Loading...
Loading...
Found 286 Skills
The drum sounds. Bloodhound, Elephant, Turtle, Beaver, Raccoon, Deer, Fox, and Owl gather for complete feature development. Use when building a full feature from exploration to documentation — secure by design.
Manual QA testing — verify features end-to-end as a user would, using every tool available (browser, macOS, bash, APIs). Focuses on what formal test suites cannot capture: visual correctness, UX flows, usability judgment, integration reality, edge cases, and failure modes. Standalone or composable with /ship. Triggers: qa, qa test, manual test, test the feature, verify it works, exploratory testing, smoke test, end-to-end verification.
Safe experimentation framework for AI agents. Creates isolated sandbox environments for trying new features, testing approaches, and exploring solutions without polluting the main codebase. USE WHEN: Agent needs to try something uncertain, explore multiple approaches, test a new library, prototype a feature, or run a technical spike before committing to implementation. PRIMARY TRIGGERS: "experiment with" = Setup sandbox + run experiment "try this approach" = Quick experiment in sandbox "spike" / "POC" / "prototype" = Time-boxed technical investigation "tinker" / "tinkering mode" = Enter experimentation workflow "explore options" = Multi-approach comparison in sandbox NOT FOR: Debugging (use debugger), testing (use test runner), or committed feature work (use git branches). DIFFERENTIATOR: Unlike git branches (for committed direction), tinkering is for "I don't know if this will work" exploration. Try 5 things in sandbox before committing to a branch. Faster feedback, zero codebase pollution.
Exploratory Data Analysis (EDA): profiling, visualization, correlation analysis, and data quality checks. Use when understanding dataset structure, distributions, relationships, or preparing for feature engineering and modeling.
Orchestrate copy exploration. Brief, generate 5 distinct approaches, adversarial review, iterate to 90+ composite, present catalog, user selects, execute.
Generate beautiful wedding invitations, save the dates, RSVP cards, and wedding programs using each::sense AI. Create classic, modern, floral, rustic, destination, and cultural wedding stationery designs.
Knowledge base for designing, reviewing, and linting agentic AI infrastructure. Use when: (1) designing a new agentic system and need to choose patterns, (2) reviewing an existing agentic architecture ADR or design doc for gaps/risks, (3) applying the lint script to an ADR markdown file to get structured findings, (4) looking up a specific agentic pattern (prompt chaining, routing, parallelization, reflection, tool use, planning, multi-agent collaboration, memory management, learning/adaptation, MCP, goal setting, exception handling, HITL, RAG, A2A, resource optimization, reasoning techniques, guardrails, evaluation, prioritization, exploration/discovery). All rules and guidance are grounded in the PDF "Agentic Design Patterns" (482 pages).
External research workflow for docs, web, APIs - NOT codebase exploration
8-agent QA loop: browser exploration via Playwright MCP, then analyze, plan, test, audit, heal, expand, snapshot. Quality gate score >= 85 to pass.
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
Use this for exploratory data analysis (EDA), generating visualizations, finding trends, and deriving insights from datasets using Python (Pandas/Seaborn/Plotly) or SQL.
Intelligent Retrieval Assistant for Cangjie Language Documentation. Supports 4 search modes (Direct Search, PageIndex Intelligent Retrieval, Hybrid Mode, Exploratory Learning). It is used when users need to: (1) Query Cangjie syntax (variable declaration, function definition, generics, etc.), (2) Look up standard library APIs (String, Array, HashMap, etc.), (3) Learn about Cangjie features or get started with the language, (4) Conduct any documentation queries related to Cangjie/cangjie/cj. It uses four MCP tools: cangjie_docs_overview, cangjie_list_docs, cangjie_search, and cangjie_get_doc for intelligent retrieval.