Loading...
Loading...
Found 1,944 Skills
Run MassGen experiments and analyze logs using automation mode, logfire tracing, and SQL queries. Use this skill for performance analysis, debugging agent behavior, evaluating coordination patterns, and improving the logging structure, or whenever an ANALYSIS_REPORT.md is needed in a log directory.
Software design principles and patterns. This skill should be used when making architectural decisions, designing classes or modules, or evaluating code structure. Use proactively when discussing SOLID principles, coupling, cohesion, connascence, refactoring structure, class design, module boundaries, dependency injection, or the Four Rules of Simple Design. (user)
Comprehensively reviews Python libraries for quality across project structure, packaging, code quality, testing, security, documentation, API design, and CI/CD. Provides actionable feedback and improvement recommendations. Use when evaluating library health, preparing for major releases, or auditing dependencies.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
When the user wants to discover, evaluate, or prioritize App Store keywords. Also use when the user mentions "keyword research", "find keywords", "search volume", "keyword difficulty", "keyword ideas", or "what keywords should I target". For implementing keywords into metadata, see metadata-optimization. For auditing current keyword performance, see aso-audit.
Use this skill when the user doesn't yet know what to test. This is the "learn the site first" step — for unfamiliar websites, new projects, or any situation where Feature/Persona artifacts don't exist yet. Use when the user: gives a URL with no specific test in mind, asks what features or flows a site has, wants to explore or walk through a site, is new to a project, or says "explore before we test". Also use for bare "test [URL]" commands with no further context. Do not use when Feature artifacts already exist or the user references specific known tests or bugs.
Codified expertise for managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, and maintaining strategic carrier relationships. Informed by transportation managers with 15+ years experience. Includes scorecarding frameworks, RFP processes, market intelligence, and compliance vetting. Use when managing carriers, negotiating rates, evaluating carrier performance, or building freight strategies.
Guide for optimizing MSBuild build parallelism and multi-project scheduling. Only activate in MSBuild/.NET build context. Use when builds are not utilizing all CPU cores, when looking to speed up multi-project builds, or when evaluating graph build mode. Covers /maxcpucount, project dependency graphs, graph build (/graph), BuildInParallel, and reducing unnecessary project references.
Proper handling of files generated during the MSBuild's build process. Only activate in MSBuild/.NET build context. Use when generated files are not being included in compilation, output, or when globs aren't capturing generated files. Covers MSBuild evaluation vs execution phases, timing targets to include generated files, and ensuring generated files are tracked for incremental builds and clean.
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
Use this skill when designing AI agent architectures, implementing tool use, building multi-agent systems, or creating agent memory. Triggers on AI agents, tool calling, agent loops, ReAct pattern, multi-agent orchestration, agent memory, planning strategies, agent evaluation, and any task requiring autonomous AI agent design.
Make every number in the final PDF traceable to the exact code line that produced it. Uses \hypertarget/\hyperlink LaTeX commands and \num{formula} evaluated at compile time. Use for reproducibility and data integrity verification.