Read recent code review on this repository's pull requests, find the mistakes reviewers keep catching, and file a GitHub issue proposing a rule so agents get it right next time. Use when running the rule mining maintenance loop, or when asked what the agent keeps getting wrong in review. Files issues only; never changes code or docs.

Read recent code review on this repository's pull requests, find the mistakes reviewers keep catching, and file a GitHub issue proposing a rule so agents get it right next time. Use when running the rule mining maintenance loop, or when asked what the agent keeps getting wrong in review. Files issues only; never changes code or docs.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when reviewing a PR's test quality via mutation testing. Runs Stryker on the diff, triages surviving mutants, and posts findings as a PR comment with inline annotations on changed lines.

Use whenever an open PR needs shepherding to a merge — watching CI, weighing the agentic reviews, resolving merge conflicts, and merging once everything is green. Assumes the PR already exists (code is written, pushed, and `gh pr create` has run); this skill starts from there. Used by the `build-feature` skill's last step, and by any agent (e.g. a dedicated babysitter) whose job is watching a PR through to landing.

Run the full POSCursor verification matrix with timestamped evidence under tmp/systematic-test-matrix/. Use for release readiness, pre-deploy QA, or when the user asks to systematically run all test surfaces (tsc, expo-doctor, Jest buckets, full Jest, Playwright, web export, export smoke). Not for authoring individual unit tests — use the testing skill for that.

Reduce the built CSS size of an app using @allxsmith/bestax-bulma — measure raw and gzip size, then apply the cheapest lever that fits (lighter prebuilt CSS flavor, hand-rolled modular Sass build, import and icon-asset hygiene). Use when the CSS bundle looks too big, a size budget or Lighthouse audit flags stylesheet weight, switching bestax.css to a versions/*.css flavor, or setting up a modular @use Bulma/Sass build.

Enforce AWS CDK security and compliance controls with cdk-nag. Use when adding rule packs, triaging findings, writing justified suppressions, integrating checks in CI/CD, or preventing insecure infrastructure patterns in CDK stacks.

Generate an original, autobiographical confessional stand-up bit/story/monologue built from a genuinely painful personal anecdote, using techniques like multi-voice character embodiment (switching voice mid-story to become a parent/cop/friend/animal/younger-self), rhythmic escalating repetition, self-implicating honesty, vivid sensory specificity, plus a blunt closing truth in place of a tidy moral. Use it when a user wants to write, punch up, workshop, critique such a piece before it gets tested at an open mic. Do not use it for observational one-liners with no personal narrator, absurdist/surreal sketches, character-only sketch writing, requests to reproduce, quote, transcribe, imitate a real performer's actual routine.

Propose or apply consolidation of episodic memories into semantic ones, combining related episodic captures into higher-level semantic summary notes. Use after a long session or when the user asks to clean up, organise, summarise, merge, or declutter memories, or requests memory cleanup or memory management. Always run --propose first so the user can review before --apply commits changes to the vault.

Use when auditing, reviewing or tightening an existing CI pipeline (e.g. Woodpecker, GitHub Actions, GitLab CI), when a secret scan or other gate logs 0 items or has no self-test or must-fail proof, when guarding the pipeline file itself with a test, when pipeline or gate files are protected or operator-signed, or when asked to make CI "stricter", "more reliable" or "trustworthy" — checks that every gate really verifies something (non-zero counts in the log, a must-fail proof), covers every file, runs at a strict level, and is pinned and ratcheted. Also use when a gate has been green for a long time without ever catching anything. Not for setting up a new pipeline or closing local/CI drift — that is ci-local-parity.

Use when asked what first impression a public brand or marketing site makes, why visitors come to it, whether the impression matches the intended positioning, or whether its calls to action work — "first impression test", "what does a visitor think in the first seconds", "persona test of the site", "does the site match our positioning", "do the CTAs work", "brand check across our sites". Runs blind persona subagents on screenshots of the first screen without scrolling, a brand-name-only test, a measured call-to-action check and a comparison with the written norm. Report only, changes no site. Not for a full site revision (use a site-revision skill), not for rewriting copy (use a copywriting skill), not for performance or accessibility audits.

Generate a .devcontainer (devcontainer.json plus Dockerfile) for AI-IDE development with AI CLI integration, skill mounting and security hardening. Use when the user wants to set up or containerize a local dev environment. Not for cloud deploys.

Interactive help with Netwrix documentation already in progress or already written. Use whenever the user wants to review, edit, tighten, restructure, or improve an existing doc, section, or paragraph ('review this page', 'does this read well', 'make this clearer', 'how should I structure this', 'fix this section'); asks why Vale or Dale flagged something or what a style rule means; wants to brainstorm or outline before writing; wants a section drafted with their input; or wants an external document (.docx) merged into an existing markdown file. Applies to any file under docs/ or any pasted doc text. When the user hands over source material to write from (a PR, a GitHub issue, Jira ticket, or Azure DevOps item, specs, notes, a detailed prompt), use doc-draft instead.

One shared denylist of catastrophic shell commands (rm -rf on / or ~, dd/mkfs, sudo rm, fork bombs, curl|sh, git push --force, gh repo delete) enforced as a PreToolUse/pre-exec guard across every AI coding agent on the machine — Cursor, Claude Code, Codex, OpenCode, Pi, Hermes, Grok, Droid, Devin. Use when adding or tuning blocked-command patterns, wiring the guard into a new agent or a new machine, debugging why a command was (or was not) blocked, or when the user mentions command guard, guardrails, dangerous command hook, or PreToolUse safety.

Maintain and improve existing k6 test scripts. Covers threshold tightening based on trend data, version migration between k6 releases, auto-fixing tests when the underlying service changes, refactoring for cleanliness, and auditing scripts against current best practices from docs. Use when the user asks to fix a failing k6 test, tighten thresholds, migrate a script to a new k6 version, refactor a test, update a script after a service change, or improve a script with best practices. Trigger on phrases like "fix my k6 test", "tighten my thresholds", "migrate to k6 v2", "update my test script", "refactor this k6 test", "my test is failing after a deploy", "apply best practices to my script", "modernize my k6 test", or "the service changed and my test broke". Also trigger when another skill (k6-trend-analysis or k6-cloud-investigate-test) hands off with a recommendation to edit a script. Maintains existing scripts; to author a new test use the k6 skill, or k6-browser-test for a browser test.

Shapes text that agents write for people: issues, PR descriptions, review replies, comments, verdicts, bug reports, and delivery reports. Produces a banner naming the agent and model, a quoted TL;DR, human-first prose under the repository template, folded supporting details, and a folded record of the skills, references, and evidence used. USE FOR: drafting or tidying agent-written GitHub text, making a PR or issue body shorter and readable, adding provenance and evidence, "write this up for humans", "add a TL;DR". DO NOT USE FOR: choosing or simulating the audience (use fusion-audience-alignment), skill or agent instruction files, commit messages, end-user product help, or publishing without confirmation.

Use ElevenLabs Realtime models (`eleven_realtime_v1_mini`, `eleven_realtime_v1_max`), the low-latency models built for voice conversation. Use when the user wants to create an ElevenAgents agent on a Realtime model or switch an existing agent's Voice mode to Realtime, set `conversation_config.realtime_model`, choose between Realtime Mini and Max, or debug a Realtime agent that won't publish or transfer. Also use when migrating a voice app built on OpenAI's Realtime API and SDK (`@openai/agents-realtime`, `gpt-realtime`) to the OpenAI-compatible ElevenLabs Realtime API, including the `client_secrets` mint, the WebSocket transport, and audio after leaving WebRTC (closes with 4001/4003, no audio). Not for choosing an agent's LLM or TTS model in Custom mode, Scribe realtime speech-to-text, or migrating Chat Completions or Responses API text calls.

Add ElevenLabs to a project from scratch. Use when the user wants to start using ElevenLabs, add text to speech, speech to text, voice agents, real-time voice for their own agent runtime (Speech Engine), sound effects, music, voice changing, voice isolation, or dubbing to their app, or get set up with an ElevenLabs account or API key for the first time. Handles sign-in, API key creation, SDK install and a test request end to end; the user leaves the conversation once, to approve a browser page. Not for fixing a key that stopped working or placing one an administrator issued (use setup-api-key).