Loading...
Loading...
Found 2,163 Skills
Use to help users get started with Nemo Gym reward profiling. Covers the basic ng_run, ng_collect_rollouts, and ng_reward_profile workflow, repeated rollouts, materialized inputs, rollout JSONL artifacts, task and rollout identity, output inspection, partial profiling, and rollout_infos. For failed jobs, prefer nemo-gym-debugging.
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-once/cache/launch pattern, per-architecture configs (sm80–sm120), parameter space design (tile sizes, occupancy, num_ctas), and 7 common pitfalls with solutions.
Use when configuring any n8n node: HTTP, webhooks, database, comms (Slack/Gmail/Discord), AI, triggers, Merge, anything. Triggers on any node-builder call (`node(...)`, `trigger(...)`, `tool(...)`, `memory(...)`, `languageModel(...)`, `ifElse(...)`, `merge(...)`, etc.), configuring a parameter, `useDataOfInput`, `numberOfInputs`, fan-in convergence, or any node-specific debugging.
Turn a vague bug report into a VERIFIED minimal reproduction and then a failing regression test, agent-driven end to end. Covers extracting the implicit repro from a thin report (env, build, steps, data), the reproduce-minimize-isolate-capture loop, git bisect to find the introducing commit, building a deterministic minimal repro (fixed seeds, frozen time, stubbed network), writing the failing regression test BEFORE the fix (red) and confirming the fix flips it green, and writing repro evidence back into the ticket. Distinguishes flaky-not-reproducible from environment-specific. Use when: "reproduce this bug," "minimal reproduction," "repro steps," "find the commit that broke it," "git bisect," "make the repro deterministic," "write a failing test for this bug," "regression test for a defect," "can't reproduce this bug." Not for: Classifying/deduplicating/severity-routing existing failures without reproducing them — that is ai-bug-triage. Generating tests from specs rather than from a defect — that is ai-test-generation. Related: ai-bug-triage, ai-test-generation, test-reliability, systematic-debugging, qa-project-context.
Use this skill when writing, fixing, extending, or reviewing OPA5 integration tests for SAP Fiori Elements applications - whether the app uses OData V4 (sap.fe.test library) or OData V2 (fioriElementsTestLibrary). Triggers on any request involving OPA5 journeys, page objects, JourneyRunner setup, test structure, mock data, or debugging test failures in a SAP Fiori Elements project generated by SAP Fiori tools. Use even when the user says "write integration tests" or "add an OPA journey" without specifying the library, as long as the project context is SAP Fiori Elements. Not applicable to freestyle UI5 apps.
This skill should be used when the user asks to "rotate SSH keys", "regenerate SSH keys", "replace SSH keys", "renew SSH keys", or when the agent needs SSH access to a deployed VM for troubleshooting (logs, debugging, database access) but discovers the expected SSH key file is missing from the local disk (e.g. `~/.ssh/<repo-name>` does not exist). Also use when the user mentions "lost SSH key", "SSH key not found", "can't SSH into server", "permission denied SSH", "moved to a new computer", or "cloned repo on another machine".
Set up a structured project memory for any software project — TODO.md as priority/effort-tagged index of future work, backlog/ for resume-friendly research/design notes on P? items, and pitfalls/ as a symptom-grep-able knowledge base of past traps. Use when a user wants somewhere to record "maybe later" ideas, freeze troubleshooting state, capture trade-off analysis, or stop re-debugging the same problem.
A portable, framework-agnostic Lighthouse CI performance-gate system for any web frontend. Enforces Core Web Vitals budgets (LCP, INP via the TBT lab proxy, CLS) and category score floors (performance, SEO, accessibility, best-practices) as a blocking CI check on every pull request. Runs Lighthouse against the production build with median-of-N runs for stability, on mobile emulation by default with an opt-in desktop form factor. Ships a single `lighthouserc.cjs` config, an npm `lhci` script, and a GitHub Actions workflow. Use this skill when adding performance gates to a project, configuring Lighthouse CI, tuning Core Web Vitals budgets, setting category score thresholds, wiring a Lighthouse GitHub Action, or debugging flaky or failing Lighthouse runs. Works with Next.js, Remix, Astro, SvelteKit, Vite, or any app that serves a production build over HTTP.
Logging best practices focused on wide events (canonical log lines) for powerful debugging and analytics
Manages Apache Airflow operations including listing, testing, running, and debugging DAGs, viewing task logs, checking connections and variables, and monitoring system health. Use when working with Airflow DAGs, pipelines, workflows, or tasks, or when the user mentions testing dags, running pipelines, debugging workflows, dag failures, task errors, dag status, pipeline status, list dags, show connections, check variables, or airflow health.
Master iOS testing - XCTest, UI testing, mocking, debugging, performance
Extracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. Stores discoveries in memory (via amplihack.memory.discoveries), suggests PATTERNS.md updates, and recommends new agent creation. Ensures knowledge persists across sessions via Kuzu memory backend.