Escrita e Conteúdo

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Full project context setup and session management skill. Use this when starting a new project, onboarding onto an existing codebase, resuming work after a session gap, ending a session and wanting to save progress, or when context is running low mid-session. Sets up a docs/context/ system that any AI tool can read (Claude, Codex, Cursor, Windsurf). Three modes: SETUP (first time), RESUME (session

Elabora respostas personalizadas e com sonoridade humana para perguntas de triagem de candidaturas de emprego, como "Por que esta função?" ou "Projeto de maior orgulho?". Use esta skill ao preencher formulários de candidatura, responder a perguntas de triagem ou redigir parágrafos de carta de apresentação e prompts comportamentais.

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.

Post-launch breakdown (~800-1500 words). What you shipped, the numbers (good or bad), what worked, what didn't, what you'd change next time. Use after every product/launch/release where you have real numbers to share — including (especially) when the numbers are embarrassing.

Checks science files for cross-layer contradictions, inconsistent equations, broken derivation chains, and violations of the universe's foundational axiom. Use when promoting drafts to canon, after writing new science content, after restructuring, or when user says "audit the science", "physics audit", "check for contradictions", "does this break anything", "verify the science", or "cross-layer ch

Rewrite docstrings and comments by reading the actual implementation, call sites, and tests — produce grounded, factual prose instead of deleting slop. Sibling of /techne:deslop. Use when the user wants to replace overhyped or hallucinated documentation with accurate one- or two-line descriptions derived from what the code actually does.

Short-form comparison post (X / LinkedIn / Threads). Two things contrasted to reveal a non-obvious preference. Use when the user wants to publish an "X vs Y" take — tools, approaches, mindsets, frameworks — and stake a side. Pairs well after a hot-take or how-to long-form piece.

Deep-dive research and analysis of external reference materials (YouTube videos, articles, GitHub repos, documentation, code sources) against the current project. ONLY trigger this skill when the user explicitly uses one of these phrases: "research this against the project", "analyze this reference", or "compare to this project" (or close variations of those phrases). Do NOT trigger just because t

Use this skill when the owner wants to write, draft, or generate a blog article. Invoke when the user says "write a blog article", "draft a blog post", "create a blog article", "generate a blog post", "write a how-to article", "draft a thought leadership piece", "write a pillar page", or similar requests for long-form web content.

Use this skill for any documentation task: writing or updating READMEs, creating docstrings, authoring runbooks, writing API documentation, creating onboarding guides, maintaining changelogs, writing architecture docs, or any task where the deliverable is written documentation. Triggers on: "write documentation", "document this", "write a README", "add docstrings", "write a runbook", "API docs", "

Auxilia na criação de artigos para blogs de tecnologia no Zenn, suportando diversos tipos como introduções de projetos, explicações técnicas e registros de TIL/aprendizado.