Documentation
by mcollina72b727514771No licenseListed Oct 8, 2026Updated Oct 8, 2026
Creates, structures, and reviews technical documentation following the Diátaxis framework (tutorials, how-to guides, reference, and explanation pages). Use when a user needs to write or reorganize docs, structure a tutorial vs. a how-to guide, build reference docs or API documentation, create explanation pages, choose between Diátaxis documentation types, or improve existing documentation structure. Trigger terms include: documentation structure, Diátaxis, tutorials vs how-to guides, organize docs, user guide, reference docs, technical writing.
Add to a SourceWeft workspace
- Open the skill in your dashboard and add it to a workspace.
- Enable it for the chats that should use it.
This skill is instructions only: it ships no scripts to execute.
Add to SourceWeftYou will be asked to sign in first, then taken straight to this skill.
Ask your agent to install it
Paste this prompt into Claude Code, Codex, Cursor or another agent that can run commands — or into SourceWeft chat. The agent reads this skill's install guide, shows you its source, license and scripts, and installs it with the SourceWeft CLI once you agree.
Read https://sourceweft.com/skills/gh-mcollina-skills-documentation/install.md and install the skill it describes. Before installing, show me its source, license and whether it ships scripts, and wait for my OK. Ask me before changing anything else on my machine.Install it yourself from a terminal
For Claude Code, Codex, Cursor and other local agents. The SourceWeft CLI fetches the skill from its source repository at the commit scanned here, and verifies every file against the hashes recorded when the skill was scanned. If anything differs, nothing is written.
npx @sourceweft/cli skills install gh-mcollina-skills-documentationAdd --agent claude-code, codex, cursor or universal to choose which agent gets it (Claude Code by default).
Upstream installer — not verified by SourceWeft
The open-source skills installer fetches the same pinned commit, but does not check the files against the hashes SourceWeft recorded.
npx skills add https://github.com/mcollina/skills/tree/72b72751477157ebda36203eaffac701ac5df5ae/skills/documentationSource and attribution
Source:mcollina/skillsinskills/documentationat commit72b7275
License: No license
Content belongs to its original authors. SourceWeft indexes it from a public repository.
More from mcollina/skills
Typescript Magician
mcollina
Guides TypeScript type work: generics, conditional and mapped types, type guards, and removing any types.
Snipgrapher
mcollina
Configures and runs the snipgrapher CLI to render syntax-highlighted code snippet images as PNG, SVG or WebP.
Octocat
mcollina
Handles git and GitHub tasks via the gh CLI, including PRs, issues, advisories, and history rewriting.
Skill Optimizer
mcollina
Optimizes AI skills for activation, clarity, and cross-model reliability through benchmarking and release gates.
Init
mcollina
Creates, updates, or prunes an AGENTS.md file with only non-discoverable, high-signal instructions for coding agents.
Linting Neostandard Eslint9
mcollina
Sets up and migrates ESLint v9 flat config with neostandard for JavaScript and TypeScript projects.
More in Writing & Content
Doc Coauthoring
anthropics
Guides users through a three-stage workflow to co-author documentation, proposals, specs and decision docs.
Job Post Builder
anthropics
Builds a hiring packet — job post, interview guide with rubrics, and offer letter template — from a role brief.
Write Spec
anthropics
Turns a feature idea or problem statement into a structured PRD with goals, user stories, requirements and metrics.
Draft Content
anthropics
Drafts marketing content such as blog posts, social posts, newsletters, landing pages, press releases and case studies.
Brand Voice Enforcement
anthropics
Applies existing brand voice guidelines to sales and marketing content, then explains the brand choices made.
Brand Review
anthropics
Reviews marketing content against brand voice, style guide and messaging standards, flagging deviations by severity.