Loading...
Loading...
Found 3,904 Skills
Use when given a GitHub issue URL or number to investigate and implement a fix. Triggers on "fix issue", "fix bug", "fix
When the user wants to design, test, or optimize their app's paywall — layout, copy, pricing display, trial offers, plan structure, hard vs soft paywall, paywall placement, or paywall A/B tests. Use when the user mentions "paywall", "paywall design", "paywall conversion", "trial-to-paid", "soft paywall", "hard paywall", "paywall A/B test", "paywall copy", "plan picker", "annual vs monthly display", "best paywall", "RevenueCat paywall", "Superwall", "Adapty", or "my paywall isn't converting". For overall pricing strategy and monetization model choice, see monetization-strategy. For trial nurture, dunning, and churn, see subscription-lifecycle. For where in the onboarding the paywall fires, see onboarding-optimization.
Everything you need to know to build, test and review Home Assistant Integrations. If you're looking at an integration, you must use this as your primary reference.
Use when symfony tdd with phpunit
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally sniff the source site for new endpoints). Confirms scope with the user, plans + executes the fix autonomously, scrubs PII, and opens a PR against mvanhorn/printing-press-library. Two user-in-loop checkpoints: scope after capture, PR draft before open. Trigger phrases: "amend the CLI", "submit a patch", "fix what I just dogfooded", "open a PR for this CLI", "patch this CLI", "add features to my CLI", "rename this command", "add these feeds to <cli>", "sniff for new APIs in <cli>", "amend with these ideas", "use printing-press-amend", "run printing-press-amend".
Orchestrate fixing a bug — reproduce it as a failing regression test, fix to green, review, and gated commit — by delegating each phase to the matching ECC agent. Use when existing behavior is broken or wrong.
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
Use when the user wants to measure or set up evals/checks for one of their skills — how fast it is, whether its output is valid, whether it fires when expected, or whether its opening classification/routing gate labels inputs correctly.
Measures the task accuracy of text models served by MAX using standard benchmarks such as GSM8K, MMLU, HellaSwag, ARC, AIME, GPQA, TruthfulQA, WinoGrande, and BABILong. Use when benchmarking a served model, comparing it with model-card or reference scores, verifying that a new MAX model produces correct answers, or running repeatable dataset evaluations against a MAX OpenAI-compatible endpoint.
Benchmark a model served on MAX with the `max benchmark` command: measure throughput (tokens/sec), latency (TTFT, TPOT, inter-token latency), and GPU utilization by driving load against a running `max serve` endpoint. Use this whenever the user wants to benchmark, load-test, or measure the performance of a MAX model, get tokens-per-second / TTFT / TPOT numbers, run a concurrency or request-rate sweep, compare latency vs throughput, size a deployment, or produce benchmark JSON, even if they don't say "benchmark" by name. Also use when a `max benchmark` run fails to connect or reports zero/garbage numbers.
Systematically fix all failing tests after business logic changes or refactoring
Write or refresh Python test coverage. Use when Codex needs to add coverage, replace stale tests, prefer executable doctest examples in public docstrings, or lock down Python behavior in repos that use `uv`, `pytest`, `nox`, and `mise`.