Agent skill

Refresh Docs

by joselado in 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.

GPL-3.0Auto-check passedDocuments & Office

Install Refresh Docs

skills CLI
$ npx skills add joselado/pyqula --skill refresh-docs -a claude-code

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

GitHub CLI
$ gh skill install joselado/pyqula refresh-docs --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/refresh-docs .claude/skills/refresh-docs && 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
refresh-docs
GitHub stars
145
Token cost
~816 tokens
SKILL.md length
392 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
GPL-3.0

At a glance

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.

  • Works in 5 steps: Recount the test suite → Recount anything else the docs assert → Re-run the static guide checks → …
  • Asked to refresh
  • SKILL.md covers 1. Recount the test suite, 2. Recount anything else the…, 3. Re-run the static guide… and 4. Rebuild the PDF, plus 1 more section
  • Calls python, bash and pytest

What it does

Refresh Docs is an agent skill from 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. Use when asked to refresh, rebuild, or update the docs or the PDF guide, after landing a feature or a batch of fixes, or before a release.

Its SKILL.md is about 820 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 Documents & Office, covering Technical writing, Test generation and PDF. It works with LaTeX. 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

  • Asked to refresh
  • Update the docs
  • After landing a feature
  • A batch of fixes

Example prompts

  • “/refresh-docs”

Requirements

  • Python 3

Workflow steps

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

  1. Recount the test suite
  2. Recount anything else the docs assert
  3. Re-run the static guide checks
  4. Rebuild the PDF
  5. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 49f87c4. 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

    Shell commands in SKILL.md call:

    • python
    • bash
    • pytest

    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

Refresh Docs loads about 816 tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 392 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~816

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 49f87c4, republished under its GPL-3.0 licence (© joselado). 392 words, ~816 tokens.

Download SKILL.mdSave it as .claude/skills/refresh-docs/SKILL.md (or your agent's skills folder).
name
refresh-docs
description
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/user_guide.pdf. Use when asked to refresh, rebuild, or update the docs or the PDF guide, after landing a feature or a batch of fixes, or before a release.

Refreshing the documentation

The guide and the README carry a handful of counted facts that drift silently: nothing fails when they go stale, so they only get fixed when someone looks. This is the sweep that looks.

Do the steps in order. Each one is cheap except the last.

1. Recount the test suite

bash
OUT=<your session scratchpad>/collect.txt
python -m pytest tests --collect-only -q > "$OUT" 2>&1; echo "exit=$?"; tail -3 "$OUT"

Redirect, never pipe. pytest ... | tail reports the pipe's exit status, so a crashed run or an unrecognized arguments error that ran no tests at all both look like success. This is not hypothetical in this repo -- it once masked a fatal interpreter abort. Write the output to the session's scratchpad directory rather than /tmp.

Then find every copy of the old number before editing any of them:

bash
grep -rn "<old count>" --include='*.md' . | grep -v '\.git/'

Today the count lives in CLAUDE.md only, but it has lived in more than one file before; grep so they move together. Leave the 37:34 whole-suite runtime alone unless you actually re-measured it on an idle machine -- that figure was measured three times (33:40, 34:18, 37:34) and re-deriving it costs more than half an hour of an idle machine.

2. Recount anything else the docs assert

The README's tutorial section counts notebooks and how many FUNCTIONALITIES bullets link to one:

bash
find jupyter-notebooks -name '*.ipynb' -not -path '*checkpoint*' | wc -l
ls jupyter-notebooks/functionalities/*.ipynb | wc -l

If a feature landed since the last sweep, the FUNCTIONALITIES list in README.md (section starts at # FUNCTIONALITIES #) may need a bullet, and the user guide a section plus an entry in # Main functions and methods.

Show full SKILL.md (156 more words)Show less

3. Re-run the static guide checks

bash
python -m pytest tests/documentation -v

These parse every snippet in user_guide.md and check (a) that each name a snippet reads is one it defines, imports, or inherits from an earlier snippet in its section, and (b) that every h.<method> / g.<method> / geometry.<factory> the guide names -- in prose as well as code -- exists on the real object. They do not run the physics, so they cannot catch a wrong argument value; they catch the guide having drifted from the library.

4. Rebuild the PDF

bash
(cd documentation && bash convert.sh)

xelatex, not the default pdflatex: the guide contains the Greek letters of the physics prose, and pdflatex fails on the first one it reaches. Confirm the build actually produced something new rather than leaving a stale file:

bash
ls -la documentation/user_guide.pdf

5. Report

Say which numbers moved and what they moved from and to, whether tests/documentation passed, and that the PDF timestamp advanced. If a count was already correct, say so rather than implying you changed it.

© 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/refresh-docs of joselado/pyqula.

Open the folder on GitHubat commit 49f87c4

Compare with similar skills

Refresh Docs 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.

Refresh Docs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Refresh Docs this skilljoselado/pyqula145—~816Automated safety check: PassGPL-3.0
Brief Compliance Checkflonat/flonat-research145—~1.7kAutomated safety check: PassMIT
Harness Book Best Practicewquguru/harness-books3.2k—~4.1kAutomated safety check: PassNone
AI Review SkillNeuroDong/Ai-Review626—~2.5kAutomated safety check: PassMIT
MineruNebutra/MinerU-Skill122—~504Automated safety check: PassMIT
Lecture To Mdysyecust/lecture-to-notes269—~3.9kAutomated safety check: PassCustom licence

Similar skills

  • Brief Compliance Check

    flonat/flonat-research

    Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief.

    145 GitHub stars~1.7k tokensUpdated 8 days ago
    Documents & OfficeAuto-check passed
  • Harness Book Best Practice

    wquguru/harness-books

    Best practices for working on the Harness books repo. An agent skill from wquguru/harness-books.

    3.2k GitHub stars~4.1k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • AI Review Skill

    NeuroDong/Ai-Review

    Generates structured AI paper reviews (SoT style) for LaTeX, PDF, and Word manuscripts.

    626 GitHub stars~2.5k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Mineru

    Nebutra/MinerU-Skill

    An AI-Native skill for parsing PDF / Office / image files into Markdown with MinerU — a fast, zero-config document parser for AI agents.

    122 GitHub stars~504 tokensUpdated 13 days ago
    Documents & OfficeAuto-check passed
  • Lecture To Md

    ysyecust/lecture-to-notes

    把课堂视频(本地或 B 站/YouTube)、文字稿、课件三者(任意组合)整理成一份详细的中文 Markdown 课堂笔记,输出按课程标题命名的 {titlename}.md(首行为 文档标题)+ 相对路径图片。Markdown 工作流,与上游 lecture-to-notes 的 LaTeX/PDF 输出并行存在;上游 skill 完全不动。触发词:markdown 笔记、md 笔记、视频转…

    269 GitHub stars~3.9k tokensUpdated 4 days ago
    Documents & OfficeAuto-check passed
  • Docs Sync

    joselado/dmrgpy

    Update docs/userguide.{md,tex} and docs/documentation.{md,tex} together after a change to dmrgpy, keeping the Markdown and LaTeX versions of each in step and verifying the .tex still compiles under…

    114 GitHub stars~926 tokensUpdated 11 days ago
    Documents & OfficeAuto-check passed

More from joselado/pyqula

  • 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 today
    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 today
    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 today
    Auto-check passed
  • User Guide Voice

    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…

    145 GitHub stars~985 tokensUpdated today
    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 today
    Auto-check passed

Works with

Questions about Refresh Docs

What does Refresh Docs do?

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. Refresh Docs is an agent skill from joselado/pyqula.pdf.

When should I use Refresh Docs?

Refresh Docs fits situations like: asked to refresh; update the docs; after landing a feature; A batch of fixes.

How do I install Refresh Docs in Claude Code?

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

How do I install Refresh Docs in Codex?

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

Can I use Refresh Docs 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 refresh-docs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/refresh-docs, .gemini/skills/refresh-docs, .github/skills/refresh-docs and .opencode/skills/refresh-docs in your project.

What does Refresh Docs need to run?

Going by SKILL.md and its folder, Refresh Docs needs the command-line tools its instructions call (python, bash and pytest). Our summary lists: Python 3.

Does Refresh Docs 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 Refresh Docs 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 Refresh Docs use?

Refresh Docs 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 Refresh Docs use?

About 816 tokens (SKILL.md is roughly 3.3k 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 Refresh Docs?

Skills that share tags, products or a category with Refresh Docs: Brief Compliance Check (flonat/flonat-research, 145 stars), Harness Book Best Practice (wquguru/harness-books, 3.2k stars), AI Review Skill (NeuroDong/Ai-Review, 626 stars) and Mineru (Nebutra/MinerU-Skill, 122 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Refresh Docs?

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.