Explorar skills

Generates a manual test plan, QA plan, test scenarios, testing checklist, or guidance on how to test changes. Works from branch diffs, stories, specs, or requirements.

Pre-commit audit. Invoke before every git commit. Diffs the staged change against the repo's "canaries" (README, decision log, roadmap, public API, doc comments, release notes, test discipline) and surfaces anything that's drifted out of sync. Updates the obvious drifts in place; flags judgement calls for the operator.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

Build and ship features with security baked in — runs OWASP Top 10 pre-scan, builds and ships with /ship, validates with post-build security review, then penetration tests the result. Use when shipping auth flows, payment logic, API endpoints, admin panels, or any security-sensitive code.

Tracks AZIMUTH's 8 primary citation source families for new publications or significant updates. Stages validated findings in research/staged-findings.md for human review before promotion to references/base-rates.md. Invoke with 'run the research scout' or 'promote staged findings'.

Teste uma ideia sob pressão convocando um conselho multipessoal para debater e decidir. Use para decisões de alto risco, como estratégia, direção de produto ou movimentos de carreira.

Inspect changed dbt assets, estimate blast radius, identify missing tests, and recommend the narrowest safe validation plan.

Guides marketers through measuring true marketing impact—covering incrementality testing, attribution model selection, geo-lift experiments, and how to avoid common measurement traps. Trigger when a user asks how to prove marketing ROI, measure a specific channel, set up attribution infrastructure, or resolve marketing-sales credit disputes.

Test a skill's quality before publishing — validate SKILL.md frontmatter schema, check instruction structure for phases and guardrails, score against the marketplace rubric out of 100, simulate a dry run to find failure points, and report a pass/fail verdict with specific fixes

Pre-launch quality gate for games: audit rendering and memory performance against platform budgets, run QA for crash-causing defects and platform certification blockers, review accessibility for CVAA and platform compliance, test security against cheating and save tampering, and evaluate UX for onboarding and settings completeness. Use before submitting to app stores, console certification, or pub

Use to restructure code while guaranteeing that all existing tests continue to pass.

Validates test quality beyond coverage: uses Claude subagents to generate intelligent mutations for source code, runs them via the project's native test runner (pytest, jest, vitest, mocha, go test), prints a structured summary, generates mutation-todos.md with per-mutant rationale, persists every run to a per-project SQLite ledger and JSONL trace under ./.logbooks/mutation-testing/, and warns whe