public-docs

por sentry

Criar e manter documentação pública do

npx skills add https://github.com/getsentry/junior --skill public-docs

Public Docs

Use this workflow to produce docs that are crisp, task-oriented, and trustworthy for external users.

Load only the references needed for the request:

TaskRead
Understand docs app layout and constraintsreferences/api-surface.md
Draft or revise common docs pagesreferences/common-use-cases.md
Diagnose docs quality/build failuresreferences/troubleshooting-workarounds.md

Core invariants

  1. Keep docs audience-facing: explain user outcomes, not internal implementation chatter.
  2. Match the local docs contract in packages/docs/src/content/docs/contribute/documentation-guidelines.md.
  3. For new or substantially edited pages, require frontmatter fields: type, summary, prerequisites, related.
  4. Include concrete verification steps for tutorial/troubleshooting content.
  5. End each page with an explicit "next step" path through internal links.
  6. Prefer minimal runnable examples over long conceptual exposition.
  7. Keep prose present around lists; avoid heading-plus-bullets-only sections.

Workflow

1. Classify the request

Select one primary path:

  • New page authoring
  • Existing page refactor/clarification
  • Information architecture update (sidebar/redirects/navigation)
  • Docs quality pass (accuracy, scannability, consistency)
  • Troubleshooting/build-fix for docs app

2. Gather local context

  1. Read packages/docs/src/content/docs/contribute/documentation-guidelines.md.
  2. Read neighboring docs in the same section (start-here, concepts, extend, operate, reference, contribute).
  3. If navigation is involved, read packages/docs/astro.config.mjs (sidebar and redirects).
  4. If public interfaces are involved, verify the exported TypeScript surface and its code comments directly.

3. Author or edit with the right page shape

  1. Pick doc type (conceptual, tutorial, reference, troubleshooting) from intent.
  2. Follow depth and section guidance from documentation guidelines.
  3. Keep wording direct and plain; remove filler or internal-only caveats.
  4. Use titled code fences for file snippets.
  5. Prefer internal links that advance the reader to the next concrete action.

4. Validate changes

Run the narrowest meaningful checks:

pnpm docs:check

When structure, sidebar, or redirects change, also run:

pnpm docs:build

5. Report completion

Return:

  1. Changed files and what each change improves for readers
  2. Validation commands executed and outcome
  3. Residual risks (for example, missing screenshots, unverified env-specific setup)

Mais skills de sentry

architecture-review
sentry
Revisão de saúde do código em nível de equipe. Encontra módulos monolíticos, falhas silenciosas, lacunas de segurança de tipo, buracos na cobertura de testes e problemas de compatibilidade com LLM.
pi-agent-integration
sentry
Integrate `@mariozechner/pi-agent-core` as the agent abstraction inside another library or runtime. Use when implementing or refactoring Pi Agent wrappers,…
sentry-debug-issue
sentry
Depure e corrija um problema do Sentry — localize-o (por link, ID ou busca), extraia o contexto completo (stack trace, breadcrumbs, trace, logs), opcionalmente execute a análise de causa raiz do Seer /…
sentry-svelte-sdk
sentry
Configuração completa do SDK do Sentry para Svelte e SvelteKit. Use quando for solicitado "adicionar Sentry ao Svelte", "adicionar Sentry ao SvelteKit", "instalar @sentry/sveltekit" ou configurar…
sentry-svelte-sdk
sentry
Configuração completa do SDK do Sentry para Svelte e SvelteKit. Use quando for solicitado a "adicionar Sentry ao Svelte", "adicionar Sentry ao SvelteKit", "instalar @sentry/sveltekit" ou configurar…
skill-scanner
sentry
Examinar habilidades de agente em busca de problemas de segurança. Use quando solicitado a "examinar uma habilidade",
prompt-optimizer
sentry
Cria, otimiza e refina iterativamente prompts de agente, prompts de sistema, prompts de desenvolvedor e modelos de prompt reutilizáveis. Use quando solicitado a melhorar um...
commit
sentry
commit — uma habilidade instalável para agentes de IA, publicada por getsentry/sentry-docs.