Agent skill

Org Literate

by natsukium in natsukium/dotfiles

Prose standard for this repository's literate Org configuration documents — first-person narrative voice, scope per setting, paragraph structure, logical rigor, restraint, and banned LLM-sounding…

CC0-1.0Auto-check passedDevelopment

Install Org Literate

skills CLI
$ npx skills add natsukium/dotfiles --skill org-literate -a claude-code

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

GitHub CLI
$ gh skill install natsukium/dotfiles org-literate --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/natsukium/dotfiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/org-literate .claude/skills/org-literate && 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
org-literate
GitHub stars
106
Token cost
~1.7k tokens
SKILL.md length
954 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
CC0-1.0

At a glance

Prose standard for this repository's literate Org configuration documents — first-person narrative voice, scope per setting, paragraph structure, logical rigor, restraint, and banned LLM-sounding…

  • Reviewing prose in .org files (configuration.org
  • SKILL.md covers Formatting, Voice, Scope per setting and Paragraphs and argument, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Org Literate is an agent skill from natsukium/dotfiles. Prose standard for this repository's literate Org configuration documents — first-person narrative voice, scope per setting, paragraph structure, logical rigor, restraint, and banned LLM-sounding English. Use when writing, rewriting, or reviewing prose in .org files (configuration.org, modules/, overlays/, README).

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: Nix dotfiles for NixOS, Darwin and WSL. The licence is CC0-1.0.

When your agent uses it

  • Reviewing prose in .org files (configuration.org

Example prompts

  • “/org-literate”

What it can do on your machine

Read from SKILL.md and the folder at commit ce7dae8. 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.

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

  • Network

    Links to these hosts (documentation or services it may open):

    • gist.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

Org Literate loads about 1.7k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 954 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 natsukium/dotfiles at commit ce7dae8, republished under its CC0-1.0 licence (© natsukium). 954 words, ~1,710 tokens.

Download SKILL.mdSave it as .claude/skills/org-literate/SKILL.md (or your agent's skills folder).
name
org-literate
description
Prose standard for this repository's literate Org configuration documents — first-person narrative voice, scope per setting, paragraph structure, logical rigor, restraint, and banned LLM-sounding English. Use when writing, rewriting, or reviewing prose in *.org files (configuration.org, modules/, overlays/, README).

Prose Standard for Literate Org Documents

Rules for writing and revising prose in this repository's Org documents. Adapted from k16shikano's japanese-tech-writing standard (https://gist.github.com/k16shikano/fd287c3133457c4fd8f5601d34aa817d), translated to English and to the register of a personal configuration narrative.

Formatting

  • Fill-wrap paragraphs at roughly 85 columns, matching the surrounding text.
  • Org markup: =code= for commands, option paths, and file names; ~verbatim~ for literal values; [[url][description]] for links, with proper nouns kept as the description.
  • Fragments of code, diffs, logs, and config belong in src blocks, not inline prose.
  • Bold a repo-specific term at its first definition; refer to it in plain text afterwards.

Voice

This configuration is a story told by its owner. The reader is a guest browsing someone's dotfiles, not a student reading a manual.

  • Narrate decisions in the first person: "I pin this to 0.9 because the 1.x series broke tangling", not "the package is pinned due to breakage".
  • Describe what software does in plain third person: "niri scrolls windows horizontally". First person is for choices, history, and opinions.
  • Real history is welcome ("after the second time a brew upgrade broke Emacs, I moved everything to Nix") — but only if it actually happened.
  • Avoid "we": there is only one author here. Avoid tutorial imperatives ("install X, then run Y") unless the section genuinely is a procedure.
  • Opinions may be blunt. "zsh's completion setup wore me down" is better material than a neutral feature comparison.

Scope per setting

  • Most settings need one or two sentences: what it enables and the visible effect.
  • Reserve the full problem-and-alternatives account for non-obvious trade-offs: architectural choices, package pins, temporary workarounds, forks.
  • Prose explains why and why-not-the-alternative; the code block already shows what. Never paraphrase the code line by line.
  • When a fact can be stated as configuration, state it in the code block even if it only repeats a default. An explicit setting is clearer than a sentence about the default.

Paragraphs and argument

  • One topic per paragraph. The first sentence tells the reader what the paragraph is about.
  • Make the logical link to the previous paragraph explicit at the start ("So", "In practice", "But that same failure…").
  • Argue in one direction: handle objections first, then state the conclusion once. Do not conclude, rebut, and re-conclude.
  • When rejecting an alternative, give the concrete reason in one sentence — a counterfactual often works ("with zsh I would have needed three plugins for this").

Logical rigor

  • Every causal claim carries its mechanism. "Enabling A breaks B" is not an explanation; say through what.
  • Do not promise unconditionally what only holds conditionally. Prefer "usually", "as long as", "when X holds" over blanket guarantees.
  • Do not flatten hedges into assertions when revising. "This seems to be a scheduler issue" stays hedged unless the surrounding text establishes it.
  • One name per concept, document-wide. Once a section introduces a term (profile, feature, overlay), keep using it; do not fall back to vague words like "the tool" or "the AI".
  • Distinct things stay distinct: two pins with two different reasons are not "the same workaround applied twice".

Reader load

  • In prose, prefer the plain description ("the launcher") over the exact identifier when precision isn't needed; the code block carries the exact names.
  • Skip decorative precision — dates, sizes, version numbers — unless the number itself is the point (a 100 MiB request cap that forced a redesign earns its place).
  • Before adding a second example or scene, say what the first one didn't cover.
  • Keep sentences short. A semicolon joining two clauses is a sign the sentence should be two sentences. Colons for elaboration and parentheses for asides are fine.
Show full SKILL.md (360 more words)Show less

Restraint

  • Bold sparingly: one or two per section, at logical pivots only.
  • A dry fact is usually enough. Save the storytelling beat — a short punchy sentence, an exclamation — for a genuine turning point: a migration, a fork, a disaster. At most once per section.
  • No rhetorical questions as transitions, no suspense-building ("little did I know…") as a habit.

Banned LLM English

These phrases add a "sounds thorough" veneer without adding content. Delete or replace on sight; after drafting, re-read against this list.

  • Previews and wrap-ups: "In this section we will explore…", "It's important to note that…", "It's worth noting…", "In summary", "Overall" (when it only restates). State the point directly.
  • Empty adjectives: "crucial", "essential", "key", "robust", "seamless", "comprehensive", "powerful", "cutting-edge" — importance claimed, not shown.
  • Empty verbs: "delve into", "dive deep", "leverage", "utilize", "harness", "streamline", "unlock", "empower", "elevate". Use the plain verb: "use", "run".
  • Connective tics: chains of "Additionally / Moreover / Furthermore"; "when it comes to"; "in terms of". If two facts share a role, join them in one sentence instead of stacking connectives.
  • Formula contrasts: "not just X, but Y" and "it's not about X — it's about Y" as a reflex; rule-of-three lists ("fast, simple, and reliable") where the third item adds nothing.
  • Filler glue: "This ensures that…", "This allows for…" when the sentence only restates the previous one. Keep it only when it adds the mechanism.
  • Contentless intensifiers: "very", "extremely", "incredibly", "significantly".
  • Em dashes are fine, but not as the default connector — more than one per paragraph reads as generated text. Prefer a comma, parentheses, or two sentences.

Headings

A heading names the component or the question the section answers ("Binary cache", "Why not cachix"). Not a procedure ("Setting it up"), and not a spoiler that states the conclusion.

Honesty

  • Do not invent history or motives. If the reason for an old setting is forgotten, say so: "I no longer remember why this is here, and I'm afraid to remove it" is honest and useful.
  • Do not describe as tested what wasn't. "Should also work on darwin, though I haven't tried" keeps the reader oriented.
  • A workaround is a workaround: name the upstream issue and the condition for removing it.

© natsukium, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/org-literate of natsukium/dotfiles.

Open the folder on GitHubat commit ce7dae8

Compare with similar skills

Org Literate 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.

Org Literate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Org Literate this skillnatsukium/dotfiles106—~1.7kAutomated safety check: PassCC0-1.0
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from natsukium/dotfiles

All 10 skills in this repo
  • Pi Review

    natsukium/dotfiles

    Delegate a source-grounded design or code review to a fresh pi CLI process using sol or luna, then address verified findings until no blockers remain.

    106 GitHub stars~972 tokensUpdated yesterday
    Auto-check passed
  • Attmcojp Claude Md

    natsukium/dotfiles

    Change the org-level CLAUDE.md that governs every attmcojp repository.

    106 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check: notes
  • Ghq

    natsukium/dotfiles

    Clone and reuse GitHub/GitLab repositories under a single managed root (ghq root) instead of fetching files one-by-one via gh api/WebFetch or scratch-cloning into /tmp.

    106 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Gui Debug

    natsukium/dotfiles

    Verify a rendering or window-chrome change in any macOS GUI app unattended — find its CGWindowID via JXA, capture that window alone (with per-pixel alpha) using screencapture -l, and read exact RGBA…

    106 GitHub stars~909 tokensUpdated yesterday
    Auto-check passed
  • Gui Debug

    natsukium/dotfiles

    Verify a rendering or window-chrome change in a GUI app unattended on Linux/Wayland under the niri compositor — enumerate windows and read output scale via niri msg --json, capture a specific window…

    106 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Po Translate

    natsukium/dotfiles

    Orchestrate English→Japanese translation of po/ja.po — classify, delegate translation/review to subagents, iterate until clean

    106 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Org Literate

What does Org Literate do?

Prose standard for this repository's literate Org configuration documents — first-person narrative voice, scope per setting, paragraph structure, logical rigor, restraint, and banned LLM-sounding…. Org Literate is an agent skill from natsukium/dotfiles. Prose standard for this repository's literate Org configuration documents — first-person narrative voice, scope per setting, paragraph structure, logical rigor, restraint, and banned LLM-sounding English.

When should I use Org Literate?

Org Literate fits situations like: reviewing prose in .org files (configuration.org.

How do I install Org Literate in Claude Code?

Run `npx skills add natsukium/dotfiles --skill org-literate -a claude-code`. Or copy the skill folder (.claude/skills/org-literate in natsukium/dotfiles) into .claude/skills/org-literate in your project. Claude Code loads it when a task matches its description.

How do I install Org Literate in Codex?

Run `npx skills add natsukium/dotfiles --skill org-literate -a codex`. Or copy the skill folder (.claude/skills/org-literate in natsukium/dotfiles) into .agents/skills/org-literate in your project. Codex loads it when a task matches its description.

Can I use Org Literate 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 natsukium/dotfiles --skill org-literate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/org-literate, .gemini/skills/org-literate, .github/skills/org-literate and .opencode/skills/org-literate in your project.

What does Org Literate need to run?

SKILL.md names no scripts, command-line tools or credentials: Org Literate is instructions for the agent only.

Does Org Literate access the network?

SKILL.md names 1 domain. As links in the text: gist.github.com. This is read from the text; nothing was executed.

Is Org Literate 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 Org Literate use?

Org Literate is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Org Literate use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Org Literate?

Skills that share tags, products or a category with Org Literate: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Org Literate?

natsukium (a GitHub user) maintains it in natsukium/dotfiles, which has 106 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 10, 2026.

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