Browse Secure Claude Skills
Search verified agent skills and review security grades before installing · full A–Z index
- LaravelLaravel 13 best practices: architecture, Eloquent, security, queues, testing, tooling. PHP 8.3+. Use when writing or reviewing Laravel applications.Votes: 0GitHub stars: 54
- Karpathy GuidelinesBehavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.Votes: 0GitHub stars: 54
- Multi Agent Task OrchestratorA production-tested pattern for coordinating multiple AI agents through a single orchestrator. Instead of letting agents work independently (and conflict), one orchestrator decomposes tasks, routes them to specialists, prevents duplicate work, and verifies results before marking anything done.Votes: 0GitHub stars: 2
- Workers Best PracticesReviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.Votes: 0GitHub stars: 2
- Systems Coding StyleWrite and review C, C++, Rust, and low-level systems code with a small, idiomatic, professional style. Use for implementation, refactoring, or review where unnecessary abstraction, allocation, cleverness, or explanatory comments should be avoided.Votes: 0GitHub stars: 2
- Modern CppWrite, review, and modernize C++ with repository-compatible language features, precise interfaces, RAII, explicit ownership, safe concurrency, and measured hardening. Use for C++ implementation, refactoring, API design, or safety review; do not use for pure C or build-system-only work.Votes: 0GitHub stars: 2
- Code StandardsGovern implementation, bug fixes, and refactors from repository orientation through scoped research, planning, evidence-led tests, implementation, review, verification, and handoff. Use for any code change; combine it with the relevant language skill for C, C++, Rust, assembly, or another stack.Votes: 0GitHub stars: 2
- Code Quality Review[Code Quality] Use when evaluating received review feedback, reviewing named code on request, or verifying a completion claim. Current diffs: changes-review; rationale: why-review.Votes: 0GitHub stars: 3
- Code Quality Review[Code Quality] Use when evaluating received review feedback, reviewing named code on request, or verifying a completion claim. Current diffs: changes-review; rationale: why-review.Votes: 0GitHub stars: 3
- Praxis WatchUse when the user wants one background session watching both the PR review-request channel and their assigned tickets — "lance la veille", "/loop /praxis-watch", "surveille les PR et mes tickets". One pass per invocation, designed for /loop. Do NOT use for a single watcher on demand (/praxis-watch-prs, /praxis-watch-tickets).Votes: 0GitHub stars: 3
- Praxis TddUse when implementing any feature or bugfix with strict baby-steps TDD - enforces minimal code and mandatory checkpointsVotes: 0GitHub stars: 3
- Praxis ReviewUniversal code review - auto-detects scope from git changes, spec, commit, or brief. Use after completing tasks, implementing major features, before merging, when stuck (fresh perspective), before refactoring (baseline check), or after fixing complex bugs.Votes: 0GitHub stars: 3
- Jev Model RouterUse `jev_route_model` when more than one available model could perform the task and the choice materially affects quality, cost, or latency.Votes: 0GitHub stars: 17
- Ponytail ReviewCode review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.Votes: 0GitHub stars: 17
- Plan ArbiterUse when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommended execution plan after agents review each other's proposals.Votes: 0GitHub stars: 17
- Code ReviewerElite code review expert specializing in modern AI-powered codeVotes: 0GitHub stars: 8
- Updating DependenciesUpdating catalog dependencies to latest minor/patch versionsVotes: 0GitHub stars: 9
- 50 Security Best PracticesUse when 安全编码最佳实践，CodeQL/Semgrep 集成 - 驱动代码安全审计、内核模块漏洞扫描。Votes: 0GitHub stars: 2
- 34 Receiving Code ReviewUse when 接收代码审查反馈 - 处理内核邮件列表 review 意见、GitHub PR review。Votes: 0GitHub stars: 2
- 33 Requesting Code ReviewUse when 请求代码审查 - 补丁提交前自查、驱动代码合并前验证。Votes: 0GitHub stars: 2