Latest Agent Skills

**Structure:**

Comprehensive process for discovering and validating data model requirements before design

A runbook written in a wiki decays silently: the dashboard is renamed, the

Cardinality and model family jointly determine the encoding.

Three shapes get argued about as if one were correct.

Comprehensive guidelines for when and how to use mocks, stubs, and fakes in tests

Apply Arrange-Act-Assert pattern for clear, maintainable tests with detailed guidance

Ownership models are usually inherited rather than chosen, and the inherited one

**SLO (Service Level Objective):** What we promise (99.9%)

State is the map between your code and real resources.

"Quality" is unmanageable until it is a set of numbers with agreed definitions.

**Monthly Partitions:**

Always start with EXPLAIN ANALYZE to understand execution:

Line coverage answers "did this line execute during the test run".

The layers trade timeliness against definitiveness.

Every metric encodes an opinion about which mistake hurts.

Plan before implementing - understand scope and approach with detailed guidance

Expected error decomposes into bias, variance, and irreducible noise.

Least privilege is easy to state and hard to hold: grant each identity only the

Every methodology — STRIDE, PASTA, LINDDUN, attack trees — is a technique for

The central pattern.

A model in production is never just weights.

Most teams run one test — expected peak for ten minutes — and believe they have

An API has no UI to hide things behind.

Founder onboarding interview that captures company context across 7 dimensions. Invoke with /cs:setup for initial interview or /cs:update for quarterly refresh. Generates ~/.claude/company-context.md used by all C-suite advisor skills.

The meta-framework for how a company runs — the connective tissue between all C-suite roles. Covers operating system selection (EOS, Scaling Up, OKR-native, hybrid), accountability charts, scorecards, meeting pulse, issue resolution, and 90-day rocks. Use when setting up company operations, selecting a management framework, designing meeting rhythms, building accountability systems, implementing OKRs, or when user mentions EOS, Scaling Up, operating system, L10 meetings, rocks, scorecard, accountability chart, or quarterly planning.

Routes tasks to locally installed CLI tools using semantic matching. Triggers on tasks requiring shell commands, file operations, code search, data processing, visualization, or external tool invocation. Uses cli-index for semantic routing.

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

This skill should be used when working with BMAD (BMad-CORE) v6-alpha projects. BMAD is a universal human-AI collaboration platform with specialized modules for software development (BMM), agent building (BMB), creative intelligence (CIS), and project management (BMD). Use this skill to understand agent workflows, command patterns, scale-adaptive methodology, and effective utilization of the four-phase development system.

Systematic API design methodology with 6 validated patterns covering parameter categorization, safe refactoring, audit-first approach, automated validation, quality gates, and example-driven documentation. Use when designing new APIs, improving API consistency, implementing breaking change policies, or building API quality enforcement. Provides deterministic decision trees (5-tier parameter system), validation tool architecture, pre-commit hook patterns. Validated with 82.5% cross-domain transferability, 37.5% efficiency gains through audit-first refactoring.

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

uv Python package manager — fast pip/venv replacement. Use when creating virtual environments, installing packages, managing dependencies, or running Python scripts with uv.

Metasuperhypergraph orchestrator with fractal scale-invariant recursion. Activates maximum performance mode through renormalization-group optimization, power-law resource allocation, and homoiconic self-improvement. Triggers on "ultrawork", complex multi-domain tasks, or when parallelization/delegation yields superlinear returns.

Scan, prioritize, and report technical debt. Usage: /tech-debt <scan|prioritize|report> [options]

Transform diverse inputs (YouTube videos/audio, existing Suno songs, raw lyrics, audio files, or conversational ideas) into highly optimized Suno V5 custom song generation prompts with intelligent character optimization (5000 lyrics, 1000 style limits), proven metatag reliability, V5-enhanced emotion tags, and template-based best practices. Use when user wants to create music with Suno, provides content for song generation, or needs help crafting effective V5 prompts.

Starlette 1.0 ASGI framework reference with working code examples for every feature. Use this skill whenever writing Starlette applications, building ASGI middleware, working with FastAPI internals, or writing async Python web services. Also trigger when the user mentions Starlette, ASGI, or needs help with routing, WebSockets, middleware, lifespan handlers, or test clients in the Starlette ecosystem — even if they don't name Starlette explicitly but are clearly working with it (e.g., importing from starlette.*, using TestClient with httpx, or writing ASGI scope/ receive/send functions). Covers the 1.0 API exclusively — all deprecated 0.x patterns have been removed.

Generates unit tests, integration tests, and E2E tests for React/Next.js applications. Scans components to create Jest + React Testing Library test stubs, analyzes Istanbul/LCOV coverage reports to surface gaps, scaffolds Playwright test files from Next.js routes, mocks API calls with MSW, creates test fixtures, and configures test runners. Use when the user asks to "generate tests", "write unit tests", "analyze test coverage", "scaffold E2E tests", "set up Playwright", "configure Jest", "implement testing patterns", or "improve test quality".

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.

Hard Call

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Specialized AI assistant for DSPy development with deep knowledge of predictors, optimizers, adapters, and GEPA integration. Provides session management, codebase indexing, and command-based workflows.

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

Generate syntactically correct Claude Code configuration components (commands, subagents, skills, output styles) with optimal cross-component integration. Triggers on requests to create slash commands, agents, subagents, skills, output styles, Claude Code plugins, agentic workflows, or multi-agent pipelines. Ensures parameter validity per component type and semantic coherence across component references.

Generate changelogs from git history and validate conventional commits. Usage: /changelog <generate|lint> [options]

Challenge

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".

Performance baseline measurement and regression detection. Use when measuring perf before/after a PR, setting up baselines, investigating "feels slow" reports, validating launch performance targets, or comparing your stack against alternatives.

Run three agents as a newsroom — a Writer, an Editor, and a Fact-checker — that draft, critique, and verify in parallel and argue until the writing survives with zero flags. This is the level above a single self-review loop, for the pieces that matter most. Best run in Claude Cowork against the user's files. Use for high-stakes writing the user wants bulletproof: a newsletter, a launch post, a client email, a public announcement. Trigger whenever the user says 'run the team', 'use the swarm', 'writer editor fact-checker', 'spawn agents to work on this', or wants the strongest possible version of a piece. For a lighter single-agent loop, use red-pen instead.

Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.

Sync tests with TestRail. Use when user mentions "testrail", "test management", "test cases", "test run", "sync test cases", "push results to testrail", or "import from testrail".

Unified content extraction and action planning. Use when user says `tapestry [URL]`, `weave [URL]`, `help me plan [URL]`, `extract and plan [URL]`, `make this actionable [URL]`, or similar phrases indicating they want to extract content and create an action plan. Automatically detects content type (YouTube video, article, PDF) and processes accordingly.

Multi-source comprehensive research using perplexity-researcher, claude-researcher, and gemini-researcher agents. Three modes - Quick (3 agents), Standard (9 agents), Extensive (24 agents with be-creative skill). USE WHEN user says 'do research', 'quick research', 'extensive research', 'find information about', 'investigate', 'analyze trends', 'current events', or any research-related request.

Codebase-wide Retrieval-Augmented Generation for deep code understanding. Use when: (1) Answering questions about large codebases by searching across all files, (2) Finding related code patterns, implementations, or dependencies across a project, (3) Building context from multiple files before making changes, (4) Understanding how a feature works end-to-end across the codebase, (5) Tracing data flow through multiple modules

Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture.

Meta-cognitive architecture optimization skill. Use when the user asks to "refactor the architecture", "optimize claude code", "evaluate components", or "run architecture audit". Also triggers automatically every 24 hours.

Detect stack and generate CI/CD pipeline configs. Usage: /pipeline <detect|generate> [options]

This skill should be used when working with Obsidian files including .md notes with wikilinks/callouts/properties, .base database views with filters/formulas, or .canvas visual diagrams. Routes to specialized sub-skills based on file type and task context. Features self-iterative learning that improves with use.

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

Interview the user with 10-15 targeted questions BEFORE building anything, then confirm a short spec, then build. Use this skill whenever the user asks Claude to build, create, make, code, design, draft, or generate anything non-trivial — an app, website, script, tool, document, presentation, campaign, plan, or system — even if the request looks detailed enough to start immediately. Especially trigger on vague one-line build requests like "make me a dashboard" or "build an app for my gym". Do NOT use for pure questions, explanations, debugging existing code, tiny edits, or reformatting.

Generate Playwright tests. Use when user says "write tests", "generate tests", "add tests for", "test this component", "e2e test", "create test for", "test this page", or "test this feature".