Agent skill

Jarvis Doc Author

by PersonalJarvis in PersonalJarvis/PersonalJarvis

Authoritative skill for writing internal Personal-Jarvis docs under docs/ and sibling directories.

Apache-2.0Auto-check passedDevelopment

Install Jarvis Doc Author

skills CLI
$ npx skills add PersonalJarvis/PersonalJarvis --skill jarvis-doc-author -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install PersonalJarvis/PersonalJarvis jarvis-doc-author --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/PersonalJarvis/PersonalJarvis.git skills-src && mkdir -p .claude/skills && cp -r skills-src/jarvis/skills/builtin/jarvis-doc-author .claude/skills/jarvis-doc-author && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
jarvis-doc-author
GitHub stars
166
Token cost
~3.1k tokens
SKILL.md length
1,274 words
Files
4 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
Apache-2.0

At a glance

Authoritative skill for writing internal Personal-Jarvis docs under docs/ and sibling directories.

  • Works in 5 steps: Classify — which Diataxis quadrant? → Determine the path → Fill in the frontmatter schema → …
  • Fundamentally reworking any Markdown doc under docs/
  • SKILL.md covers When to trigger, Workflow (5 phases), What the skill deliberately… and Reference files, plus 2 more sections
  • Reaches github.com

What it does

Jarvis Doc Author is an agent skill from PersonalJarvis/PersonalJarvis. Authoritative skill for writing internal Personal-Jarvis docs under docs/ and sibling directories. Enforces a Diataxis-compliant classification (concept/how-to/tutorial/reference/troubleshooting/adr), a uniform YAML frontmatter schema, a style canon (active voice, imperative instructions, English prose), and hard anti-patterns (no quadrant mixing, no filler intros, no "Click here"). Use when writing or fundamentally reworking any Markdown doc under docs/.

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/diataxis-quadrants.md`, `references/frontmatter-schema.md` and `references/templates.md`).

It sits in Development, covering Architecture decision records. The repository describes itself as: Your AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows, macOS, Linux. The licence is Apache-2.0.

When your agent uses it

  • Fundamentally reworking any Markdown doc under docs/
  • Tasks that involve Architecture decision records

Example prompts

  • “Click here”
  • “/jarvis-doc-author”

Requirements

  • Python 3
  • Docker

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Classify — which Diataxis quadrant?
  2. Determine the path
  3. Fill in the frontmatter schema
  4. Insert the skeleton + write the content
  5. Self-check before saving

What it can do on your machine

Read from SKILL.md and the folder at commit a7397da. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Jarvis Doc Author loads about 3.1k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 121 tokens; SKILL.md has 1,274 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~12k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from PersonalJarvis/PersonalJarvis at commit a7397da, republished under its Apache-2.0 licence (© PersonalJarvis). 1,274 words, ~3,055 tokens.

Download SKILL.mdSave it as .claude/skills/jarvis-doc-author/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
jarvis-doc-author
description
Authoritative skill for writing internal Personal-Jarvis docs under ``docs/`` and sibling directories. Enforces a Diataxis-compliant classification (concept/how-to/tutorial/reference/troubleshooting/adr), a uniform YAML frontmatter schema, a style canon (active voice, imperative instructions, English prose), and hard anti-patterns (no quadrant mixing, no filler intros, no "Click here"). Use when writing or fundamentally reworking any Markdown doc under ``docs/``.
schema_version
1
version
1.0.0
when_to_use
Use when the user or a worker creates a new Jarvis doc, reworks an existing one, writes an ADR, or produces a phase/test report — even without the word "doc"…
category
meta
tags
meta, docs, authoring, diataxis, documentation, style-guide
author
builtin
license
Apache-2.0
risk_policy.default_tier
monitor
risk_policy.require_confirmation
write_doc_file
config.docs_root
docs

Jarvis Doc Author

When a Jarvis doc is written, the rule is: classify first, then structure, then phrase, then self-check. Not the other way around.

This skill provides the scaffolding. It does not replace thinking — it enforces the discipline that separates a pile of internal Markdown files from a real doc layer (role models: Kubernetes doc site, Docker manuals, GitHub Docs).

When to trigger

Activate this skill when the user (via voice or chat) or a Sub-Jarvis explicitly or implicitly wants to write a new doc or structurally rework an existing doc. Concrete examples:

  • "Schreib ein Doc ueber den BrainManager-Routing-Discipline-Mechanismus." (Write a doc about the BrainManager routing discipline mechanism.)
  • "Leg ein ADR an fuer die Sub-Jarvis-Hard-Cap-Entscheidung." (Create an ADR for the Sub-Jarvis hard-cap decision.)
  • "Dokumentiere wie man einen neuen Brain-Provider hinzufuegt." (Document how to add a new brain provider.)
  • "Fass die Phase-6-Ergebnisse als Test-Report zusammen." (Summarize the Phase 6 results as a test report.)
  • "Mach mir eine How-To fuer das Voice-Bridge-Setup." (Create a how-to for the voice-bridge setup.)
  • A Sub-Jarvis receives the task from the main Jarvis "schreib das in docs/... rein" (write this into docs/...) — then the Sub-Jarvis consults this skill before writing.

Do NOT trigger on:

  • Code comments, docstrings, type hints — those follow the AGENTS.md rule (code identifiers in English), but need no doc scaffold.
  • Commit messages and PR descriptions — those are build artifacts.
  • Memory entries — the auto-memory is responsible for those.
  • Skill authoring — the skill-creator skill exists for that.
  • Voice-output-filter templates or TTS prompts.

Workflow (5 phases)

1. Classify — which Diataxis quadrant?

Question: what does the reader who later opens this doc want to do or understand? Exactly one quadrant wins:

QuadrantWhen...Example doc
concept (explanation)Reader wants to understand why/what it is"BrainManager-Routing-Discipline"
how-toCompetent reader wants to solve a task"Adding a new brain provider"
tutorialLearning reader needs a guided tour"Bringing up Phase-6 Self-Healing from scratch locally"
referenceReader looks for a fact"EventBus event catalog", "jarvis.toml schema"
troubleshootingReader has a symptom"TTS outputs SAPI5 robot voice instead of Cartesia"
adrArchitecture decision with consequences"ADR-0009 Self-Healing-Worker-Critic"

If unsure between tutorial and how-to: does the reader consult the doc while working (time pressure, problem in mind) → how-to. Does the reader go through it away from work to learn → tutorial. (Diataxis test, see references/diataxis-quadrants.md.)

Hard Rule: A doc serves exactly one quadrant. If the doc threatens to serve two, split it into two files with a cross-link. Quadrant mixing is anti-pattern AP-D-1 (see references/templates.md).

2. Determine the path

By quadrant + component. The conventions in the repo (as of 2026-04-28):

QuadrantDefault path
adrdocs/adr/NNNN-slug.md (NNNN = next free 4-digit number)
how-todocs/{component}/howto-{slug}.md
concept / explanationdocs/{component}/concept-{slug}.md or docs/{component}/{slug}.md
referencedocs/{component}/reference-{slug}.md or docs/reference/{slug}.md
tutorialdocs/tutorials/{slug}.md
troubleshootingdocs/troubleshooting/{slug}.md or docs/{component}/troubleshooting-{slug}.md
Phase test reportdocs/phase{N}-{slug}.md (special case, counts as a reference + concept hybrid; an existing convention overrides)

The slug is always lowercase, kebab-case, English (router-discipline, not Router-Disziplin). Never rename a slug — cross-links break otherwise.

For an ADR: check in docs/adr/ which number is next free (ls docs/adr/). Currently ADR-0001 through ADR-0012 are in use; the next free one is ADR-0013.

3. Fill in the frontmatter schema

Every Jarvis doc carries a YAML frontmatter with 7 mandatory fields:

yaml
---
title: "Concept: Router-Discipline"        # display title, in quotes
slug: router-discipline                     # URL-stable, kebab-case, append-only
diataxis: explanation                       # tutorial|howto|reference|explanation|troubleshooting|adr
status: draft                               # draft|active|deprecated
owner: harald                               # who is responsible for correctness
last_reviewed: 2026-04-28                   # ISO date YYYY-MM-DD
phase: 5                                    # master-plan phase: 0|1|1a|1c|2|3|4|5|6|7|L+P|A0..A5|-
---

Optional: tags, related (cross-refs as a list of slugs), deprecates, deprecated_by, audience (developer/operator/end-user — default developer for internal docs), next_review_due (computed from last_reviewed + cadence from config).

Full field definitions + rationale + examples: references/frontmatter-schema.md.

4. Insert the skeleton + write the content

Load the template for the chosen quadrant from references/templates.md (all 6 skeletons, copy-paste-ready). Mandatory and optional sections are marked. Fill in this order:

  1. # H1 = title from frontmatter (no emoji, no Markdown in the title).
  2. 1-2-sentence intro directly under H1, before any H2. Answers: what is the doc, who is it for, what does the reader take away? No "Welcome", no "This document describes..." — straight to the point.
  3. Quadrant-specific mandatory sections (see templates).
  4. Code blocks ALWAYS with a language tag (```python, ```bash, ```toml, ```yaml, ```json). Never bare triple backticks.
  5. ## What's next as a footer block, max 5 bullets, each with a cross-link to a follow-up doc (relative path, not an absolute URL).

Language rules (excerpt — full set in references/templates.md):

  • Active voice + imperative in how-tos and tutorials. "Activate the voice pipeline with set JARVIS_VOICE=1" — not passive constructions.
  • You form — no "the user", no "we" when the reader is meant.
  • Code identifiers in English (BrainManager, jarvis.toml, EventBus), prose in English. Identifiers in backticks, never italics.
  • Spell out acronyms on first occurrence ("Speech-to-Text (STT)").
  • No "obviously" / "simply" / "just" — it humiliates the reader who is struggling and is explicitly forbidden in the Microsoft + Google style guides.
  • No "click here" / "see this link" — the link text describes the target: "see ADR-0011 Router-Discipline", not "see here".
Show full SKILL.md (492 more words)Show less
5. Self-check before saving

Before the file is written, go through the quality checklist from references/templates.md (15 points). The most critical points:

  1. Quadrant lock: Does the doc serve exactly one Diataxis quadrant?
  2. Frontmatter complete: All 7 mandatory fields set?
  3. Title length ≤ 50 characters (max 60, user mandate 2026-04-29): The frontmatter title is the display title in the DocsView sidebar and MUST stay fully readable there. A long explanation belongs in the body H1, not in the sidebar entry. Example: NOT "ADR-0009 — Self-Healing Worker-Critic-Loop with Action/Observation-Invariant" (76 characters), BUT "ADR-0009: Self-Healing Worker-Critic" (37).
  4. Intro before H2: 1-2 sentences, no filler?
  5. Code language tags: Does every code block have a language tag?
  6. Cross-links as relative paths: docs/adr/0009-self-healing.md, not https://github.com/...?
  7. What's next ≤ 5 bullets: Does the footer block respect the K8s cap?
  8. Verification section in how-tos: Concrete pytest command, concrete log marker, concrete Computer-Use step? (Verify-before-ship mandate from AGENTS.md.)
  9. No TODO/FIXME/TBD in the body when status: active? If it is a stub: status: draft in the frontmatter and mark it in the body.

When all 9 points are green: write the file. If a confirmation is needed (risk policy write_doc_file), show the user the path + frontmatter + first 20 lines of body, ask once, then write.

What the skill deliberately omits

Kept deliberately small — Personal-Jarvis is a single-user project. The following is not the job of this skill:

  • Multi-version docs / i18n. All new docs are English (project policy); no translation workflow, no version switch.
  • Card sorting / user tests. Single-user; the information architecture follows the maintainer's own intuition.
  • Editorial review as a separate step. The self-check replaces that; linters catch 80%.
  • Eval framework like skill-creator has. Doc quality is qualitatively measurable; quantitative benchmarks would be overkill.
  • Auto-migration of all existing docs. Existing files follow different patterns; they are adapted opportunistically on re-review, not in a big bang.

Reference files

The detail definitions live in the sibling files. Read the reference file whose topic is currently being asked about — not all of them on spec.

  • references/diataxis-quadrants.md — deep definition of the 4 quadrants, tutorial-vs-how-to test, reference-vs-explanation test, mapping onto Jarvis modules.
  • references/frontmatter-schema.md — all frontmatter fields (mandatory and optional), rationale, examples per doc type, slug rules.
  • references/templates.md — complete skeletons for all 6 doc types, style canon (10 rules), anti-pattern catalog (12 points), quality checklist (15 points).

Anti-pattern quick view

Full list in references/templates.md. These are the five that are broken most often:

  • AP-D-1 Quadrant mixing (tutorial with a reference table).
  • AP-D-2 Concept doc with code snippets without a clear purpose.
  • AP-D-5 How-to without a prerequisites section.
  • AP-D-7 Owner field empty (the doc rots).
  • AP-D-12 A concept explained twice in different places (drift guaranteed — one place explains, all others link).

Trace

Skill execution emits SkillStarted -> SkillStepExecuted (1 step per phase in the workflow) -> SkillCompleted. The write_doc_file step records path + slug + Diataxis quadrant in the step payload, not the full body (token protection; the body lands on disk and is readable from there).

© PersonalJarvis, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in jarvis/skills/builtin/jarvis-doc-author of PersonalJarvis/PersonalJarvis.

  • SKILL.md
  • references/diataxis-quadrants.md
  • references/frontmatter-schema.md
  • references/templates.md

Open the folder on GitHubat commit a7397da

Compare with similar skills

Jarvis Doc Author next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Jarvis Doc Author compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jarvis Doc Author this skillPersonalJarvis/PersonalJarvis166—~3.1kAutomated safety check: PassApache-2.0
Create Vibe Featuremistralai/mistral-vibe5.1k—~1.4kAutomated safety check: PassApache-2.0
Grill With Docsmeain/dotfiles28520 repos~875Automated safety check: PassMIT
Rememberantonio-orionus/Arroxy397—~571Automated safety check: PassMIT
Grounding A Designandrew-blake/melcloudhome142—~1.1kAutomated safety check: PassMIT
Plan TreeSeemSeam/claude_codex_bridge3.6k—~6.3kAutomated safety check: PassCustom licence

Similar skills

  • Create Vibe Feature

    mistralai/mistral-vibe

    Official

    Guides feature work in the Mistral Vibe Python CLI so each change lands in the right module and matches the project's architecture decision records.

    5.1k GitHub stars~1.4k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Grill With Docs

    meain/dotfiles

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise.

    285 GitHub starsUsed in 20 repos~875 tokens
    DevelopmentAuto-check passed
  • Remember

    antonio-orionus/Arroxy

    Persists a durable Arroxy lesson — a gotcha, user preference, workflow rule, or design decision — to the right tracked file (project memory, AGENTS.md, CONTEXT.md, dev-docs, or an ADR) so any coding…

    397 GitHub stars~571 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Grounding A Design

    andrew-blake/melcloudhome

    A skill your agent uses when about to propose, brainstorm, review or revise a design, fix approach or plan for a feature or behaviour change in this repo, including "brief" or "quick" design…

    142 GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Plan Tree

    SeemSeam/claude_codex_bridge

    Maintain a structured planning document tree made of roadmap/status files, implementation status or handoff TODO files, topic notes, decision records, open questions, ideas/inspiration pools, and…

    3.6k GitHub stars~6.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Openchart

    tryopendata/skills

    Generates OpenChart (https://github.com/tryopendata/openchart) chart, table, graph, sankey, tilemap, and geo map specs from data, and guides editorial design decisions.

    142 GitHub stars~11k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed

More from PersonalJarvis/PersonalJarvis

All 12 skills in this repo
  • Skill Creator

    PersonalJarvis/PersonalJarvis

    Creates a new Jarvis skill from the user's description — the assistant writes the whole skill (name, trigger phrase, schedule, steps, spoken answer format) and files it as a draft.

    166 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Drive Jarvis CLI

    PersonalJarvis/PersonalJarvis

    A skill your agent uses when you (a Claude Code / Codex session, or any terminal agent) need to control a running Personal Jarvis instance — switch the brain provider, dispatch or inspect missions…

    166 GitHub stars~945 tokensUpdated today
    Auto-check passed
  • Generate CLI Command

    PersonalJarvis/PersonalJarvis

    Use after building a feature that adds or changes a REST route in jarvis/ui/web/routes.py, as the "definition of done" before committing.

    166 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Phase6 Adr Update

    PersonalJarvis/PersonalJarvis

    A skill your agent uses when a Phase-6 architecture decision needs to be amended or a new Phase-6 ADR needs to be written (e.g.

    166 GitHub stars~893 tokensUpdated today
    Auto-check passed
  • Phase6 Smoke Test

    PersonalJarvis/PersonalJarvis

    A skill your agent uses to run a quick end-to-end smoke test against the Phase-6 Mission-Manager + Critic-Loop.

    166 GitHub stars~725 tokensUpdated today
    Auto-check passed
  • Control API

    PersonalJarvis/PersonalJarvis

    Change Jarvis's own configuration through the local Control API instead of clicking the desktop UI or driving Computer-Use.

    159 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

Questions about Jarvis Doc Author

What does Jarvis Doc Author do?

Authoritative skill for writing internal Personal-Jarvis docs under docs/ and sibling directories. Jarvis Doc Author is an agent skill from PersonalJarvis/PersonalJarvis. Authoritative skill for writing internal Personal-Jarvis docs under docs/ and sibling directories.

When should I use Jarvis Doc Author?

Jarvis Doc Author fits situations like: fundamentally reworking any Markdown doc under docs/; tasks that involve Architecture decision records.

How do I install Jarvis Doc Author in Claude Code?

Run `npx skills add PersonalJarvis/PersonalJarvis --skill jarvis-doc-author -a claude-code`. Or copy the skill folder (jarvis/skills/builtin/jarvis-doc-author in PersonalJarvis/PersonalJarvis) into .claude/skills/jarvis-doc-author in your project. Claude Code loads it when a task matches its description.

How do I install Jarvis Doc Author in Codex?

Run `npx skills add PersonalJarvis/PersonalJarvis --skill jarvis-doc-author -a codex`. Or copy the skill folder (jarvis/skills/builtin/jarvis-doc-author in PersonalJarvis/PersonalJarvis) into .agents/skills/jarvis-doc-author in your project. Codex loads it when a task matches its description.

Can I use Jarvis Doc Author in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PersonalJarvis/PersonalJarvis --skill jarvis-doc-author -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jarvis-doc-author, .gemini/skills/jarvis-doc-author, .github/skills/jarvis-doc-author and .opencode/skills/jarvis-doc-author in your project.

What does Jarvis Doc Author need to run?

SKILL.md names no scripts, command-line tools or credentials: Jarvis Doc Author is instructions for the agent only. Our summary lists: Python 3; Docker.

Does Jarvis Doc Author access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Jarvis Doc Author safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Jarvis Doc Author use?

Jarvis Doc Author is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Jarvis Doc Author use?

About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9k tokens, read only when the agent opens those files.

What are the alternatives to Jarvis Doc Author?

Skills that share tags, products or a category with Jarvis Doc Author: Create Vibe Feature (mistralai/mistral-vibe, 5.1k stars), Grill With Docs (meain/dotfiles, 285 stars), Remember (antonio-orionus/Arroxy, 397 stars) and Grounding A Design (andrew-blake/melcloudhome, 142 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jarvis Doc Author?

PersonalJarvis (a GitHub organization) maintains it in PersonalJarvis/PersonalJarvis, which has 166 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 11, 2026.

Source: PersonalJarvis/PersonalJarvis on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.