Explorar skills

Frontend design workflow that produces non-generic, editorial-quality UI. Immediately invokes the frontend-design skill for aesthetic direction before any code is written. Enforces a written design contract that is re-read before every single component — not once and forgotten. Creates separate files per page and component, never monolithic output. Reads DESIGN.md if present for exact brand tokens

Use when demonstrating a correctly structured agent skill. Trigger when the user asks to "show a well-formed skill", "give me a skill template", or "what does a compliant SKILL.md look like". Also triggers for regression testing: this fixture MUST score maturity >= L2 with zero Critical or Error findings.

Autonomous security vulnerability scanner for codebases. Detects secrets, XSS, missing security headers, auth issues, OWASP Top 10 patterns, dependency vulnerabilities, PII exposure, CORS misconfiguration, and more. Aligned to OWASP APTS (Autonomous Penetration Testing Standard) Foundation tier. Outputs SARIF JSON, Markdown report, and APTS Conformance Claim. Use when the user wants a security aud

Interactive co-authoring skill for the wide end of the exploration funnel. Captures and refines the core intent, whether the outcome is a software app, a business process improvement, research analysis, or strategic roadmap. Guides users through gathering context, iteratively drafting the brief, and testing for blind spots.

Use this skill when the user runs /help, /help commands, or /help <command-name>. Shows plugin command reference. Read-only — writes nothing, modifies nothing.

Use this skill on EVERY Edit, Write, or code-modification tool call. Enforces minimum-diff discipline — only touch files listed in the plan's in-scope list, only modify functions listed in the plan's in-scope functions, never modify adjacent functions, never refactor or rename unrelated code, never "fix while you're here". Unrelated bugs get logged to the follow-ups file, not fixed inline. This sk

Generate optimized image prompts for AI image generation models including DALL-E 3, Midjourney, Stable Diffusion XL, Flux, and others. Creates contextually appropriate, visually compelling prompts based on page content and brand style. Trigger keywords: image prompt, AI image, hero image, marketing image, generate prompt, image generation.

Activate when the user wants to install, deploy, test, or materialize an APM package into runtime directories such as .agents/, .github/, .claude/, .cursor/, .gemini/, .codex/, .opencode/, or .windsurf/. Use after creating or converting an APM package.

(Industry standard: Meta-Learning System / Automated Autoresearch) Primary Use Case: Continuous, self-improving orchestration of an agentic system over multiple sessions. Use when: building a continuous improvement layer that autonomously identifies workflow friction, postulates hypotheses, and tests improved instructions/coding skills against an objective headless benchmark before merging and per

Use when you need to automate, test, scrape, or debug any web page. State your goal — I'll ask questions, plan, execute autonomously, and report results.

Generates and runs full end-to-end UI tests using Playwright against a live URL. Auto-installs Playwright and Chromium if not present — isolated in e2e/ folder, never pollutes app dependencies. Reads SPEC.md and FEATURES.md to automatically generate test flows covering every critical user journey. Runs tests with video recording on failure and HTML report. Two-device flows (poster + joiner, sender

Use this skill at the START of every coding task — new builds, bug fixes, and change requests. Classifies the work item, validates it against project scope, produces a high-level estimate, proposes a technology stack, and checks stack compatibility. Writes a plan artifact to .claude/sdlc/plans/ that every downstream phase and hook depends on. Must run before any Edit, Write, or code-generation too