core Principle\n\nCode review requires technical evaluation, not performative agreement.\n\n**Never blindly implement review feedback.** Verify it's correct for THIS codebase before changing anything.\n\n## The Response Pattern\n\n```\nWHEN receiving code review feedback:\n\n1. READ    — Complete feedback without reacting\n2. RESTATE — Summarize the requirement in your own words\n3. VERIFY  — Check against actual codebase state\n4. EVALUATE — Is this technically sound for THIS context?\n5. RESPOND — Technical acknowledgment OR reasoned pushback\n6. IMPLEMENT — One item at a time, verify each change\n```\n\n## Forbidden Responses\n\n**NEVER say:**\n- \"You're absolutely right!\" (without verification)\n- \"Great catch!\" (before confirming it IS a catch)\n- \"I'll fix that right away!\" (before evaluating whether it needs fixing)\n- \"Done!\" (without running verification — see skill-verification-gate)\n\n**These are social performance, not technical evaluation.** They lead to:\n- Implementing wrong suggestions\n- Introducing bugs to \"fix\" non-issues\n- Wasting time on style preferences disguised as bugs\n\n## Evaluation Checklist\n\nFor each piece of feedback:\n\n| Question | If YES | If NO |\n|----------|--------|-------|\n| Is the issue real? (verify in code) | Continue evaluation | Push back with evidence |\n| Does the suggested fix work here? | Continue evaluation | Propose alternative |\n| Does fixing this break something else? | Fix both or push back | Implement the fix |\n| Is this a style preference or a real problem? | Acknowledge, deprioritize | Fix it |\n| Was this already considered and rejected? | Explain the trade-off | Implement |\n\n## How to Push Back\n\nWhen feedback is wrong or doesn't apply:\n\n```markdown\n> Reviewer: \"This function should handle null input\"\n>\n> Response: \"Checked — this function is only called from `processUser()`\n> (line 47) which validates non-null before dispatch. Adding null handling\n> here would be dead code. The caller contract guarantees non-null.\"\n```\n\nProvide:\n1. What you checked\n2. Why the suggestion doesn't apply\n3. Evidence (line numbers, call sites, tests)\n\n## Multi-Provider Review Context\n\nIn Claude Octopus workflows, review feedback comes from multiple sources:\n\n- **Codex review** — tends toward enterprise patterns, may over-engineer\n- **Antigravity review** — tends toward ecosystem conformity, may suggest unnecessary dependencies\n- **Claude review** — tends toward elegance, may under-engineer error handling\n- **Sonnet review** — tends toward thoroughness, may flag low-priority issues\n\nWhen providers disagree:\n- Check which provider's suggestion matches the ACTUAL codebase conventions\n- The codebase's existing patterns win over any provider's preferences\n- If two providers flag the same issue, it's probably real\n\n## Handling Feedback Loops\n\nWhen a reviewer flags an issue and you fix it:\n\n1. Make the fix\n2. **Run verification** (skill-verification-gate) — prove the fix works\n3. **Re-read the original feedback** — did you address the root cause or just the symptom?\n4. If the reviewer re-reviews and finds new issues, that's normal — don't get frustrated\n5. Each round should have FEWER issues, not different ones\n\nIf the same issue keeps coming back:\n- You're fixing symptoms, not the root cause\n- Stop and re-read the feedback from scratch\n- Ask the reviewer to clarify if the issue is ambiguous\n\n## When Review Feedback Conflicts with Requirements\n\nIf a reviewer suggests something that contradicts the spec\u002Frequirements:\n\n1. Note the conflict explicitly\n2. Check if the spec is wrong (it might be)\n3. If spec is correct: implement the spec, note the reviewer's concern for future consideration\n4. If spec is wrong: flag to the user before changing anything\n\n**Requirements trump review suggestions. User intent trumps both.**\n",{"name":5,"paths":24,"trigger":26,"description":7,"disable-model-invocation":27},[25],".git\u002F**","EXPLICITLY USE when:\n- Receiving code review feedback (PR comments, review agent output)\n- Processing suggestions from \u002Focto:review or \u002Focto:staged-review\n- Responding to CI failure feedback\n- Handling changes-requested status on a PR\n",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fskill-review-response",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-review-response",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-review-response",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-review-response","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fskill-review-response\u002FSKILL.md",[],[50,57,64,71,79,86],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7EXRM12046G0GM1WGMMFXCN","ci-cd-and-automation","Automates CI\u002FCD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fci-cd-and-automation\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7EXRFYYSJ3Y15AGPDDEWWQD","chrome-devtools","Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-devtools\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7EXR6EYPE4X5X1BTAE6QJRV","chrome-cdp","Drive a real Chrome via the Chrome DevTools Protocol (CDP). Ensures a\ndebuggable Chrome is running (launching it if needed) so the agent can\nnavigate, read page content, inspect the DOM, run JavaScript, and take\nscreenshots — without the user typing any launch command. Includes a\nfirst-class \"review a live running app\" flow: point Chrome at the app under\ndevelopment and inspect\u002Fscreenshot the REAL page (what a static-artifact tool\ncannot do). Backed by Glimpse and the chrome-devtools MCP server. Use when\nasked to \"use chrome\", \"open chrome\", \"drive my browser\", \"read the page in\nchrome\", \"review the running app\", \"screenshot the app\", or \"\u002Fchrome-cdp\".","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-cdp\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7EXR1Y7E79KQKG4J798XGH6","check-identity-pack","Run an AFP 100-point or AUSTRAC safe-harbour identity check over a set of documents, and report exactly what's missing. Use when the user asks to check identity documents, verify someone's ID for onboarding, or assess whether a document pack satisfies Australian identity requirements.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcheck-identity-pack\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7EXQXW7C7PGREJW9ZZTZ16H","changelog","Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchangelog\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7EXQMH2ZME3ANN8Q8MEWPFB","cellxgene-census","Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs\u002Fdownloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcellxgene-census\u002FSKILL.md",[],[]]