Loading...
Loading...
Found 258 Skills
Reference skill for Zoom Probe SDK. Use after routing to a preflight workflow when testing browser compatibility, media permissions, audio or video diagnostics, and network readiness before users join.
Guides the agent through the Capgo CLI command surface and routes requests to more specific Capgo skills. Use when the user asks generally about the Capgo CLI, app setup, diagnostics, OTA operations, native builds, or organization commands. Do not use when a more specific Capgo skill already clearly matches the request.
Donella Meadows's System Leverage Points applied to any complex system — company, market, policy, or organization. Spawns a team of specialist agents — System Cartographer, Leverage Diagnostician, Counterintuitive Analyst, Paradigm Archaeologist, Dancing Advisor — who each apply a distinct lens from Meadows's framework to identify where you're wasting effort on low-leverage interventions. The lead synthesizes into a leverage audit: which level you're pushing at, which level you should be pushing at, and whether you're pushing in the right direction. Use when the user says "meadows this", "where's the leverage", "systems analysis", "why isn't this working", or describes a complex system that seems stuck despite effort. Works as a standalone analysis or paired with /munger.
Look up the public API of any JVM dependency (Scala 3, Scala 2, Java) from the terminal — type signatures, members, docs, and source as Markdown, no JAR unpacking needed. Use this skill whenever you need to call an unfamiliar library method, explore a package's types, or check a dependency's API. Prefer cellar over Metals MCP only for looking up external dependency APIs (`cellar get-external` vs Metals `inspect`/`get-docs`) — cellar needs no project import and queries any published Maven artifact. For everything else (references, rename, goto definition, diagnostics, compile), use Metals.
Optimize a Next.js app that has `cacheComponents: true` — either the static shell on first paint, or the in-app navigation between routes. Picks the matching diagnostic loop and runs it.
Creates comprehensive GitHub Actions CI/CD workflows for linting, testing, building, and deploying. Includes caching strategies, matrix builds, artifact handling, and failure diagnostics. Use for "GitHub Actions", "CI pipeline", "workflow automation", or "continuous integration".
Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real `data/` source and predicts on a *disjoint* portion that deliberately carries **no pre-history buffer**. The assertion is structural — the number of predictions must equal the number of rows in the predict grid. A pipeline that loads-then-features-then-splits will silently drop the cold-start rows of the predict slice and the test will fail with a row-count mismatch; a pipeline that marks X early and references upstream history nodes from feature steps will pass trivially. The smoke test is the executable proof of the X-marker placement rule from `build-ml-pipeline`. TRIGGER when: `test-ml-pipeline` has dispatched here to write the smoke test for an approved experiment; `pytest tests/smoke/` is failing on row count; the user asks "why is the smoke test failing?"; a pipeline edit in `build-ml-pipeline` needs an executable proof; an experiment script changes the pipeline shape and the matching smoke test needs revisiting. SKIP when: the design note does not exist or is not yet approved (route to `iterate-ml-experiment`); the user is asking about a regression test or schema invariant (route to `regression-test-ml-pipeline` / `distribution-test-ml-pipeline` once those exist); the question is the *interpretation* of CV metrics, not predict-time correctness (route to `evaluate-ml-pipeline`). HOW TO USE: read the matching experiment's `journal/NN_*.md` and `experiments/NN_*.py` first to understand the pipeline's source binding (what env-dict keys does `build_learner` expect?). Then construct two env-dicts from the **real `data/` source** — a train env and a predict env — such that the predict env carries *only the rows we want predictions for* and *no pre-history buffer*. The hard assertion is that the prediction count matches the predict-env row count exactly. The soft assertion is that the smoke set's MAE is within `3 × CV_mean` (or the task-appropriate analogue). **Do not write the design note or run CV — that's other skills' job.**
Detect and resolve Unity C# compilation errors using VSCode diagnostics. Use this skill when Unity projects have compilation errors that need diagnosis and automated fixes. Analyzes errors from VSCode Language Server, proposes solutions based on error patterns, and handles version control conflicts for Unity projects.
Advanced sub-skill for scikit-learn focused on model interpretability, feature importance, and diagnostic tools. Covers global and local explanations using built-in inspection tools and SHAP/LIME integrations.
Validate Godot GDScript files using gdlint, gdformat, gdradon, and LSP diagnostics. Use when users want to: (1) Check code quality after making changes, (2) Validate before committing, (3) Run code metrics analysis, (4) Run export validation, (5) Get real-time LSP diagnostics. Uses command-line tools directly and MCP tools for LSP integration.
Check production health: Sentry errors, Vercel logs, health endpoints, GitHub CI/CD. Outputs structured findings. Use log-production-issues to create issues. Invoke for: production diagnostics, error audit, health status, CI failures.
Manage Alibaba Cloud Edge Security Acceleration (ESA) via OpenAPI/SDK. Use for site lifecycle management, DNS/record operations, origin and cache rules, WAF/security policy management, and diagnostics/troubleshooting for ESA resources.