Agent Skills Standard for Codex

Skills (200)

• caveman-commit — Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message"…
• caveman-compress — Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as…
• caveman-review — Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes…
• caveman — Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode"…
• battle-test — Deep audit of a skills directory against the Skill Creator standard. Produces a scored report and phased remediation plan.
• brainstorm-feature — SDLC intake that turns a rough idea into an approved BRD-lite brief (Why lane) or delivery contract (Direction lane) at docs/brd/brd-[slug].md, sized by SNC tier.
• code-review — Run an AI-assisted PR or diff code review using multi-layer lenses with confidence scoring.
• codebase-review — Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.
• cyber-exercise — Run a bounded cybersecurity exercise workflow with authorization, runtime, control, evidence, and independent adjudication gates; supports safe offline planning and optional isolated lab validation.
• cyber-purple-validation — Controlled purple validation using paired action-observation evidence, explicit defensive outcomes, and optional isolated lab routing.
• cyber-triage — Evidence-led blue incident triage with authorization, runtime gates, and optional isolated lab retest handoff.
• deploy-release — Dispatch provider-neutral cloud operations and verify staged or production releases with rollback and smoke checks.
• design-solution — Turn an approved PRD or implementation goal into SRS/FRS technical requirements (How), architecture, contracts, and verification decisions.
• dev-fix — Unified developer workflow for fixing bugs. Analyzes issue-tracker context, cross-checks docs/code, proposes a solution, implements the fix, verifies locally, and delivers a PR/MR.
• evals-run — Workflow skill for evals run.
• implement-feature — Implement an approved feature plan with benefit-based placement, TDD, revision-bound evidence, and PR-ready output.
• implementation-readiness — Verify BRD-lite, PRD, SRS/FRS, UX, and test prerequisites before implementation starts.
• incident-hotfix — Mitigate a production incident or urgent regression first, then route to root-cause remediation and a postmortem.
• marketing-campaign — Plan, govern, and measure developer marketing campaigns using evidence-led contracts, explicit capacity bounds, and host authorization gates.
• monitor-respond — Turn a control-band breach or scheduled scan result into a tiered, evidence-backed response and a routed intake.
• pentest — PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.
• plan-feature — Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.
• publish-notes — Draft user-facing release notes, store changelogs, and internal publish summaries.
• retro-learn — Convert delivery findings into skill, eval, workflow, and documentation improvements.
• review-system-design — Review a system design someone else provided - screenshot, drawio, Mermaid, slides, doc, or IaC - by extracting it into a confirmed fact sheet, then scoring it on the nine axes.
• sdlc — Route a task to the next synced SDLC workflow based on current artifacts and repo state.
• security-test
• session-report
• skill-benchmark
• system-design-session
• test-loop
• traceability-audit
• uat-signoff
• update-docs
• verify-bug
• verify-work
• zephyr-coverage-analysis
• android-agp-upgrade
• android-architecture
• android-background-work
• android-compose-migration
• android-compose
• android-concurrency
• android-deployment
• android-design-system
• android-di
• android-edge-to-edge
• android-legacy-navigation
• android-legacy-security
• android-legacy-state
• android-navigation-3
• android-navigation-type-safe
• android-navigation
• android-networking
• android-notifications
• android-performance
• android-persistence
• android-resources
• android-security
• android-state
• android-testing
• android-tooling
• android-xml-views
• angular-architecture
• angular-components
• angular-dependency-injection
• angular-directives-pipes
• angular-forms
• angular-http-client
• angular-performance
• angular-routing
• angular-rxjs-interop
• angular-security
• angular-ssr
• angular-state-management
• angular-style-guide
• angular-testing
• angular-tooling
• common-accessibility
• common-agent-guardrails
• common-api-design
• common-architecture-audit
• common-architecture-diagramming
• common-best-practices
• common-book-to-skill
• common-code-review
• common-context-optimization
• common-dast-tooling
• common-debugging
• common-decision-discipline
• common-devops-operations
• common-documentation
• common-error-handling
• common-exploit-verification
• common-family-ux
• common-feedback-reporter
• common-git-collaboration
• common-learning-log
• common-llm-security
• common-mobile-animation
• common-mobile-ux-core
• common-mobile-visual-testing
• common-observability
• common-operator-profile
• common-owasp
• common-pentest-methodology
• common-performance-engineering
• common-protocol-enforcement
• common-review-policy
• common-sdlc-metrics
• common-security-audit
• common-security-standards
• common-session-retrospective
• common-skill-creator
• common-software-requirements
• common-stitch-design
• common-store-changelog
• common-subagent-driven-development
• common-task-complexity-routing
• common-tdd
• common-telemetry
• common-ui-design
• common-web-visual-testing
• common-workflow-writing
• cyber-authorization
• cyber-detection-engineering
• cyber-detection-validation
• cyber-engagement-planning
• cyber-evidence
• cyber-exercise-adjudication
• cyber-exercise-control
• cyber-framework-mapping
• cyber-incident-triage
• cyber-lab-validation
• cyber-scoped-validation
• cyber-threat-hunting
• dart-best-practices
• dart-language
• dart-tooling
• database-hana
• database-migrations
• database-mongodb
• database-postgresql
• database-query-performance
• database-redis
• database-schema-design
• database-transactions
• flutter-auto-route-navigation
• flutter-bloc-state-management
• flutter-cicd
• flutter-concurrency
• flutter-dependency-injection
• flutter-design-system
• flutter-error-handling
• flutter-feature-based-clean-architecture
• flutter-getx-navigation
• flutter-getx-state-management
• flutter-go-router-navigation
• flutter-idiomatic-flutter
• flutter-layer-based-clean-architecture
• flutter-localization
• flutter-navigation
• flutter-notifications
• flutter-performance
• flutter-retrofit-networking
• flutter-riverpod-state-management
• flutter-security
• flutter-testing
• flutter-widgets
• golang-api-server
• golang-architecture
• golang-concurrency
• golang-configuration
• golang-database
• golang-error-handling
• golang-language
• golang-logging
• golang-security
• golang-testing
• golang-tooling
• ios-app-lifecycle
• ios-architecture
• ios-dependency-injection
• ios-deployment
• ios-design-system
• ios-localization
• ios-navigation
• ios-networking
• ios-notifications
• ios-performance
• ios-persistence
• ios-security
• ios-state-management
• ios-swiftui
• ios-ui-navigation
• java-best-practices
• java-concurrency
• java-language
• java-testing
• java-tooling