Skill reviews

Google Workspace administration via the gws CLI (github.com/googleworkspace/cli). Install, authenticate, and automate Gmail, Drive, Sheets, Calendar, Docs, Chat, and Tasks. Run sec

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (10 tags): a typed call is more reliable

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutio

• References files that are not bundled: engineering-team/playwright-pro/
• 1 referenced file(s) missing: engineering-team/playwright-pro/
• Does not say what the result is

Company Architect: builds a business from scratch as an OKF (Open Knowledge Format) bundle — a tree of version-controllable .md files with frontmatter type, links forming a graph,

• References files that are not bundled: ../00-fundacao/identidade.md
• 1 referenced file(s) missing: ../00-fundacao/identidade.md
• Does not say what the process needs to start

Code review through the lens of real engineers' documented philosophies (Torvalds, Thompson, Carmack, Kent Beck, Jobs, Cagan). Complements abstract-role adversarial review with nam

• References files that are not bundled: ../adversarial-reviewer/SKILL.md, ../code-reviewer/SKILL.md, ../senior-security/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill

PreToolUse security-anti-pattern hook for Claude Code. Catches 12 common security risks (command injection, XSS, SQL injection, unsafe deserialization, GitHub Actions workflow inje

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (4 tags): a typed call is more reliable

Audits and designs iOS/macOS/watchOS/visionOS interfaces against the Apple Human Interface Guidelines, including the Liquid Glass design language (announced WWDC25, shipped with iO

• Does not say what the result is
• No condition that starts the skill

Creates demand generation campaigns, optimizes paid ad spend across LinkedIn, Google, and Meta, develops SEO strategies, and structures partnership programs. Use when planning dema

• 13 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run

• References files that are not bundled: ../../references/cma-primitives.md, ../../references/loops-and-workflows.md
• 2 referenced file(s) missing: ../../references/cma-primitives.md, ../../references/loops-and-workflows.md
• Does not say what the result is

Generate Playwright tests. Use when user says "write tests", "generate tests", "add tests for", "test this component", "e2e test", "create test for", "test this page", or "test thi

• References files that are not bundled: templates/crud/, templates/checkout/, templates/search/
• 9 referenced file(s) missing: templates/crud/, templates/checkout/, templates/search/
• 5 mutating operations with no state check

Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says "/

• Does not say what the result is
• No condition that starts the skill

Design AWS architectures for startups using serverless patterns and IaC templates. Use when asked to design serverless architecture, create CloudFormation templates, optimize AWS c

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• 7 mutating operations with no state check

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.

• References files that are not bundled: REFERENCE.md
• 1 referenced file(s) missing: REFERENCE.md
• Does not say what the result is

ISO 13485 Quality Management System implementation and maintenance for medical device organizations. Provides QMS design, documentation control, internal auditing, CAPA management,

• References files that are not bundled: ../quality-manager-qmr/, ../capa-officer/, ../qms-audit-expert/
• 10 top-level sections: this looks like several domains in one skill
• 5 referenced file(s) missing: ../quality-manager-qmr/, ../capa-officer/, ../qms-audit-expert/

Router/index for the 4 business & growth skills bundled in this plugin: customer-success-manager (health scoring, churn risk, expansion), sales-engineer (RFP analysis, competitive

• Does not say what the result is
• No condition that starts the skill

App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and G

• References files that are not bundled: ../content-creator/, ../marketing-demand-acquisition/, ../marketing-strategy-pmm/
• 12 top-level sections: this looks like several domains in one skill
• 3 referenced file(s) missing: ../content-creator/, ../marketing-demand-acquisition/, ../marketing-strategy-pmm/

Use when the user asks to perform security audits, penetration testing, vulnerability scanning, OWASP Top 10 checks, or offensive security assessments. Covers static analysis, depe

• References files that are not bundled: ../senior-secops/SKILL.md, ../senior-security/SKILL.md, engineering/skills/dependency-auditor/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill

Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-

• References files that are not bundled: ../../DESIGN.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 1 referenced file(s) missing: ../../DESIGN.md

Medical device risk management specialist implementing ISO 14971 throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production informatio

• References files that are not bundled: ../quality-manager-qms-iso13485/, ../capa-officer/, ../regulatory-affairs-head/
• 10 top-level sections: this looks like several domains in one skill
• 4 referenced file(s) missing: ../quality-manager-qms-iso13485/, ../capa-officer/, ../regulatory-affairs-head/

Reverse-engineer any codebase into a complete Product Requirements Document (PRD). Analyzes routes, components, state management, API integrations, and user interactions to produce

• References files that are not bundled: pages/01-user-mgmt-list.md
• 13 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: pages/01-user-mgmt-list.md

Index of the engineering-team skills bundle for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, da

• Does not say what the result is
• No condition that starts the skill

Comprehensive incident response framework from detection through resolution and post-incident review. Battle-tested SRE/DevOps practices: severity classification, timeline reconstr

• Does not say what the result is
• No condition that starts the skill

Use when a Head of People Ops, BizOps lead, or Internal Communications owner needs to draft and sequence an internal-only change-management communication — a re-org announcement, a

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

/cs:compliance-readiness <program> — Multi-framework compliance officer 6-question forcing interrogation of any compliance program. Use before starting a new framework, planning th

• References files that are not bundled: ../../agents/cs-compliance-officer.md, ../compliance-os/SKILL.md
• 2 referenced file(s) missing: ../../agents/cs-compliance-officer.md, ../compliance-os/SKILL.md
• No condition that starts the skill

Use when a security incident has been detected or declared and needs classification, triage, escalation path determination, and forensic evidence collection. Covers SEV1-SEV4 class

• References files that are not bundled: ../threat-detection/SKILL.md, ../cloud-security/SKILL.md, ../red-team/SKILL.md
• 12 top-level sections: this looks like several domains in one skill
• 4 referenced file(s) missing: ../threat-detection/SKILL.md, ../cloud-security/SKILL.md, ../red-team/SKILL.md

Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git r

• Does not say what the result is
• No condition that starts the skill