Explore skills
Showing 15391–15420 of 22248 skills
代码安全审计 - 漏洞扫描、依赖检查、安全最佳实践
laolaoshiren/claude-code-skills-zh
Stars: 913Claude CodeCodex中文代码审查专家 - 生成详细的中文代码审查报告
laolaoshiren/claude-code-skills-zh
Stars: 913Claude CodeCodexHouse rules and craft for LaTeX Beamer decks (storyboarding, slide prose, frame budgets, layout, XeLaTeX and Korean fonts, color, figures, Overleaf hygiene, build QA). Use to write, edit, review, or build a Beamer deck.
scdenney/open-science-skills
Stars: 70Claude CodeCodexOperate a selective workspace for complex reasoning, long tasks, repository engineering, coordinated agents, and authorized security analysis. Use when work requires durable state, evidence, cross-file consistency, or recovery; keep direct answers lightweight.
Tiger3807861189/J-Space-Cognition-Suite
Stars: 2.9kClaude CodeCodexA skill written the way the whole surface was written before 2026-10-05. The gate must reject it.
plugin87/ux-ui-agent-skills
Stars: 3.1kClaude CodeCodexUse when adding an unspecified data source to an Expo/React Native Power Apps mobile app; routes to Dataverse, SharePoint, or another connector.
microsoft/power-platform-skills
Stars: 1.1kClaude CodeCodexSystem and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexMulti-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexStructured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexStrict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexAutomatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry points, dependencies, and test layout.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexSession-scoped hook lifecycle management with enable/disable/status controls, execution profiling, and color-coded performance alerts.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexFeature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodex6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexMulti-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexDynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexPattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexEvaluation harness for testing agent and skill quality through structured benchmarks, regression tests, and quality scoring.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexPM2 process management, backend/frontend cascade execution, parallel worktree builds, and cross-service integration testing.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexResearch-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs before any implementation begins.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexAgentShield security audit with 5 scanning categories, 102 static analysis rules, and optional red-team simulation.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexRed-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexCreate, track, and land convoys of related beads as primary work orders in the Gas Town multi-agent orchestration framework.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexArchitect code review with DRY, YAGNI, abstraction, and test coverage principle enforcement
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexContext priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexExecute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexDecompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexStructured code quality assessment with Conventional Comments format, scaled review depth, and soft-gating verdicts preserving user autonomy.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexSystematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodexDisciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.
a5c-ai/babysitter
Stars: 1.9kClaude CodeCodex