Explorar skills

Single-entry slash command for the Peec AI growth loop. Detects whether the current working directory has a setup_state.json, what state it's in (missing / fresh / stale / very stale / brownfield-importable), and hands off to the right skill — /peec-setup (full or import or audit) or /peec-agent. Use when the user says "/peec-start", "what should I do for Peec", "is my setup done", or any opening

Produce an ATDD-first implementation plan in Claude Code's native plan mode, with named design patterns called out where they earn their keep. The skill enters plan mode automatically (via the EnterPlanMode tool), runs /flagrare:codebase-explore to ground the plan in the actual codebase, then produces a plan-mode plan that MUST include both: (1) 3-5 acceptance tests in plain English defining 'done

Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.

Static-analysis penetration test that hunts for exploitable vulnerabilities with proof-of-concept payloads and fix code. Covers SQL and NoSQL injection (string concatenation, raw queries, operator injection), XSS (reflected, stored, DOM-based, template injection, dangerouslySetInnerHTML), authentication bypass (missing auth middleware, JWT algorithm confusion, predictable tokens, OAuth state CSRF)

Use when implementing any feature or bugfix, before writing implementation code

Activates the QuantTrader agent for quantitative trading, signal generation, and portfolio risk sizing. Use this skill when you need buy/sell/hold signals with entry price, target, stop-loss, and R:R ratio; position sizing via Kelly Criterion; market regime detection (trending/ranging/volatile); backtesting logic; or VWAP/TWAP execution planning. Outputs structured JSON trade signals with plain-En

Analyze and score test coverage across all testing dimensions -- unit, integration, E2E, load, visual regression, contract, and accessibility. Auto-detects tech stack and test infrastructure, runs existing coverage tools, identifies gaps by category, scores each on a 0-10 scale with weighted overall health, and produces a prioritized remediation plan routing to the right testing sub-skill. Use whe

Configure device matrix testing across real phones, tablets, and emulators. Sets up Firebase Test Lab, AWS Device Farm, or BrowserStack with smart device selection covering flagships to budget phones, test sharding for parallel execution, flaky test quarantine, and cross-device performance benchmarking. Use when you need to test on multiple devices, validate across screen sizes, catch device-speci

Auto-detects any tech stack, generates and runs exhaustive end-to-end tests. Triggered by "end-to-end tests", "e2e tests", "integration tests", "test the whole app", "generate tests", "test coverage", "write e2e", "run e2e", "full test suite".

Deterministic 3-cycle loop for gathering codebase context before acting. Broad search → exact source and tests → target-specific docs and setup. Stop after enough context or report what is still missing.

Audits AZIMUTH's coverage completeness. Cross-references what SKILL.md claims to handle against what reference, diagnostic, and domain-policy files actually cover. Identifies thin coverage, missing domains, and structural inconsistencies. Run before major version planning.

Ative um modo de trabalho automático 24x7 para melhorias contínuas, correções, testes e polimento em código, ML/dados, pesquisa, design ou escrita. Ele opera sem parar até que você o instrua a parar, ideal para projetos de longa duração.