Explorar skills

Use esta skill para editar, revisar ou autoauditar textos, removendo sinais de escrita de IA e tornando-os mais humanos. Ela aborda características comuns da escrita de IA, como inflação promocional, atribuição vaga, vocabulário de IA e prolixidade.

Generate properly formatted Markdown from unstructured notes, scratch text, transcripts, or rough drafts. Use when the user wants content rewritten into cleaner Markdown without inventing new information.

Destila una guía de estilo de escritura desde 3-5 muestras de referencia y 1-2 textos propios. Genera `scribetronic/style/writing-style.md` con las 8 secciones (voice, structure, sentence-level, signature moves, anti-patterns, ejemplos +, ejemplos -, revision checklist). Usar cuando el usuario quiera crear o refrescar la guía de estilo de su blog/newsletter.

Rigid TDD process for writing and verifying tests before implementation. Use when implementing any feature or bugfix. Receives test case bullet points from the plan and enforces red-green cycle.

Use when reviewing novel chapters or manuscripts for logic consistency, character authenticity, plot cohesion, foreshadowing payoff, emotional resonance, narrative vividness, and content compliance. Also triggers for first-chapter editorial audits against web novel platform submission standards. Triggers on requests like "check the story", "review this chapter", "is this consistent with character"

Scans a project for agent-harness gaps and outputs a prioritised list with paste-ready config snippets to close them. Covers hooks, CI, pre-commit, instruction file quality, init.sh, and session discipline. Use when starting a new project, auditing an existing harness, writing or reviewing CLAUDE.md/AGENTS.md, setting up CI gates, beginning multi-day autonomous work, or when user says "set up harn

Trigger on "consult lint", "consistency pass", "diagram vs narrative", "broken promises across docs", "cross-artifact check", "scope drift lint". Read-only diff across frame, arc, gates, acceptance, commercial, architecture artifact. NOT rewriting copy (use consult-package), NOT drawing diagrams (use arch-diagrams).

Run the concept-merger reducer subagent over the per-node enrichment sidecars to produce or refresh `lineage/{repo}/concepts.yaml` — the deduplicated concept catalog with cross-axis equivalences and canonicalisation candidates. Anchored on `documentation/docs/main-concepts.md` for the canonical vocabulary. Maintainer-curated entries preserved across refreshes.

Parse and understand Cantonese user input. ALWAYS use this skill first when user writes in Cantonese or uses Cantonese vocabulary. This skill translates Cantonese to standard Chinese/English for LLM comprehension.

当用户想为 Skills 批量添加中文翻译时使用，支持全局 agent 目录（~/.claude/skills、~/.cursor/skills、~/.trae-cn/skills 等）以及当前项目目录下的 .claude/skills、.cursor/skills 等。适用场景：用户说"给 skills 加中文"、"汉化所有 skill"、"翻译当前项目的 skill"。

Use when reviewing novel chapters or manuscripts for logic consistency, character authenticity, plot cohesion, foreshadowing payoff, emotional resonance, narrative vividness, and content compliance. Also triggers for first-chapter editorial audits against web novel platform submission standards. Triggers on requests like "check the story", "review this chapter", "is this consistent with character"

Short-form numbered list post for X / LinkedIn / Threads. "X things I learned doing Y", "X mistakes that cost me Z", "X principles for Z". Use when the user has a small set (3–10) of crisp, parallel points worth shipping as a standalone short-form piece — or when distilling a how-to / launch-retro long-form into a list.