drafael
UserReusable agent skills and workflows for everyday development.
Categories
Indexed Skills (20)
blast-radius
Analyze a concrete code change for credible breakage beyond the obvious diff and seek executable proof for the assumptions that make it safe. Manual invocation only; use for an explicitly requested blast-radius analysis of a local diff, commit range, branch comparison, or local patch.
brainstorm
Design future behavior, architecture, ownership, features, or substantive alternatives through collaborative exploration before implementation. Use when the user explicitly asks to brainstorm, design, explore options, or think through a future change, or when another active skill identifies consequential design decisions that still need exploration. Use explain-code for neutral current-code walkthroughs and technical-writing, when available, to structure an agreed design.
clarify
Investigate expected-versus-actual behavior, suspected defects, and historical design rationale. Use when someone asks why observed behavior differs from expectations, whether behavior is wrong, or why a design decision exists. Use explain-code for neutral questions about what code does or how it works, and wrong when the user rejects the assistant's current approach.
debug-error
Systematically debug and fix errors using structured investigation. Use when the user asks to "debug", "fix an error", "troubleshoot", "investigate a bug", or shares an error message or stack trace.
explain-code
Explain current code behavior, structure, runtime flow, data flow, and component ownership. Use for ordinary walkthroughs, line-by-line explanations, subsystem mental models, and questions about what code does or how it works. Use teach, when explicitly invoked and available, for progressive learning; technical-writing, when available, for substantial standalone documentation; clarify for expectation mismatches or historical intent; code-review for finding problems; refactor-code for changing structure; and brainstorm for new architecture.
java-coder
Mandatory for every task in a Java codebase, including planning, implementation, debugging, refactoring, review, testing, Maven or Gradle build and dependency changes, performance or security analysis, and Java-related documentation. Detect Java projects from pom.xml, Gradle files, gradlew, or .java sources. Load before inspecting or changing the repository even when the user does not explicitly mention Java. Covers Java 21+, Spring Boot, Swing/EDT, code style, testing, security, and desktop UI.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
refactor-code
Change existing code through narrow, behavior-preserving, test-backed simplification without speculative architecture or scope growth. Use for requests to refactor, clean up, restructure, or simplify code. Use explain-code instead when the user only wants an explanation of the current structure.
reflect
Review the current session for durable, evidence-backed improvements to existing local skills. Manual invocation only; use when the user explicitly asks to reflect or run a session retrospective. Never edit skills or perform external actions without individual approval.
teach
Teach repository-backed code and engineering work through a progressive, evidence-grounded conversation. Manual invocation only; use when the user explicitly invokes teach to understand a change, subsystem, architecture, runtime behavior, or evidenced rationale. Read-only; do not modify files.
technical-writing
Write, revise, or review substantial technical documentation and design artifacts for a defined reader and task. Use for READMEs, guides, tutorials, how-to documentation, reference material, runbooks, RFCs, ADRs, technical specifications, and implementation plans. Use a design workflow first when future behavior or architecture needs exploration. Use unslop, when available, for small style-only edits. Do not use for code-only work, routine messages, release notes, PR descriptions, commit messages, or verbatim text.
test-coverage
Analyze and improve test coverage. Use when reviewing coverage gaps, writing missing tests, setting up coverage tooling, or improving branch/line/statement coverage for any language or framework.
unslop
Edit or review prose to remove formulaic AI-writing patterns while preserving facts, meaning, and the author's existing voice. Use for small style-only edits, articles, reports, messages, release notes, and other prose, or as the final pass after substantial technical writing. When technical-writing is available, use it first for substantial technical documentation and design artifacts. Do not use for code-only tasks or text that must remain verbatim.
write-tests
Write unit, integration, component, and end-to-end tests for code. Use when the user asks to "write tests", "add tests", "add test coverage", or "create test cases" for functions, services, components, CLIs, or user flows.
code-review
Find actionable defects and risks through a focused, evidence-based review of correctness, regressions, security, performance, architecture, and testing. Use for requests to review, audit, critique, or identify improvements. Use blast-radius, when explicitly invoked and available, for cross-boundary consequence tracing and executable safety proof of a concrete change. Use explain-code when the user only wants to understand current behavior or architecture.
owasp-security
Use when reviewing code for security vulnerabilities, implementing authentication/authorization, handling user input, or discussing web application security. Covers OWASP Top 10:2025, ASVS 5.0, and Agentic AI security (2026).
pretty-mermaid
Render beautiful Mermaid diagrams as SVG or ASCII art using the beautiful-mermaid library. Supports 15+ themes, 5 diagram types (flowchart, sequence, state, class, ER), and ultra-fast rendering. Use this skill when: 1. User asks to "render a mermaid diagram" or provides .mmd files 2. User requests "create a flowchart/sequence diagram/state diagram" 3. User wants to "apply a theme" or "beautify a diagram" 4. User needs to "batch process multiple diagrams" 5. User mentions "ASCII diagram" or "terminal-friendly diagram" 6. User wants to visualize architecture, workflows, or data models
skill-hunter
Use when the user wants to find NEW external skills for a project, build a skill stack from external registries, or compare external options against project needs. Do not use for questions about how to use already-installed/local skills.
typescript-coder
Mandatory for every task in a TypeScript or mixed TypeScript codebase, including planning, implementation, debugging, refactoring, review, testing, dependency and build changes, CI, security analysis, and TypeScript-related documentation. Detect projects from tsconfig files, .ts/.tsx sources, TypeScript dependencies, or TypeScript framework configuration. Load before inspecting or changing such repositories. Covers Node.js, Bun, existing Deno projects, backend, frontend, CLI/TUI, Electron, Electrobun, Tauri, AWS CDK, and modern tooling.
wrong
Reset after the user rejects the assistant's current answer, plan, implementation, or problem-solving direction. Use for "your approach is wrong", "start over", "try a different approach", or when the attempted solution has demonstrably failed. Use clarify for incorrect system behavior and brainstorm when the user wants multiple new designs or alternatives.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.