Explorar skills

Create structured QA round documents for manual testing phases. Generates tracking docs with issue logging, session planning, and verification workflows.

Analyze code quality with codopsy-ts. Quality scoring (A–F), cyclomatic & cognitive complexity, 13 lint rules, baseline tracking, hotspot detection, and auto-fix. Use when asked to check code quality, reduce complexity, track quality trends, or find code smells.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

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

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Utilice para escribir o convertir pruebas JUnit en Java o Kotlin con la biblioteca TableTest. Se activa al probar múltiples escenarios con la misma lógica de aserción, convertir métodos @Test repetitivos, iniciar un nuevo @TableTest, o al preguntar sobre la sintaxis de TableTest o escribir pruebas para una característica.

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

Write failing tests from work-plan contracts and acceptance criteria

契約書・利用規約を読み込み、リスク条項・不利な条件・確認すべき点を一覧化するスキル。法的アドバイスではなくチェックリストとして使用する。

Package a compiled Genai skill for sharing — creates a portable zip archive with SKILL.md, input.schema.json, README, and assets. Use when the user wants to distribute or share a compiled skill.

Use when creating, drafting, or rewriting Linear issues (epics, stories, hardening tickets, refactor tasks) in any workspace. Applies the linear-issue-craft conventions for titles, description structure, tone, labels, and epic-to-story decomposition. Trigger when the user says "draft an issue", "open an epic", "file a ticket", "write a Linear issue", or pastes a rough idea/bug report and asks for

Author robust /goal conditions for Claude Code v2.1.139+. Provides the 4-piece recipe (end state + proof + invariant + bound), 6 pattern templates (migration, file-size budget, queue drain, test repair, dep upgrade, docs/changelog), and an anti-pattern checklist. The evaluator that judges /goal conditions only reads the transcript — never runs tools. This skill exists to make conditions the evalua