cdf-simulation
Component-owned guidance for CDF Simulation requests submitted directly or through Airflow-triggered DIG Flow Catalog prompts — golden THT board, THT…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
Testing & quality
12,901 results
tripy-debugging
Debug and diagnose errors in nvtripy code. Use when: interpreting TripyException stack traces, enabling MLIR/TensorRT debug output, understanding error…
gitnexus-debugging
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?",…
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration,…
model-selection
Choose which model tier to spend on a piece of work — the most capable model (Fable 5 / Opus) versus a cheaper, faster one — so quality holds where it matters…
1k-debug-logging
Add or clean temporary OneKey debug console logs with consistent prefixes and safe stringify. Excludes analytics and permanent server logs.
1k-ui-verify
Drive OneKey desktop or mobile apps to verify real visual and interactive behavior using CDP/Playwright or agent-device. Use for UI verification or screenshot…
om-smart-test
Run only the tests affected by changed code. Use when the user says "run affected tests", "run smart tests", "test only what changed", "run tests for this PR",…
integration-tests
Run the packaged OpenAI Agents Python SDK integration tests from clean wheel and source-distribution environments. Use for release readiness, live OpenAI…
code-review
Reviews code changes using CodeRabbit AI. Use when user asks for code review, PR feedback, code quality checks, security issues, or requests fix-review cycles.
vercel-flags
Vercel Flags guidance — feature flags platform with unified dashboard, Flags Explorer, gradual rollouts, A/B testing, and provider adapters. Use when…
convex-test
Generate convex-test tests for the app's Convex functions.
convex-verify
Prove a Convex feature works — seed, drive as multiple mocked users via convex-test, assert behavior including the negative authz cases (wrong user refused,…
openclaw-test-audit
Audit or remove low-value, implementation-coupled, or duplicative OpenClaw tests and simplify test-only seams.
investigate-ci-failure
Investigate CI/Prow job failures on a GitHub pull request. Use when the user pastes a PR URL and asks about CI failures, red checks, test failures, or wants to…
safe-code-change
After a code change, find affected tests, update them to match new behavior, then run the full validation pipeline once. Use when the user has made or asked…
validate-and-fix
Run the full validation pipeline (make test-unit, make verify, make test-integration) and auto-fix trivial failures like black formatting, unused imports, and…
ov-debug-matcher-pass
Debug why an OpenVINO MatcherPass transformation is not firing. Use this skill immediately when a user says a transformation is "not applied", a "pass has no…
ov-transformation-tests
Write unit tests for OpenVINO ov::Model graph transformations (passes). Use when the user asks to write, add, or refactor tests for a transformation pass…
ov-update-pytorch-version
Upgrade the PyTorch version used by OpenVINO tests (torch / torchvision / torchaudio) and resolve fallout — missing operator translators, new functionalized…
lead-scoring
Activate for: lead score, score this lead, qualify, qualification, lead quality, ICP match, fit score, should we pursue, is this a good lead, lead tier, hot…
interrogate
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".…
principle-prove-it-works
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy,…
tdd
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the…