Author and run Atheris - Google's Python coverage-guided fuzzer built on libFuzzer. Covers pip installation, atheris.Setup + atheris.Fuzz invocation, TestOneInput(data: bytes) target signature, FuzzedDataProvider for structured input, instrument_imports() / instrument_func decorators for coverage instrumentation, and libFuzzer-passthrough flags (-atheris_runs, -max_total_time, -dict). Use for fuzzing Python libraries - also supports CPython native-extension fuzzing.

Author and run AFL++ - out-of-process coverage-guided fuzzer (a community fork of Google's original AFL with improved mutations and instrumentation). Covers afl-cc / afl-clang-fast instrumented build, afl-fuzz invocation, parallel master/slave (-M / -S), dictionary support (-x), QEMU mode (-Q) for binaries without source, output structure (queue / crashes / hangs), crash minimisation (afl-tmin), corpus minimisation (afl-cmin), crash filename triage, and CI integration. Use for fuzzing standalone binaries (file processors, command-line tools) where libFuzzer's in-process model doesn't fit; for cross-fuzzer corpus strategy see corpus-management-reference.

Wraps Unleash (Open Source / SaaS) SDK testing patterns: bootstrap with a static toggles array (no network), the test mode (disableMetrics + disablePolling), the custom strategy testing pattern (implement a Strategy class + assert isEnabled), and assignment-integrity tests. Use when writing tests for code that uses Unleash for feature flags.

Wraps Optimizely Feature Experimentation SDK testing patterns - client init from a fixture datafile (offline-friendly), the decide / decideAll v5 API, forced-decisions for per-test arm pinning (fixing which variation a user gets), OptimizelyUserContext + activate/track events, assignment-integrity (deterministic bucketing) tests. Use when writing A/B tests or feature-flag tests for Optimizely-instrumented application code. For another experimentation SDK use the matching harness - statsig-test, vwo-test, amplitude-experiment-test, or split-io-test; for experiment DESIGN gates not SDK code use ab-test-validity-checklist.

Author and run GitHub Issues bug workflows via REST API (2026-03-10): issue creation, state changes (open / closed with `state_reason`), label-based severity/priority classification, and comment attachment. Covers `POST /repos/{owner}/{repo}/issues`, `PATCH` for `state_reason` transitions (completed / not_planned / duplicate / reopened), and label conventions for GitHub's binary open/closed model; Projects v2, `gh` CLI, and CI wiring live in references/. Use when programmatically managing the GitHub Issues bug lifecycle; for the same workflow on another tracker use azuredevops-bug-workflow, jira-bug-workflow-runner, or linear-bug-workflow-runner.

Configures Pester v5 for testing PowerShell CLIs, scripts, and cmdlets - Describe/Context/It blocks, Should assertions, Mock for isolating external dependencies, BeforeAll/BeforeEach setup hooks, Invoke-Pester with PesterConfiguration for tags, code coverage, and NUnit/JUnit XML output in CI. Use when the unit-under-test is a PowerShell script, function, or CLI tool invoked from pwsh on Windows or cross-platform.

Conventions for designing AND testing CLI output so it stays parseable and assertable - exit-code policy (0 success, non-zero failure with stable codes per failure mode), `stdout` for primary data / `stderr` for messages, `--json` / `--plain` for machine-readable output, deterministic ordering and timestamps, `NO_COLOR` / TTY-aware color, `-q` / `--verbose` discipline, and stable `--help` / `--version`. Built on the [Command Line Interface Guidelines][clig]. Use when designing or testing a CLI's output - a new flag, command, or error message, writing CLI assertions, or fixing flaky tests caused by non-deterministic output; it is the assertion contract for `bats-testing` and tells `tui-snapshot-tester` what does NOT need a snapshot.

Configures LitmusChaos for Kubernetes-native chaos engineering - installs via Helm, picks ChaosExperiments from the ChaosHub (`pod-delete`, `network-latency`, `node-cpu-hog`, etc.), authors a ChaosEngine CR scoping the experiment + steady-state probes, runs as part of the cluster, exports Prometheus metrics for the verdict. Use when the platform is Kubernetes (CNCF-hosted; cloud-native). Prefer over chaos-mesh when the team wants a ChaosCenter web UI for workflow scheduling and ChaosHub catalog browsing; use chaos-mesh for fine-grained network-fault policies via its own CRD family.

Configures Gremlin (commercial) for cross-platform chaos engineering (fault injection, resilience testing) - installs the Gremlin agent on Linux / Windows / Kubernetes, picks attack types (resource, network, state, request), chains attacks into Scenarios (chaos experiments), integrates with the Reliability Score for forward-looking metrics. Use when the platform spans multiple environments (bare metal + cloud + serverless) and the team needs a commercial-supported solution per Gremlin's multi-platform support.

Pure-reference catalog of cache-coherence patterns across the request path. Defines the five-tier cache stack (browser → CDN → reverse-proxy → application → data store), the per-tier cache-writing patterns (cache-aside, write-through, write-back, write-around, refresh-ahead), and the canonical invalidation strategies (TTL-only, event-driven purge, surrogate keys, version-tagged URLs, soft purge), plus an anti-pattern table and a worked multi-tenant coherence-test example. Deep detail lives in references/: RFC 9111 Cache-Control / Vary / ETag directive tables, the cross-tier test surface, cache-stampede (thundering-herd) mitigations incl. the XFetch formula, and RFC 5861 stale-while-revalidate / stale-if-error semantics. Use for pattern selection, Cache-Control header design, coherence audits, stampede-refresh strategy, and SWR/SIE window design; use a cache-key-collision check when the question is whether two concrete requests collide on a key scheme.

Wraps browser-side Cache-Control testing with Playwright (Cypress for legacy stacks): asserting response Cache-Control headers from Network events, ETag round-trips (If-None-Match → 304), service-worker strategies (Workbox cacheFirst / networkFirst / staleWhileRevalidate), and reload semantics (normal vs hard). Covers MDN Cache-Control + RFC 9111. Use when auditing browser-tier caching in E2E tests. For CDN-edge purge use cdn-cache-purge-tests; for the reverse-proxy tier use varnish-test-vtc-syntax; for an app-tier store use redis-cache-tests; SWR directive semantics live in stale-while-revalidate-reference.

Configures Lighthouse CI's Accessibility category for automated accessibility testing (a11y / WCAG coverage) - `categories:accessibility` audits backed by axe-core (axe) - with per-URL minimum-score assertions (fail a build when a page's score drops below a threshold) and per-audit overrides, distinct from the Performance category that `lighthouse-perf` covers. Use when the project already runs Lighthouse CI for Web Vitals and the team wants to add accessibility coverage in the same pipeline rather than spinning up a separate scanner.

Author and run E2E tests on LambdaTest - cloud grid for cross-browser + real-device testing with W3C WebDriver, Cypress, Playwright, and Appium support. Covers LT_USERNAME + LT_ACCESS_KEY auth, hub URL hub.lambdatest.com/wd/hub, W3C capabilities + LT:Options dict (build, name, project, smartUI, network, console, video, tunnel), LambdaTest Tunnel for internal apps. Use for cross-browser regression with LambdaTest as the cloud grid; complements BrowserStack + Sauce Labs.

Generates AI quality evaluation reports for LLM and ML-powered products — designs golden datasets, defines accuracy metrics, tracks quality across iterations, and produces stakeholder-ready summaries that explain probabilistic behaviour in business language. Use when evaluating AI or LLM output quality, building an eval framework or golden dataset, benchmarking accuracy between releases or prompt versions, reporting AI quality to clients or executives, or when the user asks "how good is our AI", "accuracy report", "eval results", "benchmark the model", or "why does the AI give different answers to the same question".

Respond in the voice of a salty seafaring pirate — swapping everyday words for nautical slang, droppin' the 'g' on -ing endings, and sprinkling in sea metaphors, while keeping all code, commands, and technical facts exact. Use when the user asks Claude to talk like a pirate, go full buccaneer, or invokes /pirate-speak. Applies the persona to all replies until the user asks to stop.

Write and run HTTP API tests in Hurl's plain-text format. Use when testing REST/GraphQL APIs, writing integration or smoke tests for HTTP endpoints, chaining requests with captured values, polling async APIs, converting curl commands into maintainable tests, or producing executable API documentation. Trigger on .hurl files, the hurl or hurlfmt CLI, jsonpath/xpath response assertions, or any ask to 'test an API' with a simple text-based tool.

AST-based code search, lint, and rewrite using ast-grep. Use when finding code patterns structurally (not textually), writing lint rules, building codemods, or migrating API usage across a codebase. Prefer over regex grep when the match target is a syntactic construct (function call, import, class field, assignment).

Answer questions about the Zod schema validation library and help build schemas, parsers, refinements, transforms, codecs, and error formatters. Use when developers: (1) ask about Zod APIs like `z.object`, `z.string`, `z.array`, `z.union`, `z.discriminatedUnion`, `parse`, `safeParse`, `z.infer`; (2) define request/response/form schemas in TypeScript; (3) handle `ZodError` or customize error messages; (4) migrate between Zod v3 and v4 (entry-point split, `formatError` → `treeifyError`/`prettifyError`, unified `error` param replacing `message`/`errorMap`). Triggers on: "zod", "z.object", "z.string", "z.array", "z.union", "z.infer", "z.input", "z.output", "ZodError", "$ZodError", "safeParse", "parseAsync", "z.codec", "treeifyError", "prettifyError", "flattenError", "discriminatedUnion", "zod/v4", "zod/v3", "zod/mini", "z.coerce", "superRefine".

Use when creating or editing Nullstone IaC YAML files under `.nullstone/` — adding or wiring apps, datastores, networks, domains, subdomains, ingresses, clusters, cluster-namespaces; setting `vars`, `environment`, `connections`, or `capabilities`; configuring `events`. Triggers on file paths `.nullstone/config.yml`, `.nullstone/{env}.yml`, `.nullstone/previews.yml`, and anything under `.nullstone/stacks/{stack}/`.

Install, uninstall, or list tessl skill tiles for installed mks plugins. Use this when asked to "install the tile for an mks plugin", "uninstall the tile for an mks plugin", "list tiles for an mks plugin", "tessl install PLUGIN", "tessl uninstall PLUGIN", or "tessl list". This skill is only for the mks CLI — not for any other plugin system.