[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F44M8CGVABW62STBKRT7VW":3,"skill-same:01M7F44M8CGVABW62STBKRT7VW":58},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7F44M8CGVABW62STBKRT7VW","review-swarm",null,"Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps.","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\u002F05-技能与代理开发\u002Freview-swarm\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: review-swarm\ndescription: \"Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps.\"\nrisk: safe\nsource: https:\u002F\u002Fgithub.com\u002FDimillian\u002FSkills\u002Ftree\u002Fmain\u002Freview-swarm\nsource_repo: Dimillian\u002FSkills\nsource_type: community\ndate_added: 2026-07-01\nlicense: MIT\nlicense_source: https:\u002F\u002Fgithub.com\u002FDimillian\u002FSkills\u002Fblob\u002Fmain\u002FLICENSE\n---\n\n# Review Swarm\n## When to Use\n\nUse this skill when you need parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review,...\n\n\nReview a diff with four read-only sub-agents in parallel, then have the main agent filter, order, and summarize only the issues that matter. This skill is review-only: sub-agents do not edit files, and the main agent does not apply fixes as part of this workflow.\n\n## Step 1: Determine Scope and Intent\n\nPrefer this scope order:\n\n1. Files or paths explicitly named by the user\n2. Current git changes\n3. An explicit branch, commit, or PR diff requested by the user\n4. Most recently modified tracked files, only if the user asked for a review and there is no clearer diff\n\nIf there is no clear review scope, stop and say so briefly.\n\nWhen using git changes, choose the smallest correct diff command:\n\n- unstaged work: `git diff`\n- staged work: `git diff --cached`\n- mixed staged and unstaged work: review both\n- explicit branch or commit comparison: use exactly what the user requested\n\nBefore launching reviewers, read the closest local instructions and any relevant project docs for the touched area, such as:\n\n- `AGENTS.md`\n- repo workflow docs\n- architecture or contract docs for the touched module\n\nBuild a short intent packet for the reviewers:\n\n1. What behavior is meant to change\n2. What behavior should remain unchanged\n3. Any stated or inferred constraints, such as compatibility, rollout, security, or migration expectations\n\nIf the user did not state the intent clearly, infer it from the diff and say that the inference may be incomplete.\n\n## Step 2: Launch Four Read-Only Reviewers in Parallel\n\nLaunch four sub-agents when the scope is large enough for parallel review to help. For a tiny diff or one very small file, it is acceptable to review locally instead.\n\nFor every sub-agent:\n\n- give the same scope and the same intent packet\n- state that the sub-agent is read-only\n- do not let the sub-agent edit files, run `apply_patch`, stage changes, commit, or perform any other state-mutating action\n- ask for concise findings only\n- ask for: file and line or symbol, issue, why it matters, recommended follow-up, and confidence\n- tell the sub-agent to avoid nits, style preferences, and speculative concerns without concrete impact\n- tell the sub-agent to send findings back to the main agent only\n\nUse these four review roles.\n\n### Sub-Agent 1: Intent and Regression Review\n\nReview whether the diff matches the intended behavior change without introducing extra behavior drift.\n\nCheck for:\n\n1. Unintended behavior changes outside the stated scope\n2. Broken edge cases or fallback paths\n3. Contract drift between callers and callees\n4. Missing updates to adjacent flows that should change together\n\nThis sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.\n\nRecommended sub-agent role: `reviewer`\n\n### Sub-Agent 2: Security and Privacy Review\n\nReview the diff for security regressions, privacy risks, and trust-boundary mistakes.\n\nCheck for:\n\n1. Missing or weakened authn or authz checks\n2. Unsafe input handling, injection risks, or validation gaps\n3. Secret, token, or sensitive data exposure\n4. Risky defaults, permission expansion, or trust of unverified data\n\nThis sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.\n\nRecommended sub-agent role: `reviewer`\n\n### Sub-Agent 3: Performance and Reliability Review\n\nReview the diff for new cost, fragility, or operational risk.\n\nCheck for:\n\n1. Duplicate work, redundant I\u002FO, or unnecessary recomputation\n2. Added work on startup, render, request, or other hot paths\n3. Leaks, missing cleanup, retry storms, or subscription drift\n4. Ordering, race, or failure-handling problems that make the change brittle\n\nThis sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.\n\nRecommended sub-agent role: `reviewer`\n\n### Sub-Agent 4: Contracts and Coverage Review\n\nReview the diff for compatibility gaps and missing safety nets.\n\nCheck for:\n\n1. API, schema, type, config, or feature-flag mismatches\n2. Migration or backward-compatibility fallout\n3. Missing or weak tests for the changed behavior\n4. Missing logs, metrics, assertions, or error paths that make regressions harder to detect\n\nThis sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.\n\nRecommended sub-agent role: `reviewer`\n\nReport only issues that materially affect correctness, security, privacy, reliability, compatibility, or confidence in the change. It is better to miss a nit than to bury the user in low-value noise.\n\n## Step 3: Aggregate and Filter Findings\n\nThe main agent owns synthesis. Treat sub-agent output as raw review input, not final output.\n\nMerge findings across all four reviewers and filter aggressively:\n\n- drop duplicates\n- drop weak or speculative claims\n- drop issues that conflict with the stated intent\n- drop minor style or readability comments unless they hide a real bug or maintenance risk\n\nNormalize surviving findings into this shape:\n\n1. File and line or nearest symbol\n2. Category: regression, security, reliability, or contracts\n3. Severity: high, medium, or low\n4. Why it matters\n5. Recommended fix or follow-up\n6. Confidence: high, medium, or low\n\nIf a reviewer may be correct but the intent is unclear, turn it into an open question instead of a finding.\n\n## Step 4: Order the Output\n\nPresent findings in this order:\n\n1. High-severity, high-confidence issues\n2. Medium-severity issues that are likely worth fixing before merge\n3. Lower-severity issues or follow-ups that can wait\n\nKeep the review concise. Findings should be actionable and evidence-backed.\n\nIf there are no material issues, say that directly instead of manufacturing feedback.\n\n## Step 5: Recommend a Clear Path Forward\n\nAfter the findings, give the user a short path forward:\n\n- what to fix before merge\n- what to improve if time permits\n- what can safely be left alone\n\nWhen helpful, group the path forward into:\n\n- `fix now`\n- `fix soon`\n- `optional follow-up`\n\nDo not implement fixes as part of this skill. The output is a read-only review plus a prioritized recommendation.\n\n## Example\n\n**User request:**\n\n> Use @review-swarm for this task: Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps.\n\n## Limitations\n\n- Use this skill only when the task clearly matches its upstream source and local project context.\n- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.\n- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.\n","# Review Swarm\n## When to Use\n\nUse this skill when you need parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review,...\n\n\nReview a diff with four read-only sub-agents in parallel, then have the main agent filter, order, and summarize only the issues that matter. This skill is review-only: sub-agents do not edit files, and the main agent does not apply fixes as part of this workflow.\n\n## Step 1: Determine Scope and Intent\n\nPrefer this scope order:\n\n1. Files or paths explicitly named by the user\n2. Current git changes\n3. An explicit branch, commit, or PR diff requested by the user\n4. Most recently modified tracked files, only if the user asked for a review and there is no clearer diff\n\nIf there is no clear review scope, stop and say so briefly.\n\nWhen using git changes, choose the smallest correct diff command:\n\n- unstaged work: `git diff`\n- staged work: `git diff --cached`\n- mixed staged and unstaged work: review both\n- explicit branch or commit comparison: use exactly what the user requested\n\nBefore launching reviewers, read the closest local instructions and any relevant project docs for the touched area, such as:\n\n- `AGENTS.md`\n- repo workflow docs\n- architecture or contract docs for the touched module\n\nBuild a short intent packet for the reviewers:\n\n1. What behavior is meant to change\n2. What behavior should remain unchanged\n3. Any stated or inferred constraints, such as compatibility, rollout, security, or migration expectations\n\nIf the user did not state the intent clearly, infer it from the diff and say that the inference may be incomplete.\n\n## Step 2: Launch Four Read-Only Reviewers in Parallel\n\nLaunch four sub-agents when the scope is large enough for parallel review to help. For a tiny diff or one very small file, it is acceptable to review locally instead.\n\nFor every sub-agent:\n\n- give the same scope and the same intent packet\n- state that the sub-agent is read-only\n- do not let the sub-agent edit files, run `apply_patch`, stage changes, commit, or perform any other state-mutating action\n- ask for concise findings only\n- ask for: file and line or symbol, issue, why it matters, recommended follow-up, and confidence\n- tell the sub-agent to avoid nits, style preferences, and speculative concerns without concrete impact\n- tell the sub-agent to send findings back to the main agent only\n\nUse these four review roles.\n\n### Sub-Agent 1: Intent and Regression Review\n\nReview whether the diff matches the intended behavior change without introducing extra behavior drift.\n\nCheck for:\n\n1. Unintended behavior changes outside the stated scope\n2. Broken edge cases or fallback paths\n3. Contract drift between callers and callees\n4. Missing updates to adjacent flows that should change together\n\nThis sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.\n\nRecommended sub-agent role: `reviewer`\n\n### Sub-Agent 2: Security and Privacy Review\n\nReview the diff for security regressions, privacy risks, and trust-boundary mistakes.\n\nCheck for:\n\n1. Missing or weakened authn or authz checks\n2. Unsafe input handling, injection risks, or validation gaps\n3. Secret, token, or sensitive data exposure\n4. Risky defaults, permission expansion, or trust of unverified data\n\nThis sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.\n\nRecommended sub-agent role: `reviewer`\n\n### Sub-Agent 3: Performance and Reliability Review\n\nReview the diff for new cost, fragility, or operational risk.\n\nCheck for:\n\n1. Duplicate work, redundant I\u002FO, or unnecessary recomputation\n2. Added work on startup, render, request, or other hot paths\n3. Leaks, missing cleanup, retry storms, or subscription drift\n4. Ordering, race, or failure-handling problems that make the change brittle\n\nThis sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.\n\nRecommended sub-agent role: `reviewer`\n\n### Sub-Agent 4: Contracts and Coverage Review\n\nReview the diff for compatibility gaps and missing safety nets.\n\nCheck for:\n\n1. API, schema, type, config, or feature-flag mismatches\n2. Migration or backward-compatibility fallout\n3. Missing or weak tests for the changed behavior\n4. Missing logs, metrics, assertions, or error paths that make regressions harder to detect\n\nThis sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.\n\nRecommended sub-agent role: `reviewer`\n\nReport only issues that materially affect correctness, security, privacy, reliability, compatibility, or confidence in the change. It is better to miss a nit than to bury the user in low-value noise.\n\n## Step 3: Aggregate and Filter Findings\n\nThe main agent owns synthesis. Treat sub-agent output as raw review input, not final output.\n\nMerge findings across all four reviewers and filter aggressively:\n\n- drop duplicates\n- drop weak or speculative claims\n- drop issues that conflict with the stated intent\n- drop minor style or readability comments unless they hide a real bug or maintenance risk\n\nNormalize surviving findings into this shape:\n\n1. File and line or nearest symbol\n2. Category: regression, security, reliability, or contracts\n3. Severity: high, medium, or low\n4. Why it matters\n5. Recommended fix or follow-up\n6. Confidence: high, medium, or low\n\nIf a reviewer may be correct but the intent is unclear, turn it into an open question instead of a finding.\n\n## Step 4: Order the Output\n\nPresent findings in this order:\n\n1. High-severity, high-confidence issues\n2. Medium-severity issues that are likely worth fixing before merge\n3. Lower-severity issues or follow-ups that can wait\n\nKeep the review concise. Findings should be actionable and evidence-backed.\n\nIf there are no material issues, say that directly instead of manufacturing feedback.\n\n## Step 5: Recommend a Clear Path Forward\n\nAfter the findings, give the user a short path forward:\n\n- what to fix before merge\n- what to improve if time permits\n- what can safely be left alone\n\nWhen helpful, group the path forward into:\n\n- `fix now`\n- `fix soon`\n- `optional follow-up`\n\nDo not implement fixes as part of this skill. The output is a read-only review plus a prioritized recommendation.\n\n## Example\n\n**User request:**\n\n> Use @review-swarm for this task: Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps.\n\n## Limitations\n\n- Use this skill only when the task clearly matches its upstream source and local project context.\n- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.\n- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.\n",{"name":5,"risk":24,"source":25,"license":15,"date_added":26,"description":7,"source_repo":27,"source_type":28,"license_source":29},"safe","https:\u002F\u002Fgithub.com\u002FDimillian\u002FSkills\u002Ftree\u002Fmain\u002Freview-swarm",1782864000000,"Dimillian\u002FSkills","community","https:\u002F\u002Fgithub.com\u002FDimillian\u002FSkills\u002Fblob\u002Fmain\u002FLICENSE","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Freview-swarm",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":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill review-swarm",{"tool":44,"command":45},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill review-swarm",{"tool":47,"command":48},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill review-swarm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Freview-swarm\u002FSKILL.md",true,[52],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"agents\u002Fopenai.yaml","REFERENCE","参考文档",248,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Freview-swarm\u002Fagents\u002Fopenai.yaml",[59,66,71,78,85,92],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":67,"name":61,"nameZh":6,"description":62,"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},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\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":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]