Agent skill

User Guide Voice

by joselado in joselado/pyqula

The maintainer's writing voice for documentation/userguide.md -- the three registers (chapter prose, section intros, catalogue bullets), the spelling decisions, what not to write, and which chapters…

GPL-3.0Auto-check passedWriting & Content

Install User Guide Voice

skills CLI
$ npx skills add joselado/pyqula --skill user-guide-voice -a claude-code

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

GitHub CLI
$ gh skill install joselado/pyqula user-guide-voice --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/joselado/pyqula.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/user-guide-voice .claude/skills/user-guide-voice && 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
user-guide-voice
GitHub stars
145
Token cost
~985 tokens
SKILL.md length
492 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
GPL-3.0

At a glance

The maintainer's writing voice for documentation/userguide.md -- the three registers (chapter prose, section intros, catalogue bullets), the spelling decisions, what not to write, and which chapters…

  • Tasks that involve Technical writing
  • SKILL.md covers When the guide has to change, README's FUNCTIONALITIES list, What VOICE.md covers, so you… and Maintainer material stays out…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

User Guide Voice is an agent skill from joselado/pyqula. The maintainer's writing voice for documentation/userguide.md -- the three registers (chapter prose, section intros, catalogue bullets), the spelling decisions, what not to write, and which chapters are the maintainer's own prose to fix rather than rewrite. Load this before writing or rewriting a single sentence of the user guide, including when merely adding a section for a new feature, and before touching README.md's FUNCTIONALITIES list. Prose written without it reads like a language model wrote it, which is…

Its SKILL.md is about 990 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 Writing & Content, covering Technical writing. The repository describes itself as: Python library to compute properties of quantum tight binding models, including topological, electronic and magnetic properties and including the effect of many-body interactions. The licence is GPL-3.0.

When your agent uses it

  • Tasks that involve Technical writing

Example prompts

  • “/user-guide-voice”

What it can do on your machine

Read from SKILL.md and the folder at commit a61709a. 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

    No URLs in SKILL.md.

    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

User Guide Voice loads about 985 tokens when it runs. Until then it costs about 144 tokens; SKILL.md has 492 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~144
When it runs · the whole SKILL.md, loaded when a task matches
~985

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 joselado/pyqula at commit a61709a, republished under its GPL-3.0 licence (© joselado). 492 words, ~985 tokens.

Download SKILL.mdSave it as .claude/skills/user-guide-voice/SKILL.md (or your agent's skills folder).
name
user-guide-voice
description
The maintainer's writing voice for documentation/user_guide.md -- the three registers (chapter prose, section intros, catalogue bullets), the spelling decisions, what not to write, and which chapters are the maintainer's own prose to fix rather than rewrite. Load this before writing or rewriting a single sentence of the user guide, including when merely adding a section for a new feature, and before touching README.md's FUNCTIONALITIES list. Prose written without it reads like a language model wrote it, which is the exact failure this exists to prevent.

Writing the pyqula user guide

documentation/VOICE.md is the full reference and is the authority here. Read it before writing -- sections 1 to 4 first, then sections 5 to 8 as a reference while writing, then run the checklist in section 10 before finishing. When something in it disagrees with a sentence the maintainer wrote in the guide, the maintainer's sentence wins.

When the guide has to change

When a change adds or materially changes a user-facing feature, update documentation/user_guide.md, and README.md's FUNCTIONALITIES list where relevant. The existing style for a new feature is a short prose section with the physics and the motivation, a runnable code snippet, and -- for anything with a method on Hamiltonian or Geometry -- an entry in the "Main functions and methods" reference at the end of the guide.

README's FUNCTIONALITIES list

The maintainer's bullets are the model: 3 to 8 words, one noun phrase, no parentheses, no keyword names ("Metal-superconductor transport", "Frequency resolved topological density").

  • A bullet and its [[notebook]] link fit on one rendered line, so the text stays at 75 characters at most. Cut parenthetical lists, backticked keywords and "with/including/ together with" tails. The cut detail becomes the opening paragraph of the notebook.
  • Every bullet links to its own executed notebook in jupyter-notebooks/functionalities/<section>/. A new feature bullet comes with a new notebook, never without one. Two bullets for the same feature become one.
  • In the notebook, show at least one heatmap (a color map over k-space, real space, $(k,\omega)$ or a parameter plane) instead of, or besides, a line plot whenever the physics allows one.
  • Do not re-voice the maintainer's own bullets; fix a typo at most.
Show full SKILL.md (219 more words)Show less

What VOICE.md covers, so you know what you are missing without it

  • Who is speaking to whom: the maintainer writing to a physicist who wants to compute something, never reframing the reader as a beginner
  • Three registers, never mixed inside one paragraph: chapter prose (narrated build-up), section intros ("We will now see how..."), and catalogue bullets (definition-first, no narration). The typical failure is a catalogue bullet that grows a paragraph of narration, or a chapter paragraph that reads like a docstring
  • A calibration table of phrases per 1000 words, including the ones to keep at zero: "worth noting", "notably", "crucially", "importantly", "well-known", "textbook", contractions, em-dashes, exclamation marks
  • Spelling decisions: onsite, mean-field, tight-binding, self-consistent, band structure
  • Sentence length targets, measured on the maintainer's own chapters
  • How a chapter and a section are built, as an eight-step shape
  • Which chapters are the maintainer's own prose -- fix, do not rephrase -- and which are Claude-written and may be converted

Maintainer material stays out of the guide

Pointers into src/ and tests/, benchmark tables, profiling stories, the registry behind a mode= string, the history of a fix, the reason a default was chosen for implementation rather than physical reasons: none of it helps a reader who wants to know what a method computes. It belongs in CLAUDE.md, in the module docstring, or in future_development/.

© joselado, GPL-3.0. 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/user-guide-voice of joselado/pyqula.

Open the folder on GitHubat commit a61709a

Compare with similar skills

User Guide Voice 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.

User Guide Voice compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
User Guide Voice this skilljoselado/pyqula145—~985Automated safety check: PassGPL-3.0
Beads Documentation Style Guidegastownhall/beads28k—~3.2kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins11k10 repos~2.4kAutomated safety check: PassNone
Heym Documentation Articlesheymrun/heym1.1k—~780Automated safety check: PassCustom licence
Chinese Technical Writingleter/zh-tech-writing352—~656Automated safety check: PassMIT
Nbj Write Clearlydaniel-p-green/nbj-write-clearly117—~1.1kAutomated safety check: PassMIT

Similar skills

  • Sets the house style for the beads user docs: the canonical concept model, required terminology, prose and diagram conventions, and checks before docs work is done.

    28k GitHub stars~3.2k tokensUpdated today
    Writing & ContentAuto-check passed
  • Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    11k GitHub starsUsed in 10 repos~2.4k tokens
    Writing & ContentAuto-check passed
  • Creates and updates documentation articles for the Heym platform: category choice, manifest entry, markdown file and cross-links from existing pages.

    1.1k GitHub stars~780 tokensUpdated today
    Writing & ContentAuto-check passed
  • Chinese Technical Writing

    leter/zh-tech-writing

    Sets writing rules for Chinese technical docs: short plain sentences, consistent typography and a checklist for removing AI-sounding filler.

    352 GitHub stars~656 tokensUpdated 15 days ago
    Writing & ContentAuto-check passed
  • Nbj Write Clearly

    daniel-p-green/nbj-write-clearly

    Drafts, revises, and audits reader-first technical and product documentation.

    117 GitHub stars~1.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Developer Docs Technical Writer

    vercel-labs/github-tools

    Official

    Writes, reviews and edits developer documentation for SDKs, libraries and frameworks, from getting-started guides and API references to migration guides.

    130 GitHub stars~3.9k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed

More from joselado/pyqula

  • Refresh Docs

    joselado/pyqula

    Refresh pyqula's documentation after a change - recount the test suite, propagate every number that moved, re-run the static user-guide checks, and rebuild documentation/userguide.pdf.

    145 GitHub stars~816 tokensUpdated 3 days ago
    Auto-check passed
  • Error Conventions

    joselado/pyqula

    How pyqula raises errors -- which exception type for which failure, the registries behind string-selected options (mode=, solver=, channel=, operator names), and the shared Hilbert-space guards in…

    145 GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed
  • New Feature

    joselado/pyqula

    The completeness checklist for adding a user-facing feature to pyqula - where the implementation goes, what kind of test it needs, and the five documentation surfaces that must move with it.

    145 GitHub stars~1.4k tokensUpdated 3 days ago
    Auto-check passed
  • GPU Backend

    joselado/pyqula

    pyqula's CPU/GPU switch (src/pyqula/gpu.py), how a routine is routed onto the device, per-call precision, and the tiered porting plan in documentation/gpuportingplan.md.

    145 GitHub stars~679 tokensUpdated 3 days ago
    Auto-check passed
  • Wannierization

    joselado/pyqula

    pyqula's Wannierization (wanniertk/), what h.getwannierhamiltonian() returns, the disentanglement window keywords and which combinations raise NotImplementedError, and the bundled pure-Python…

    145 GitHub stars~1.2k tokensUpdated 3 days ago
    Auto-check passed

Questions about User Guide Voice

What does User Guide Voice do?

The maintainer's writing voice for documentation/userguide.md -- the three registers (chapter prose, section intros, catalogue bullets), the spelling decisions, what not to write, and which chapters…. User Guide Voice is an agent skill from joselado/pyqula.md -- the three registers (chapter prose, section intros, catalogue bullets), the spelling decisions, what not to write, and which chapters are the maintainer's own prose to fix rather than rewrite.

When should I use User Guide Voice?

User Guide Voice fits situations like: tasks that involve Technical writing.

How do I install User Guide Voice in Claude Code?

Run `npx skills add joselado/pyqula --skill user-guide-voice -a claude-code`. Or copy the skill folder (.claude/skills/user-guide-voice in joselado/pyqula) into .claude/skills/user-guide-voice in your project. Claude Code loads it when a task matches its description.

How do I install User Guide Voice in Codex?

Run `npx skills add joselado/pyqula --skill user-guide-voice -a codex`. Or copy the skill folder (.claude/skills/user-guide-voice in joselado/pyqula) into .agents/skills/user-guide-voice in your project. Codex loads it when a task matches its description.

Can I use User Guide Voice 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 joselado/pyqula --skill user-guide-voice -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/user-guide-voice, .gemini/skills/user-guide-voice, .github/skills/user-guide-voice and .opencode/skills/user-guide-voice in your project.

What does User Guide Voice need to run?

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

Does User Guide Voice access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is User Guide Voice 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 User Guide Voice use?

User Guide Voice is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does User Guide Voice use?

About 985 tokens (SKILL.md is roughly 3.9k 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 User Guide Voice?

Skills that share tags, products or a category with User Guide Voice: Beads Documentation Style Guide (gastownhall/beads, 28k stars), Technical Writing Standard (cursor/plugins, 11k stars), Heym Documentation Articles (heymrun/heym, 1.1k stars) and Chinese Technical Writing (leter/zh-tech-writing, 352 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains User Guide Voice?

joselado (a GitHub user) maintains it in joselado/pyqula, which has 145 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 7, 2026.

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