Use when an agent, prompt, model or tool change needs proof it did not make the agent worse — setting up a regression eval suite, deciding whether a pass-rate drop is real or noise, grading tool-call trajectories, finding flaky eval cases, or wiring an eval gate into CI that blocks the merge. Runs repeated trials, reports pass@k and pass^k, compares candidate to baseline with paired statistics, and refuses to pass a dropped case, a critical-case regression, or a forbidden tool call.

Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.

Use when designing, reviewing, or paying for an agent memory system — adding memory to an agent, choosing between long-context / RAG / graph / agentic memory, auditing what a CLAUDE.md or memory directory actually holds, deciding what to keep and what to expire, or when a memory store keeps growing and nobody has said what leaves it. Prices the write path, picks which cost to pay, classifies records as facts / skills / logs, and refuses a design that has no forgetting policy.

Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).

OpenTelemetry Transformation Language (OTTL) expert for writing and debugging telemetry transformations in the OpenTelemetry Collector. Use when authoring or reviewing `transform`, `filter`, `tail_sampling` processor configs or `routing` connector configs, debugging OTTL syntax or semantics, transforming traces, metrics, logs, or profiles, or converting data-processing requirements into OTTL statements.

Review Langfuse changes for SSRF, tenant isolation, secret handling, unsafe redirects or uploads, RBAC drift, and client telemetry privacy. Use when a design or change accepts URLs or host fields, handles secrets or cross-tenant data, makes outbound requests, adds an integration, follows redirects, widens permissions, or can send customer-controlled UI data through analytics, monitoring, or session replay.

Integrate LaunchDarkly qualitative user feedback into a JavaScript/TypeScript codebase. Guides framework and design system detection, builds the sendFeedback utility and feedback widget matching existing project patterns. Use when the user wants to add a Give Feedback widget, collect user sentiment tied to feature flags, set up feedback collection, or wire up the $ld:feedback tracking event.

[02] META. Create new skills when existing ones don't cover the task. Analyze unique requirements, build framework (Frame → Research → Plan → Execute), integrate risks, and declare new skill. Use when facing novel problems that existing skills can't address.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Re-explain the previous assistant message, or any text typed after the command, in a much simpler way. For when a reply made you go 'bro what'. Use /bro for a plain-language version of the last answer, or /bro <text> to simplify a pasted paragraph, error, email, or doc.

Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.

Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.

Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

UiPath Integration Service connector authoring (REST+JSON) on disk via `uip is connectors builder`. Triggers on `element.json`, `element-metadata.json`, `standard-resources/*.json`, a `periodic-uipath-*`/`periodic-design-*` connector repo, or any request to build/edit an IS connector: init the connector shell, configure auth (19 types via `auth set`, incl. jwtOauth claims, FPS, none), add activities with fields/params/methods/hooks, wire polling/webhook triggers, add auth-system resources, inspect, validate, and surgically read/write files via state. Import + publish live on the parent `uip is connectors` (need `uip login`). NOT for operating a published connector — connections, ping, run an activity→uipath-platform; NOT for `.flow` connector nodes→uipath-maestro-flow.

Learn my brand once and stop asking me every time. Use when someone says learn my brand, set up my brand, here's our brand book, remember how we talk, what can we claim, can we say this, approve our claims, sign off our voice, our price or product changed, the client approved the claims, pick up where we left off, or check our claims are still current. Reads what GooseWorks already found about the brand, asks only the gaps as drafts to confirm, audits every claim (including ones research marked approved) and gets the ones that matter signed off with proof, scope and review date, turns the voice into rules the owner confirms, checks logo, colours and fonts, and saves it all as it goes so every other job loads it instead of asking. Ends with an unknowns list and a read-back. Not for who our customers are and what they say (use research-audience) or writing positioning from scratch (not covered yet).

Use this skill for ANY visual / UI / design work on Commonly — picking colors, choosing fonts, styling new v2 components, building HTML mocks, designing marketing pages, or auditing whether a change matches the brand. Triggers on tasks involving v2.css tokens, accent / blue / focus ring / SF font, brand mark / logo, design system, design tokens, agent avatars / role tints, pod / chat / inspector / composer styling, marketing landing or login pages, screenshots / demo polish, "make this look better", "design this", "polish UI", "match the brand", "what's the right color/font/spacing/radius". Sources of truth live at `frontend/design-system/` (tokens.css, README.md, brand mark SVG, preview cards) and `frontend/src/v2/v2.css` (production tokens). Read both before recommending or shipping anything.

List recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they need to find a specific meeting by browsing rather than searching.

List recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they need to find a specific meeting by browsing rather than searching.

Test REST, GraphQL, and webhook APIs for contract conformance, input fuzzing, error semantics, idempotency, pagination, and rate limits using schema-driven and property-based tools. Use when an app exposes or consumes APIs or webhooks.