Explorar skills

Run an anti-slop cleanup workflow on AI-generated code — regression-tests-first, smell-by-smell, behavior preserved.

Computes development quality and velocity metrics from git history and tracks improvement over time. Measures fix ratios, rework hotspots, test coverage, DORA metrics, and code churn.

Build, test, and debug Zorro Agent RL environments for Atropos training. Covers the ZorroAgentBaseEnv interface, reward functions, agent loop integration, evaluation with tools, wandb logging, and the three CLI modes (serve/process/evaluate). Use when creating, reviewing, or fixing RL environments in the zorro-agent repo.

Review then build — chains architecture review into implementation. Accepts any spec format (ticket, PRD, engineering spec, feature description, screenshot) and autonomously reviews the design, resolves gaps, then implements with tests and a PR.

Decision-quality pre-commitment analysis for initiative-level go/no-go calls with meaningful downside and limited reversibility — launches, rewrites, key hires, partnerships, strategic bets, timelines. Invoke when the user explicitly asks to pressure test, validate, or evaluate such a decision (e.g. 'should we do this,' 'pressure test,' 'go/no-go,' 'are we ready'). Do NOT invoke for routine code r

Generate and run load tests with k6, Locust, or Artillery. Auto-detects API framework, creates realistic user behavior flows (browsing, authenticated CRUD, search-heavy), runs ramp-up, sustained, spike, and stress test profiles with defined latency and error-rate thresholds, then produces a bottleneck analysis with optimization recommendations. Use when you need to benchmark API performance, find

Fix broken builds, type errors, or test failures with the smallest safe diff — no opportunistic refactors, no cleanup, no unrelated changes.

Inventory and prioritize all technical debt in a codebase. Scans for TODO/FIXME/HACK markers and stale comments, outdated and deprecated dependencies with CVE detection, high-churn files and cyclomatic complexity hotspots, duplicated code blocks, missing test coverage on critical paths (auth, payments, data mutations), hardcoded magic numbers and configuration debt, god objects over 500 lines, cir

Review pull requests with full context. Fetches linked Jira tickets, Figma designs, and Notion docs via MCP, spawns parallel subagents for systematic code review (correctness, security, tests, SOLID, clean code), then drafts friendly, humanized GitHub-ready comments. Use when reviewing PRs, examining code changes, or when the user asks for a code review.

Guides Claude to help B2B marketers develop, test, and refine messaging and copy—from foundational positioning and flagship messages to homepage copy, outbound messaging, and channel-specific execution—using practices sourced exclusively from Exit Five podcast guests.

Guidance for B2B marketers on developing, producing, testing, and iterating on creative assets across paid, organic, video, and brand channels—trigger when working on ad creative, campaign ideation, brand differentiation, video content, or creative team workflows.

Busca e resume as últimas notícias de IA da internet, incluindo blogs de tecnologia, centros de pesquisa, newsletters e sites de notícias, e então renderiza um resumo interativo polido como um artefato React no chat.