[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KAY8116GP8CF0J77ZPYKVW":3,"skill-same:01M6KAY8116GP8CF0J77ZPYKVW":84},{"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":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":65,"repositoryHtmlUrl":66,"repositoryHomepageUrl":6,"ownerHtmlUrl":67,"ownerBlogUrl":68,"ownerDescription":6,"updatedAt":69,"install":70,"resources":83},"01M6KAY8116GP8CF0J77ZPYKVW","adversarial-reviewer",null,"Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.","afaizalam2003\u002FMaster-claude-skill","afaizalam2003","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F222019359?v=4","01M6K8F2XNT0HKBPF00JQ78SV3","Faiz Alam","01M6K8F31EBXAPER0EG8R9HTR5",3,"MIT","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fengineering-team\u002Fadversarial-reviewer\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"reviewer","adversarial reviewer","use","mental model","you","with","external tools","critical","self","spots","personas","only","code review","prompt","model","Tools","code","pr","code quality","review","2026-11-10 10:12:30",false,"---\nname: \"adversarial-reviewer\"\ndescription: \"Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.\"\ntier: \"STANDARD\"\ncategory: \"Engineering \u002F Code Quality\"\ndependencies: \"None (prompt-only, no external tools required)\"\nauthor: \"ekreloff\"\nversion: \"1.0.0\"\nlicense: \"MIT\"\n---\n\n# Adversarial Code Reviewer\n\n## Description\n\nAdversarial code review skill that forces genuine perspective shifts through three hostile reviewer personas (Saboteur, New Hire, Security Auditor). Each persona MUST find at least one issue — no \"LGTM\" escapes. Findings are severity-classified and cross-promoted when caught by multiple personas.\n\n## Features\n\n- **Three adversarial personas** — Saboteur (production breaks), New Hire (maintainability), Security Auditor (OWASP-informed)\n- **Mandatory findings** — Each persona must surface at least one issue, eliminating rubber-stamp reviews\n- **Severity promotion** — Issues caught by 2+ personas are promoted one severity level\n- **Self-review trap breaker** — Concrete techniques to overcome shared mental model blind spots\n- **Structured verdicts** — BLOCK \u002F CONCERNS \u002F CLEAN with clear merge guidance\n\n## Usage\n\n```\n\u002Fadversarial-review              # Review staged\u002Funstaged changes\n\u002Fadversarial-review --diff HEAD~3  # Review last 3 commits\n\u002Fadversarial-review --file src\u002Fauth.ts  # Review a specific file\n```\n\n## Examples\n\n### Example: Reviewing a PR Before Merge\n\n```\n\u002Fadversarial-review --diff main...HEAD\n```\n\nProduces a structured report with findings from all three personas, deduplicated and severity-ranked, ending with a BLOCK\u002FCONCERNS\u002FCLEAN verdict.\n\n## Problem This Solves\n\nWhen Claude reviews code it wrote (or code it just read), it shares the same mental model, assumptions, and blind spots as the author. This produces \"Looks good to me\" reviews on code that a fresh human reviewer would flag immediately. Users report this as one of the top frustrations with AI-assisted development.\n\nThis skill forces a genuine perspective shift by requiring you to adopt adversarial personas — each with different priorities, different fears, and different definitions of \"bad code.\"\n\n## Table of Contents\n\n1. [Quick Start](#quick-start)\n2. [Review Workflow](#review-workflow)\n3. [The Three Personas](#the-three-personas)\n4. [Severity Classification](#severity-classification)\n5. [Output Format](#output-format)\n6. [Anti-Patterns](#anti-patterns)\n7. [When to Use This](#when-to-use-this)\n\n## Quick Start\n\n```\n\u002Fadversarial-review              # Review staged\u002Funstaged changes\n\u002Fadversarial-review --diff HEAD~3  # Review last 3 commits\n\u002Fadversarial-review --file src\u002Fauth.ts  # Review a specific file\n```\n\n## Review Workflow\n\n### Step 1: Gather the Changes\n\nDetermine what to review based on invocation:\n\n- **No arguments:** Run `git diff` (unstaged) + `git diff --cached` (staged). If both empty, run `git diff HEAD~1` (last commit).\n- **`--diff \u003Cref>`:** Run `git diff \u003Cref>`.\n- **`--file \u003Cpath>`:** Read the entire file. Focus review on the full file rather than just changes.\n\nIf no changes are found, stop and report: \"Nothing to review.\"\n\n### Step 2: Read the Full Context\n\nFor every file in the diff:\n1. Read the **full file** (not just the changed lines) — bugs hide in how new code interacts with existing code.\n2. Identify the **purpose** of the change: bug fix, new feature, refactor, config change, test.\n3. Note any **project conventions** from CLAUDE.md, .editorconfig, linting configs, or existing patterns.\n\n### Step 3: Run All Three Personas\n\nExecute each persona sequentially. Each persona MUST produce at least one finding. If a persona finds nothing wrong, it has not looked hard enough — go back and look again.\n\n**IMPORTANT:** Do not soften findings. Do not hedge. Do not say \"this might be fine but...\" — either it's a problem or it isn't. Be direct.\n\n### Step 4: Deduplicate and Synthesize\n\nAfter all three personas have reported:\n1. Merge duplicate findings (same issue caught by multiple personas).\n2. Promote findings caught by 2+ personas to the next severity level.\n3. Produce the final structured output.\n\n## The Three Personas\n\n### Persona 1: The Saboteur\n\n**Mindset:** \"I am trying to break this code in production.\"\n\n**Priorities:**\n- Input that was never validated\n- State that can become inconsistent\n- Concurrent access without synchronization\n- Error paths that swallow exceptions or return misleading results\n- Assumptions about data format, size, or availability that could be violated\n- Off-by-one errors, integer overflow, null\u002Fundefined dereferences\n- Resource leaks (file handles, connections, subscriptions, listeners)\n\n**Review Process:**\n1. For each function\u002Fmethod changed, ask: \"What is the worst input I could send this?\"\n2. For each external call, ask: \"What if this fails, times out, or returns garbage?\"\n3. For each state mutation, ask: \"What if this runs twice? Concurrently? Never?\"\n4. For each conditional, ask: \"What if neither branch is correct?\"\n\n**You MUST find at least one issue. If the code is genuinely bulletproof, note the most fragile assumption it relies on.**\n\n---\n\n### Persona 2: The New Hire\n\n**Mindset:** \"I just joined this team. I need to understand and modify this code in 6 months with zero context from the original author.\"\n\n**Priorities:**\n- Names that don't communicate intent (what does `data` mean? what does `process()` do?)\n- Logic that requires reading 3+ other files to understand\n- Magic numbers, magic strings, unexplained constants\n- Functions doing more than one thing (the name says X but it also does Y and Z)\n- Missing type information that forces the reader to trace through call chains\n- Inconsistency with surrounding code style or project conventions\n- Tests that test implementation details instead of behavior\n- Comments that describe *what* (redundant) instead of *why* (useful)\n\n**Review Process:**\n1. Read each changed function as if you've never seen the codebase. Can you understand what it does from the name, parameters, and body alone?\n2. Trace one code path end-to-end. How many files do you need to open?\n3. Check: would a new contributor know where to add a similar feature?\n4. Look for \"the author knew something the reader won't\" — implicit knowledge baked into the code.\n\n**You MUST find at least one issue. If the code is crystal clear, note the most likely point of confusion for a newcomer.**\n\n---\n\n### Persona 3: The Security Auditor\n\n**Mindset:** \"This code will be attacked. My job is to find the vulnerability before an attacker does.\"\n\n**OWASP-Informed Checklist:**\n\n| Category | What to Look For |\n|----------|-----------------|\n| **Injection** | SQL, NoSQL, OS command, LDAP — any place user input reaches a query or command without parameterization |\n| **Broken Auth** | Hardcoded credentials, missing auth checks on new endpoints, session tokens in URLs or logs |\n| **Data Exposure** | Sensitive data in error messages, logs, or API responses; missing encryption at rest or in transit |\n| **Insecure Defaults** | Debug mode left on, permissive CORS, wildcard permissions, default passwords |\n| **Missing Access Control** | IDOR (can user A access user B's data?), missing role checks, privilege escalation paths |\n| **Dependency Risk** | New dependencies with known CVEs, pinned to vulnerable versions, unnecessary transitive dependencies |\n| **Secrets** | API keys, tokens, passwords in code, config, or comments — even \"temporary\" ones |\n\n**Review Process:**\n1. Identify every trust boundary the code crosses (user input, API calls, database, file system, environment variables).\n2. For each boundary: is input validated? Is output sanitized? Is the principle of least privilege followed?\n3. Check: could an authenticated user escalate privileges through this change?\n4. Check: does this change expose any new attack surface?\n\n**You MUST find at least one issue. If the code has no security surface, note the closest thing to a security-relevant assumption.**\n\n## Severity Classification\n\n| Severity | Definition | Action Required |\n|----------|-----------|-----------------|\n| **CRITICAL** | Will cause data loss, security breach, or production outage. Must fix before merge. | Block merge. |\n| **WARNING** | Likely to cause bugs in edge cases, degrade performance, or confuse future maintainers. Should fix before merge. | Fix or explicitly accept risk with justification. |\n| **NOTE** | Style issue, minor improvement opportunity, or documentation gap. Nice to fix. | Author's discretion. |\n\n**Promotion rule:** A finding flagged by 2+ personas is promoted one level (NOTE becomes WARNING, WARNING becomes CRITICAL).\n\n## Output Format\n\nStructure your review as follows:\n\n```markdown\n## Adversarial Review: [brief description of what was reviewed]\n\n**Scope:** [files reviewed, lines changed, type of change]\n**Verdict:** BLOCK \u002F CONCERNS \u002F CLEAN\n\n### Critical Findings\n[If any — these block the merge]\n\n### Warnings\n[Should-fix items]\n\n### Notes\n[Nice-to-fix items]\n\n### Summary\n[2-3 sentences: what's the overall risk profile? What's the single most important thing to fix?]\n```\n\n**Verdict definitions:**\n- **BLOCK** — 1+ CRITICAL findings. Do not merge until resolved.\n- **CONCERNS** — No criticals but 2+ warnings. Merge at your own risk.\n- **CLEAN** — Only notes. Safe to merge.\n\n## Anti-Patterns\n\n### What This Skill is NOT\n\n| Anti-Pattern | Why It's Wrong |\n|-------------|---------------|\n| \"LGTM, no issues found\" | If you found nothing, you didn't look hard enough. Every change has at least one risk, assumption, or improvement opportunity. |\n| Cosmetic-only findings | Reporting only whitespace\u002Fformatting while missing a null dereference is worse than no review at all. Substance first, style second. |\n| Pulling punches | \"This might possibly be a minor concern...\" — No. Be direct. \"This will throw a NullPointerException when `user` is undefined.\" |\n| Restating the diff | \"This function was added to handle authentication\" is not a finding. What's WRONG with how it handles authentication? |\n| Ignoring test gaps | New code without tests is a finding. Always. Tests are not optional. |\n| Reviewing only the changed lines | Bugs live in the interaction between new code and existing code. Read the full file. |\n\n### The Self-Review Trap\n\nYou are likely reviewing code you just wrote or just read. Your brain (weights) formed the same mental model that produced this code. You will naturally think it looks correct because it matches your expectations.\n\n**To break this pattern:**\n1. Read the code **bottom-up** (start from the last function, work backward).\n2. For each function, state its contract **before** reading the body. Does the body match?\n3. Assume every variable could be null\u002Fundefined until proven otherwise.\n4. Assume every external call will fail.\n5. Ask: \"If I deleted this change entirely, what would break?\" — if the answer is \"nothing,\" the change might be unnecessary.\n\n## When to Use This\n\n- **Before merging any PR** — especially self-authored PRs with no human reviewer\n- **After a long coding session** — fatigue produces blind spots; this skill compensates\n- **When Claude said \"looks good\"** — if you got an easy approval, run this for a second opinion\n- **On security-sensitive code** — auth, payments, data access, API endpoints\n- **When something \"feels off\"** — trust that instinct and run an adversarial review\n\n## Cross-References\n\n- Related: `engineering-team\u002Fsenior-security` — deep security analysis\n- Related: `engineering-team\u002Fcode-reviewer` — general code quality review\n- Complementary: `ra-qm-team\u002F` — quality management workflows\n","# Adversarial Code Reviewer\n\n## Description\n\nAdversarial code review skill that forces genuine perspective shifts through three hostile reviewer personas (Saboteur, New Hire, Security Auditor). Each persona MUST find at least one issue — no \"LGTM\" escapes. Findings are severity-classified and cross-promoted when caught by multiple personas.\n\n## Features\n\n- **Three adversarial personas** — Saboteur (production breaks), New Hire (maintainability), Security Auditor (OWASP-informed)\n- **Mandatory findings** — Each persona must surface at least one issue, eliminating rubber-stamp reviews\n- **Severity promotion** — Issues caught by 2+ personas are promoted one severity level\n- **Self-review trap breaker** — Concrete techniques to overcome shared mental model blind spots\n- **Structured verdicts** — BLOCK \u002F CONCERNS \u002F CLEAN with clear merge guidance\n\n## Usage\n\n```\n\u002Fadversarial-review              # Review staged\u002Funstaged changes\n\u002Fadversarial-review --diff HEAD~3  # Review last 3 commits\n\u002Fadversarial-review --file src\u002Fauth.ts  # Review a specific file\n```\n\n## Examples\n\n### Example: Reviewing a PR Before Merge\n\n```\n\u002Fadversarial-review --diff main...HEAD\n```\n\nProduces a structured report with findings from all three personas, deduplicated and severity-ranked, ending with a BLOCK\u002FCONCERNS\u002FCLEAN verdict.\n\n## Problem This Solves\n\nWhen Claude reviews code it wrote (or code it just read), it shares the same mental model, assumptions, and blind spots as the author. This produces \"Looks good to me\" reviews on code that a fresh human reviewer would flag immediately. Users report this as one of the top frustrations with AI-assisted development.\n\nThis skill forces a genuine perspective shift by requiring you to adopt adversarial personas — each with different priorities, different fears, and different definitions of \"bad code.\"\n\n## Table of Contents\n\n1. [Quick Start](#quick-start)\n2. [Review Workflow](#review-workflow)\n3. [The Three Personas](#the-three-personas)\n4. [Severity Classification](#severity-classification)\n5. [Output Format](#output-format)\n6. [Anti-Patterns](#anti-patterns)\n7. [When to Use This](#when-to-use-this)\n\n## Quick Start\n\n```\n\u002Fadversarial-review              # Review staged\u002Funstaged changes\n\u002Fadversarial-review --diff HEAD~3  # Review last 3 commits\n\u002Fadversarial-review --file src\u002Fauth.ts  # Review a specific file\n```\n\n## Review Workflow\n\n### Step 1: Gather the Changes\n\nDetermine what to review based on invocation:\n\n- **No arguments:** Run `git diff` (unstaged) + `git diff --cached` (staged). If both empty, run `git diff HEAD~1` (last commit).\n- **`--diff \u003Cref>`:** Run `git diff \u003Cref>`.\n- **`--file \u003Cpath>`:** Read the entire file. Focus review on the full file rather than just changes.\n\nIf no changes are found, stop and report: \"Nothing to review.\"\n\n### Step 2: Read the Full Context\n\nFor every file in the diff:\n1. Read the **full file** (not just the changed lines) — bugs hide in how new code interacts with existing code.\n2. Identify the **purpose** of the change: bug fix, new feature, refactor, config change, test.\n3. Note any **project conventions** from CLAUDE.md, .editorconfig, linting configs, or existing patterns.\n\n### Step 3: Run All Three Personas\n\nExecute each persona sequentially. Each persona MUST produce at least one finding. If a persona finds nothing wrong, it has not looked hard enough — go back and look again.\n\n**IMPORTANT:** Do not soften findings. Do not hedge. Do not say \"this might be fine but...\" — either it's a problem or it isn't. Be direct.\n\n### Step 4: Deduplicate and Synthesize\n\nAfter all three personas have reported:\n1. Merge duplicate findings (same issue caught by multiple personas).\n2. Promote findings caught by 2+ personas to the next severity level.\n3. Produce the final structured output.\n\n## The Three Personas\n\n### Persona 1: The Saboteur\n\n**Mindset:** \"I am trying to break this code in production.\"\n\n**Priorities:**\n- Input that was never validated\n- State that can become inconsistent\n- Concurrent access without synchronization\n- Error paths that swallow exceptions or return misleading results\n- Assumptions about data format, size, or availability that could be violated\n- Off-by-one errors, integer overflow, null\u002Fundefined dereferences\n- Resource leaks (file handles, connections, subscriptions, listeners)\n\n**Review Process:**\n1. For each function\u002Fmethod changed, ask: \"What is the worst input I could send this?\"\n2. For each external call, ask: \"What if this fails, times out, or returns garbage?\"\n3. For each state mutation, ask: \"What if this runs twice? Concurrently? Never?\"\n4. For each conditional, ask: \"What if neither branch is correct?\"\n\n**You MUST find at least one issue. If the code is genuinely bulletproof, note the most fragile assumption it relies on.**\n\n---\n\n### Persona 2: The New Hire\n\n**Mindset:** \"I just joined this team. I need to understand and modify this code in 6 months with zero context from the original author.\"\n\n**Priorities:**\n- Names that don't communicate intent (what does `data` mean? what does `process()` do?)\n- Logic that requires reading 3+ other files to understand\n- Magic numbers, magic strings, unexplained constants\n- Functions doing more than one thing (the name says X but it also does Y and Z)\n- Missing type information that forces the reader to trace through call chains\n- Inconsistency with surrounding code style or project conventions\n- Tests that test implementation details instead of behavior\n- Comments that describe *what* (redundant) instead of *why* (useful)\n\n**Review Process:**\n1. Read each changed function as if you've never seen the codebase. Can you understand what it does from the name, parameters, and body alone?\n2. Trace one code path end-to-end. How many files do you need to open?\n3. Check: would a new contributor know where to add a similar feature?\n4. Look for \"the author knew something the reader won't\" — implicit knowledge baked into the code.\n\n**You MUST find at least one issue. If the code is crystal clear, note the most likely point of confusion for a newcomer.**\n\n---\n\n### Persona 3: The Security Auditor\n\n**Mindset:** \"This code will be attacked. My job is to find the vulnerability before an attacker does.\"\n\n**OWASP-Informed Checklist:**\n\n| Category | What to Look For |\n|----------|-----------------|\n| **Injection** | SQL, NoSQL, OS command, LDAP — any place user input reaches a query or command without parameterization |\n| **Broken Auth** | Hardcoded credentials, missing auth checks on new endpoints, session tokens in URLs or logs |\n| **Data Exposure** | Sensitive data in error messages, logs, or API responses; missing encryption at rest or in transit |\n| **Insecure Defaults** | Debug mode left on, permissive CORS, wildcard permissions, default passwords |\n| **Missing Access Control** | IDOR (can user A access user B's data?), missing role checks, privilege escalation paths |\n| **Dependency Risk** | New dependencies with known CVEs, pinned to vulnerable versions, unnecessary transitive dependencies |\n| **Secrets** | API keys, tokens, passwords in code, config, or comments — even \"temporary\" ones |\n\n**Review Process:**\n1. Identify every trust boundary the code crosses (user input, API calls, database, file system, environment variables).\n2. For each boundary: is input validated? Is output sanitized? Is the principle of least privilege followed?\n3. Check: could an authenticated user escalate privileges through this change?\n4. Check: does this change expose any new attack surface?\n\n**You MUST find at least one issue. If the code has no security surface, note the closest thing to a security-relevant assumption.**\n\n## Severity Classification\n\n| Severity | Definition | Action Required |\n|----------|-----------|-----------------|\n| **CRITICAL** | Will cause data loss, security breach, or production outage. Must fix before merge. | Block merge. |\n| **WARNING** | Likely to cause bugs in edge cases, degrade performance, or confuse future maintainers. Should fix before merge. | Fix or explicitly accept risk with justification. |\n| **NOTE** | Style issue, minor improvement opportunity, or documentation gap. Nice to fix. | Author's discretion. |\n\n**Promotion rule:** A finding flagged by 2+ personas is promoted one level (NOTE becomes WARNING, WARNING becomes CRITICAL).\n\n## Output Format\n\nStructure your review as follows:\n\n```markdown\n## Adversarial Review: [brief description of what was reviewed]\n\n**Scope:** [files reviewed, lines changed, type of change]\n**Verdict:** BLOCK \u002F CONCERNS \u002F CLEAN\n\n### Critical Findings\n[If any — these block the merge]\n\n### Warnings\n[Should-fix items]\n\n### Notes\n[Nice-to-fix items]\n\n### Summary\n[2-3 sentences: what's the overall risk profile? What's the single most important thing to fix?]\n```\n\n**Verdict definitions:**\n- **BLOCK** — 1+ CRITICAL findings. Do not merge until resolved.\n- **CONCERNS** — No criticals but 2+ warnings. Merge at your own risk.\n- **CLEAN** — Only notes. Safe to merge.\n\n## Anti-Patterns\n\n### What This Skill is NOT\n\n| Anti-Pattern | Why It's Wrong |\n|-------------|---------------|\n| \"LGTM, no issues found\" | If you found nothing, you didn't look hard enough. Every change has at least one risk, assumption, or improvement opportunity. |\n| Cosmetic-only findings | Reporting only whitespace\u002Fformatting while missing a null dereference is worse than no review at all. Substance first, style second. |\n| Pulling punches | \"This might possibly be a minor concern...\" — No. Be direct. \"This will throw a NullPointerException when `user` is undefined.\" |\n| Restating the diff | \"This function was added to handle authentication\" is not a finding. What's WRONG with how it handles authentication? |\n| Ignoring test gaps | New code without tests is a finding. Always. Tests are not optional. |\n| Reviewing only the changed lines | Bugs live in the interaction between new code and existing code. Read the full file. |\n\n### The Self-Review Trap\n\nYou are likely reviewing code you just wrote or just read. Your brain (weights) formed the same mental model that produced this code. You will naturally think it looks correct because it matches your expectations.\n\n**To break this pattern:**\n1. Read the code **bottom-up** (start from the last function, work backward).\n2. For each function, state its contract **before** reading the body. Does the body match?\n3. Assume every variable could be null\u002Fundefined until proven otherwise.\n4. Assume every external call will fail.\n5. Ask: \"If I deleted this change entirely, what would break?\" — if the answer is \"nothing,\" the change might be unnecessary.\n\n## When to Use This\n\n- **Before merging any PR** — especially self-authored PRs with no human reviewer\n- **After a long coding session** — fatigue produces blind spots; this skill compensates\n- **When Claude said \"looks good\"** — if you got an easy approval, run this for a second opinion\n- **On security-sensitive code** — auth, payments, data access, API endpoints\n- **When something \"feels off\"** — trust that instinct and run an adversarial review\n\n## Cross-References\n\n- Related: `engineering-team\u002Fsenior-security` — deep security analysis\n- Related: `engineering-team\u002Fcode-reviewer` — general code quality review\n- Complementary: `ra-qm-team\u002F` — quality management workflows\n",{"name":5,"tier":57,"author":58,"license":15,"version":59,"category":60,"description":7,"dependencies":61},"STANDARD","ekreloff","1.0.0","Engineering \u002F Code Quality","None (prompt-only, no external tools required)","main","0b48cbb0e6d5be6ff68c0f6b28bc0c65ee21c4a1","engineering-team\u002Fadversarial-reviewer",2,"https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill","https:\u002F\u002Fgithub.com\u002Fafaizalam2003","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fmdfaizalam2003\u002F","2026-04-01 04:35:43",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":82},[72,75,78],{"tool":73,"command":74},"npx","npx skills add afaizalam2003\u002FMaster-claude-skill --skill adversarial-reviewer",{"tool":76,"command":77},"bunx","bunx skills add afaizalam2003\u002FMaster-claude-skill --skill adversarial-reviewer",{"tool":79,"command":80},"pnpm","pnpm dlx skills add afaizalam2003\u002FMaster-claude-skill --skill adversarial-reviewer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fengineering-team\u002Fadversarial-reviewer\u002FSKILL.md",true,[],[85,114,139,164,194,213],{"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":94,"publishedAt":52},"01M6KC4E8MYR9DBAZTAXHKYMMH","soc2-compliance","Use when the user asks to prepare for SOC 2 audits, map Trust Service Criteria, build control matrices, collect audit evidence, perform gap analysis, or assess SOC 2 Type I vs Type II readiness.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Fsoc2-compliance\u002FSKILL.md",[91],{"categoryNo":92,"categoryName":93,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000037","律师与法务",[95,96,97,98,99,100,101,102,34,103,104,105,106,107,108,109,110,111,112,113],"compliance","soc2","soc2 compliance","audit evidence","audit","collect","soc","analysis","evidence","trust","build","map","control","type","gap","readiness","gap analysis","assess","for",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":52},"01M6KC461R3GKGZ1TAYHVR1MW9","risk-management-specialist","Medical device risk management specialist implementing ISO 14971 throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use when user mentions risk management, ISO 14971, risk analysis, FMEA, fault tree analysis, hazard identification, risk control, risk matrix, benefit-risk analysis, residual risk, risk acceptability, or post-market risk.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Frisk-management-specialist\u002FSKILL.md",[],[121,122,123,124,125,126,127,128,102,34,129,130,131,132,133,134,135,136,137,138],"risk","risk management specialist","management","risk management","risk evaluation","product","Evaluation","lifecycle","risk matrix","iso","medical","iso 14971","identification","information","post-production","tree","matrix","implementing",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":52},"01M6KC3HF5ZFSSP2NZF68PEPFB","regulatory-affairs-head","Senior Regulatory Affairs Manager for HealthTech and MedTech companies. Prepares FDA 510(k), De Novo, and PMA submission packages; analyzes regulatory pathways for new medical devices; drafts responses to FDA deficiency letters and Notified Body queries; develops CE marking technical documentation under EU MDR 2017\u002F745; coordinates multi-market approval strategies across FDA, EU, Health Canada, PMDA, and NMPA; and maintains regulatory intelligence on evolving standards. Use when users need to plan or execute FDA submissions, navigate 510(k) or PMA approval processes, achieve CE marking, prepare pre-submission meeting materials, write regulatory strategy documents, respond to agency queries, or manage compliance documentation for medical device market access.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Fregulatory-affairs-head\u002FSKILL.md",[],[146,147,148,149,150,151,152,153,154,34,155,156,157,158,159,160,161,162,163,113],"regulatory affairs head","regulatory","head","documents","devices","health","plan","write","strategy","standards","queries","manage","strategies","de","users","respond","medical devices","manager",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":176,"publishedAt":52},"01M6KC34Z8M1559EY1CXYBJB1A","quality-manager-qms-iso13485","ISO 13485 Quality Management System implementation and maintenance for medical device organizations. Provides QMS design, documentation control, internal auditing, CAPA management, and certification support. Use when working with medical device quality systems, preparing for ISO 13485 audits, managing regulatory compliance documentation, setting up corrective actions, or building audit preparation programs. Useful for quality management, audit preparation, regulatory compliance, medical device documentation, and corrective action workflows.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Fquality-manager-qms-iso13485\u002FSKILL.md",[170,173],{"categoryNo":171,"categoryName":172,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":174,"categoryName":175,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000032","设计师",[177,178,163,179,180,181,182,183,184,34,185,186,187,188,189,190,191,192,113,193],"quality manager qms iso13485","quality","design","workflows","validation","actions","certification","system","maintenance","document","systems","records","ISO 13485","organizations","corrective action","internal audit","preparation",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":201,"publishedAt":52},"01M6KC2FXHBHXYX2ZZ17Y3GDB4","quality-manager-qmr","Senior Quality Manager Responsible Person (QMR) for HealthTech and MedTech companies. Provides quality system governance, management review leadership, regulatory compliance oversight, and quality performance monitoring per ISO 13485 Clause 5.5.2.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Fquality-manager-qmr\u002FSKILL.md",[200],{"categoryNo":92,"categoryName":93,"taxonomyType":29,"taxonomyTypeDesc":30},[202,178,163,51,203,204,205,206,95,207,184,208,147,209,210,211,130,189,113,212],"quality manager qmr","policy","performance","governance","monitoring","regulatory compliance","oversight","cost","culture","leadership","person",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":224,"publishedAt":52},"01M6KC1VRR5JTDBNZANHPS6VR6","quality-documentation-manager","Document control system management for medical device QMS. Covers document numbering, version control, change management, and 21 CFR Part 11 compliance. Use for document control procedures, change control workflow, document numbering, version management, electronic signature compliance, or regulatory documentation review.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Fquality-documentation-manager\u002FSKILL.md",[219,222,223],{"categoryNo":220,"categoryName":221,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":92,"categoryName":93,"taxonomyType":29,"taxonomyTypeDesc":30},[225,226,178,163,51,227,228,99,184,229,230,231,232,233,131,234,235,236,237,113],"documentation","quality documentation manager","workflow","change","change management","list","master","system management","documentation review","cfr","21 cfr part 11","change control","retention"]