Automated summary
Structures documentation (READMEs, RFCs, onboarding guides, PR descriptions) to minimize the cognitive load on readers and reviewers.
Strengths
- Ships a reusable default skeleton: lead with the answer, quick path, details, checklist, next step
- Explicitly addresses review-facing docs: what to review first, what is deliberately out of scope, and links across chained PRs
- Favours recognition over recall by pushing tables, checklists, examples and templates instead of prose to memorize
- Provides concrete commands to gauge how much markdown changed and how heavy a PR is
Limitations
- Does not verify that docs match actual code behaviour, that is delegated to docs-alignment-ops
- Does not cover the tone of human review comments, handled by comment-writer-ops
- Tightly coupled to the JARVIS/Gentle AI ecosystem (jarvis-core precedence, linked skills)
Use it when writing or restructuring a README, RFC, onboarding guide, or PR description that is long and hard to scan.
Use it when the only goal is to check that the documentation still reflects the current code behaviour.
Security analysis
CautionLa skill no contiene comandos destructivos, exfiltración, ofuscación ni instrucciones para desactivar salvaguardas. El riesgo es moderado porque declara Bash y usa `git`/`gh`, además de permitir edición/escritura, pero los comandos mostrados son legítimos y orientados a inspeccionar cambios de documentación y metadatos de PR.
- •Declara Bash y usa comandos git/gh; `gh pr view` puede implicar acceso de red a GitHub, aunque sea de solo lectura.
- •Incluye permisos Edit/Write para documentación; es intencional, pero conviene invocarla solo en archivos de docs previstos.
Examples
Rewrite this README so a new contributor can get productive fast: lead with the answer, add a quick path with 3 steps, move edge cases into a details table, and end with a checklist.Write the PR description for my current branch: state what changed and why, say what reviewers should look at first, list what is deliberately out of scope, and add acceptance checklists.This onboarding guide is 3000 words and hard to scan. Restructure it with progressive disclosure, short sections and signposting, keeping the happy path first.name: cognitive-doc-design-ops description: > Diseñar docs con baja carga cognitiva: lead with answer, progressive disclosure, checklists para review. Trigger: README, RFC, onboarding, descripción PR, guías densas o difíciles de escanear. license: Apache-2.0 metadata: author: JARVIS Global (patch) version: "1.0-jarvis" scope: [global] category: planning upstream: Gentleman-Programming/gentle-ai:cognitive-doc-design auto_invoke: - "Redactar o mejorar README, RFC, onboarding o guía" - "Escribir descripción de PR o notas para review" - "Doc largo, denso o difícil de escanear" triggers: cognitive doc design, baja carga cognitiva, PR description, onboarding doc, README structure, review-facing docs related-skills: - jarvis-core - docs-alignment-ops - chained-pr-ops - branch-pr-ops - writing-plans allowed-tools: [Read, Edit, Write, Glob, Grep, Bash]
JARVIS / Cursor (mandatory)
- Precedencia:
jarvis-core> esta skill. Exactitud vs código:docs-alignment-ops. - PRs encadenados: enlazar PR anterior/siguiente y "qué revisar primero" — ver
chained-pr-ops. - Comentarios humanos en review:
comment-writer-ops(tono); esta skill cubre estructura del doc. - Doc: docs/GENTLEMAN_ECOSYSTEM_INTEGRATION.md.
Cognitive Doc Design Ops
Cuándo usar
- Crear o editar documentación que alguien debe entender rápido, retener o usar durante review.
- PR descriptions, guías de contribución, arquitectura, onboarding.
- Doc que se siente largo, denso o difícil de escanear.
Cuándo NO usar: solo verificar que docs = código → docs-alignment-ops.
Patrones críticos
| Patrón | Regla | |--------|-------| | Lead with the answer | Decisión, acción u outcome primero; contexto después | | Progressive disclosure | Happy path primero; detalles, edge cases y refs después | | Chunking | Secciones pequeñas; listas planas cortas | | Signposting | Headings, labels, callouts, resúmenes para orientar al lector | | Recognition over recall | Tablas, checklists, ejemplos y plantillas > prosa memorizable | | Review empathy | El revisor verifica intent sin reconstruir toda la historia |
Forma por defecto
Usar esta estructura salvo que el repo tenga plantilla más fuerte:
# <Título orientado al outcome>
<Un párrafo: qué cambió, a quién ayuda y por qué importa.>
## Quick path
1. <Primera acción>
2. <Segunda acción>
3. <Verificación o resultado esperado>
## Details
| Topic | Decision |
|-------|----------|
| <área> | <explicación concisa> |
## Checklist
- [ ] <El lector puede confirmar esto>
- [ ] <El lector puede confirmar aquello>
## Next step
<Enlace o acción que continúa el flujo.>
PR y docs de review
Reducir burnout del revisor haciendo explícito el camino de review:
- Qué revisar primero.
- Qué queda fuera de scope a propósito.
- Enlaces al PR anterior y siguiente si la cadena es encadenada (
chained-pr-ops). - Una sección = una decisión o unidad de trabajo.
- Checklists para criterios de aceptación y verificación.
Comandos
# Markdown cambiado en la rama actual
git diff --name-only -- '*.md'
# Carga cognitiva del PR (líneas cambiadas)
gh pr view <PR_NUMBER> --json additions,deletions,changedFiles
Skills relacionadas
docs-alignment-ops— docs describen comportamiento actual del código.chained-pr-ops— PRs >400 líneas y navegación entre slices.comment-writer-ops— redactar comentarios humanos en review/issues.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/cognitive-doc-design-ops-mrzxupuk/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/cognitive-doc-design-ops-mrzxupuk' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/cognitive-doc-design-ops-mrzxupuk/download' --output '.skill-downloads/cognitive-doc-design-ops-mrzxupuk/SKILL.md.part' && mv '.skill-downloads/cognitive-doc-design-ops-mrzxupuk/SKILL.md.part' '.skill-downloads/cognitive-doc-design-ops-mrzxupuk/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/cognitive-doc-design-ops-mrzxupuk/SKILL.md' && test -s '.skill-downloads/cognitive-doc-design-ops-mrzxupuk/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/cognitive-doc-design-ops' && cp -R '.skill-downloads/cognitive-doc-design-ops-mrzxupuk' '.claude/skills/cognitive-doc-design-ops'Cursor
test -f '.skill-downloads/cognitive-doc-design-ops-mrzxupuk/SKILL.md' && test -s '.skill-downloads/cognitive-doc-design-ops-mrzxupuk/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/cognitive-doc-design-ops' && cp -R '.skill-downloads/cognitive-doc-design-ops-mrzxupuk' '.cursor/skills/cognitive-doc-design-ops'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/cognitive-doc-design-ops-mrzxupuk'openskills read 'cognitive-doc-design-ops-mrzxupuk'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/cognitive-doc-design-ops-mrzxupuk/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.