Agent skill

Tsh Writing Documentation

by TheSoftwareHouse in TheSoftwareHouse/copilot-collections

Authors and updates repository documentation — README, CHANGELOG, in-repo /docs, and the published documentation site.

MITAuto-check passedDevelopment

Install Tsh Writing Documentation

skills CLI
$ npx skills add TheSoftwareHouse/copilot-collections --skill tsh-writing-documentation -a claude-code

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

GitHub CLI
$ gh skill install TheSoftwareHouse/copilot-collections tsh-writing-documentation --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/TheSoftwareHouse/copilot-collections.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/tsh-writing-documentation .claude/skills/tsh-writing-documentation && 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
tsh-writing-documentation
GitHub stars
284
Token cost
~1.8k tokens
SKILL.md length
881 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Authors and updates repository documentation — README, CHANGELOG, in-repo /docs, and the published documentation site.

  • Editing documentation content without touching product code
  • SKILL.md covers Core Design Principles, Writing for Busy Readers, Documentation Targets and Workflow, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Static sites and blogs

What it does

Tsh Writing Documentation is an agent skill from TheSoftwareHouse/copilot-collections. Authors and updates repository documentation — README, CHANGELOG, in-repo /docs, and the published documentation site. Covers documentation structure, documentation-site build expectations, and the write-vs-review boundary. Use when creating or editing documentation content without touching product code.

Its SKILL.md is about 1.8k 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, covering Static sites and blogs, Changelog and release notes and Technical documentation. The repository describes itself as: Opinionated AI-enabled workflows for product engineering. The licence is MIT.

When your agent uses it

  • Editing documentation content without touching product code
  • Tasks that involve Static sites and blogs
  • Tasks that involve Changelog and release notes

Example prompts

  • “Use the tsh-writing-documentation skill to author and updates repository documentation — README, CHANGELOG, in-repo /docs, and the published…”
  • “/tsh-writing-documentation”

What it can do on your machine

Read from SKILL.md and the folder at commit 2fbe51e. 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

Tsh Writing Documentation loads about 1.8k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 881 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
~1.8k

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 TheSoftwareHouse/copilot-collections at commit 2fbe51e, republished under its MIT licence (© TheSoftwareHouse). 881 words, ~1,790 tokens.

Download SKILL.mdSave it as .claude/skills/tsh-writing-documentation/SKILL.md (or your agent's skills folder).
name
tsh-writing-documentation
description
Authors and updates repository documentation — README, CHANGELOG, in-repo `/docs`, and the published documentation site. Covers documentation structure, documentation-site build expectations, and the write-vs-review boundary. Use when creating or editing documentation content without touching product code.
user-invocable
false

Writing Documentation

Owns repository documentation: authors clear, accurate, and well-structured content and keeps the documentation set internally consistent. README, CHANGELOG, in-repo /docs, and the published documentation site are the targets of that ownership, with explicit conventions for structure, documentation-site builds, and the boundary between writing documentation and writing product code.

Core Design Principles

<principles>
<documentation-scope>
This skill owns repository documentation broadly — content only, never product code. Its targets are README files, CHANGELOG entries, in-repo `/docs` markdown, and the published documentation site. It never writes or edits product code, configuration logic, tests, or infrastructure. When documentation must describe code behavior, read the code to describe it accurately, but do not modify it. If documentation cannot be written without first changing code, stop and report the dependency instead of editing code.
</documentation-scope>
<accuracy-over-volume>
Documentation must describe what the system actually does, not what it might do. Verify every factual claim — file paths, command names, option flags, version numbers, link targets — against the repository before writing it. The reader already understands general concepts; add only the project-specific information they cannot infer. Prefer a short, correct page over a long, speculative one.
Less is more: cut every word, sentence, and section that does not earn its place, because brevity serves the busy reader.
</accuracy-over-volume>
<structure-mirrors-neighbors>
New documentation pages mirror the structure of existing nearby pages rather than introducing a new shape. Match heading order, frontmatter fields, link style, and section naming used by sibling files in the same directory. Consistency across the docs set matters more than any individual stylistic preference.
</structure-mirrors-neighbors>
<links-must-resolve>
Internal documentation links must resolve, so a broken internal link is a build failure, not a cosmetic issue. Only link to pages that already exist or that you create in the same task. Never invent a link target to a page that does not exist; use plain code formatting or an existing valid link instead.
</links-must-resolve>
</principles>

Writing for Busy Readers

The principles in Writing for Busy Readers by Todd Rogers and Jessica Lasky-Fink shape the reader-centered craft rules below.

<busy-reader-craft>
<enough-formatting>
Use headings, lists, and tables only when they improve navigation or comprehension. Remove decorative or redundant formatting that does not help the reader find or understand the content.
</enough-formatting>
<design-for-navigation>
Front-load the conclusion or most important information, and make headings descriptive enough for skimming. Structure pages so a reader scanning quickly can jump to the right section without guessing.
</design-for-navigation>
<make-reading-easy>
Write short sentences, use plain words, keep to one idea per paragraph, and prefer active voice. Avoid jargon unless the reader can reasonably be assumed to know it.
</make-reading-easy>
<show-why-it-matters>
State the purpose and relevance of a page or section early, so readers know why it matters to them. Connect the content to the task they are trying to complete.
</show-why-it-matters>
<make-acting-easy>
End pages or sections with clear next steps or actionable guidance. Make the reader's path forward obvious instead of leaving them to infer what to do next.
</make-acting-easy>
</busy-reader-craft>

Documentation Targets

TargetLocationConventions
READMErepo root README.md and nested README.md filesPlain Markdown; keep headings and tone consistent with the existing file.
CHANGELOGCHANGELOG.mdAppend entries in the existing format; do not rewrite historical entries.
In-repo docs/docs markdownPlain Markdown; follow the structure of neighboring documents.
Documentation sitepublished documentation pagesMarkdown documentation pages with standard frontmatter (sidebar_position, title); internal documentation links must resolve.
Show full SKILL.md (321 more words)Show less

Workflow

Use the checklist below and keep it synchronized with your todo list:

text
Documentation progress:
- [ ] Step 1: Identify the documentation target and audience
- [ ] Step 2: Gather accurate source facts
- [ ] Step 3: Match the neighboring structure
- [ ] Step 4: Write or update the content
- [ ] Step 5: Validate links and the docs build

Step 1: Identify the documentation target and audience. Determine which target type the task touches (README, CHANGELOG, in-repo /docs, or the documentation site), who the reader is, and what they need to accomplish. Confirm the change is documentation-only and not a disguised code change.

Step 2: Gather accurate source facts. Read the relevant code, configuration, and existing documentation to verify every claim you intend to make. Do not document behavior you have not confirmed.

Step 3: Match the neighboring structure. Open one or two sibling pages in the same directory and mirror their frontmatter, heading order, link conventions, and section naming. For the documentation site, reuse the established page shape for that section (agent pages, skill pages, prompt pages).

Step 4: Write or update the content. Write concise, accurate prose. Keep edits scoped to the documentation files named in the task. Do not touch product code, tests, or infrastructure. When writing prose, apply the reader-centered craft rules in Writing for Busy Readers above.

Step 5: Validate links and the documentation build. For documentation-site changes, run the documentation site build; broken internal links must resolve or the build fails. For README, CHANGELOG, and /docs changes, verify referenced paths and links resolve manually. Fix issues before handing off.

Write vs. Review

This skill writes and updates documentation. It does not perform formal code review or design review. When a documentation change depends on a product-code change, report the dependency to the orchestrator rather than making the code change. When the documentation needs sign-off on technical accuracy beyond what the source files reveal, surface the open question instead of guessing.

Connected Skills

  • tsh-technical-context-discovering - to confirm project conventions and existing documentation patterns before writing.
  • tsh-codebase-analysing - to read and understand the code or artifacts a documentation page must accurately describe.
  • tsh-creating-instructions - to keep declarative project rules in instruction files rather than narrative documentation.

© TheSoftwareHouse, MIT. 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 .github/skills/tsh-writing-documentation of TheSoftwareHouse/copilot-collections.

Open the folder on GitHubat commit 2fbe51e

Compare with similar skills

Tsh Writing Documentation 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.

Tsh Writing Documentation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tsh Writing Documentation this skillTheSoftwareHouse/copilot-collections284—~1.8kAutomated safety check: PassMIT
Docs Guardsickn33/agentic-awesome-skills47k1 repos~2kAutomated safety check: PassMIT
Manor Doc Maintenancemanor-os/manor-ai162—~581Automated safety check: PassCustom licence
Simple Englishmoeru-ai/airi50k2 repos~4.6kAutomated safety check: PassMIT
Changesetwithastro/astro63k—~1.1kAutomated safety check: PassCustom licence
Writing Commentswithastro/astro63k—~2.7kAutomated safety check: PassCustom licence

Similar skills

  • Docs Guard

    sickn33/agentic-awesome-skills

    Review generated or changed documentation before it ships, including READMEs, API references, docstrings, changelogs, tutorials, and documentation sites.

    47k GitHub starsUsed in 1 repo~2k tokens
    DevelopmentAuto-check passed
  • Manor Doc Maintenance

    manor-os/manor-ai

    A skill your agent uses when Manor README, docs-site, public screenshots/videos, release-ready wording, quickstart, configuration docs, roadmap, changelog, API docs, or public self-hosted…

    162 GitHub stars~581 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed
  • Changeset

    withastro/astro

    Official

    Create a changeset for the Astro monorepo. An agent skill from withastro/astro.

    63k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Writing Comments

    withastro/astro

    Official

    How to write JSDoc (/ /) and inline (//) comments in the Astro codebase, for contributors reading the source — not end users.

    63k GitHub stars~2.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Fern Navigation

    ai-dynamo/dynamo

    Knowledge of Fern's site-level navigation and structure configuration — how a docs site is organized in docs.yml (and product/version .yml files) using sections, pages, folders, tabs, tab variants…

    8.3k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed

More from TheSoftwareHouse/copilot-collections

All 21 skills in this repo
  • Tsh Creating Skills

    TheSoftwareHouse/copilot-collections

    Create new skills (SKILL.md) for GitHub Copilot. An agent skill from TheSoftwareHouse/copilot-collections.

    284 GitHub stars~4.1k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Implementing Frontend

    TheSoftwareHouse/copilot-collections

    Frontend component patterns, composition, design token integration, barrel file organization, error handling, and Figma-to-code workflow.

    284 GitHub stars~2.6k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Implementing Terraform Modules

    TheSoftwareHouse/copilot-collections

    Build reusable Terraform modules for AWS, Azure, and GCP infrastructure following infrastructure-as-code best practices.

    284 GitHub stars~1.6k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Optimizing Frontend

    TheSoftwareHouse/copilot-collections

    Frontend rendering optimization, code splitting, memoization strategies, bundle size control, asset optimization, and memory management.

    284 GitHub stars~4.1k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Reviewing Frontend

    TheSoftwareHouse/copilot-collections

    Frontend-specific code review criteria, component anti-patterns, hooks quality, rendering correctness, accessibility and performance spot-checks, and module organization issues.

    284 GitHub stars~4.4k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Writing Hooks

    TheSoftwareHouse/copilot-collections

    Custom hook and composable patterns — naming, composition, stable return shapes, lifecycle cleanup, and testing strategies.

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

Categories

Questions about Tsh Writing Documentation

What does Tsh Writing Documentation do?

Authors and updates repository documentation — README, CHANGELOG, in-repo /docs, and the published documentation site. Tsh Writing Documentation is an agent skill from TheSoftwareHouse/copilot-collections. Authors and updates repository documentation — README, CHANGELOG, in-repo /docs, and the published documentation site.

When should I use Tsh Writing Documentation?

Tsh Writing Documentation fits situations like: editing documentation content without touching product code; tasks that involve Static sites and blogs; tasks that involve Changelog and release notes.

How do I install Tsh Writing Documentation in Claude Code?

Run `npx skills add TheSoftwareHouse/copilot-collections --skill tsh-writing-documentation -a claude-code`. Or copy the skill folder (.github/skills/tsh-writing-documentation in TheSoftwareHouse/copilot-collections) into .claude/skills/tsh-writing-documentation in your project. Claude Code loads it when a task matches its description.

How do I install Tsh Writing Documentation in Codex?

Run `npx skills add TheSoftwareHouse/copilot-collections --skill tsh-writing-documentation -a codex`. Or copy the skill folder (.github/skills/tsh-writing-documentation in TheSoftwareHouse/copilot-collections) into .agents/skills/tsh-writing-documentation in your project. Codex loads it when a task matches its description.

Can I use Tsh Writing Documentation 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 TheSoftwareHouse/copilot-collections --skill tsh-writing-documentation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tsh-writing-documentation, .gemini/skills/tsh-writing-documentation, .github/skills/tsh-writing-documentation and .opencode/skills/tsh-writing-documentation in your project.

What does Tsh Writing Documentation need to run?

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

Does Tsh Writing Documentation 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 Tsh Writing Documentation 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 Tsh Writing Documentation use?

Tsh Writing Documentation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tsh Writing Documentation use?

About 1.8k tokens (SKILL.md is roughly 7.2k 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 Tsh Writing Documentation?

Skills that share tags, products or a category with Tsh Writing Documentation: Docs Guard (sickn33/agentic-awesome-skills, 47k stars), Manor Doc Maintenance (manor-os/manor-ai, 162 stars), Simple English (moeru-ai/airi, 50k stars) and Changeset (withastro/astro, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tsh Writing Documentation?

TheSoftwareHouse (a GitHub organization) maintains it in TheSoftwareHouse/copilot-collections, which has 284 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 5, 2026.

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