agentleFS
14ag14ag/claude-skills/technical-writer/SKILL.md

technical-writer

Skill0 starsChanged 3 months agoMITView on GitHub

Technical writing router for software repositories. Use when the user asks to create or improve README, CONTRIBUTING, CHANGELOG, SECURITY, wiki, or community health files; draft or refine GitHub issues, bug reports, feature requests, task issues, or issue templates/forms; edit repository description, homepage, or topics; or write Conventional Commit messages. Do not use for code implementation, debugging, or general prose unrelated to a software project.

48 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use 0-template, github-actions-builder and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JayRHaSkill

    0-template

    Template for creating a new Agent Skill. Copy this folder, rename it to your skill's kebab-case name, and fill in every section. Use this as the starting point whenever you author a new skill for the AgentSkills library.

    Also in 3 projects that use this

  • JayRHaSkill

    github-actions-builder

    Builds reliable, fast, and secure GitHub Actions CI/CD workflows with dependency caching, build matrices, scoped secrets, concurrency control, and reusable/composite workflows. Use this skill when the user asks to "create a GitHub Actions workflow", "set up CI", "add CI/CD", "fix a flaky/slow GitHub Actions pipeline", "add a build matrix", "cache dependencies in CI", "write a reusable workflow", "configure deployment with environments and secrets", or mentions files under .github/workflows.

    Also in 3 projects that use this

  • xcrrrSkill

    proofreader

    Use this skill when reviewing written content for grammar, spelling, punctuation, style consistency, and tone—before publishing, submitting, or sending. Trigger phrases: 'proofread this', 'check my writing', 'review this for errors', 'edit this email/report/essay'. Do NOT use when structural rewrites or content changes are needed—proofreading fixes surface errors, not substantive problems.

    Also in 3 projects that use this

  • zwjbendnSkill

    habit-builder

    Designs and manages healthy habits for sustainable weight loss through lifestyle change. Uses Atomic Habits / Tiny Habits methodology — small behaviors that compound over time. Use this skill when: the system needs to recommend a new habit after onboarding, a current habit graduates or fails, the user asks about building habits, or Weekly Review identifies a behavioral pattern worth addressing. Also use when evaluating habit progress, deciding when a habit has "graduated," or handling a restart after the user falls off. This skill does not send its own reminders — habit check-ins are woven into meal conversations managed by Notification Composer. This skill owns the check-in logic (when, how often, tone); Notification Composer provides the conversation vehicle.

    Also in 4 projects that use this

  • nahisahoSkill

    database-administrator

    Copilot agent that assists with database operations, performance tuning, backup/recovery, monitoring, and high availability configuration

    Also in 3 projects that use this

  • +7 more from JayRHa

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. 0 are common, 12 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep this file lean. Read only the reference files needed for the current task.

    line 16
  2. Very specific:

    Read references/writing-standards.md for every prose task longer than a sentence.

    line 21
  3. Distinctive:

    If the request is unrelated to software-project writing, do not force this skill.

    line 26
  4. Very specific:

    Use this path when the user asks to create or improve repository docs such as README.md, CONTRIBUTING.md, CHANGELOG.md, SECURITY.md, wiki …

    line 33
  5. Distinctive:

    Use this path when the user asks to write or refine:

    line 46
  6. Distinctive:

    Use this path when the user asks to write, rewrite, or improve a git commit message.

    line 62
  7. Distinctive:

    Use this path when the user asks to update repository description, homepage, or topics, especially when the task should flow through a …

    line 70
  8. Distinctive:

    If the request is vague but clearly about repository writing, present this menu:

    line 79
  9. Distinctive:

    If the user already named the artifact they want, skip the menu and route directly to the matching reference.

    line 87
  10. Distinctive:

    Run only when documentation generation is blocked by missing high-impact metadata that cannot be inferred from the repository.

    line 94
  11. Distinctive:

    Run when the user wants to edit repository description, homepage, or topics through the local form before applying changes with GitHub CLI.

    line 109
  12. Very specific:

    Keep generated prose aligned with references/writing-standards.md.

    line 129
  13. Distinctive:

    When the task maps to a repository file, write or update the file in the correct repository location.

    line 130
  14. Distinctive:

    When the task is a GitHub issue or commit message, return the final content in a fenced Markdown block unless the user explicitly asked for …

    line 132
  15. Distinctive:

    All files in this skill folder and their roles:

    line 138

“Common” is measured: kept by at least 6 in 10 of the 42 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Technical Writer

This skill handles repository-facing technical writing for software projects. Keep this file lean. Read only the reference files needed for the current task.

Operating Rules

  1. Identify the narrowest writing job that fully answers the user.
  2. Read references/writing-standards.md for every prose task longer than a sentence.
  3. Load only the task-specific reference that matches the request.
  4. Preserve existing repository facts. Do not invent features, commands, file paths, versions, or workflows.
  5. If the request is unrelated to software-project writing, do not force this skill.

Capability Map

1. Documentation Generation and Refinement

Use this path when the user asks to create or improve repository docs such as README.md, CONTRIBUTING.md, CHANGELOG.md, SECURITY.md, wiki pages, or GitHub community health files.

Read:

  • references/generate-docs.md
  • references/github-community-standards.md when placement or community health rules matter
  • references/ms-engineering-playbook-docs.md when the repository uses Azure DevOps, a code wiki, or the user explicitly wants Microsoft-style docs

2. GitHub Issue Writing

Use this path when the user asks to write or refine:

  • a GitHub issue
  • a bug report
  • a feature request
  • a task or tracking issue
  • issue templates or issue forms

Read:

  • references/issue-writer.md

This is a first-class skill capability. Prefer this path for prompts like "write an issue about the login page crashing", "turn this into a feature request", or "create bug and feature request templates".

3. Commit Message Writing

Use this path when the user asks to write, rewrite, or improve a git commit message.

Read:

  • references/commit-messages.md

4. Repository Metadata Editing

Use this path when the user asks to update repository description, homepage, or topics, especially when the task should flow through a small launch form and GitHub CLI automation.

Read:

  • references/repo-settings.md

Intent Routing

If the request is vague but clearly about repository writing, present this menu:

  • A Generate new documentation
  • B Improve existing documentation
  • C Edit repository details
  • D Compose or refine a GitHub issue
  • E Write a commit message

If the user already named the artifact they want, skip the menu and route directly to the matching reference.

Script Entry Points

scripts/launch-form.ps1

Run only when documentation generation is blocked by missing high-impact metadata that cannot be inferred from the repository.

Command:

pwsh -File scripts/launch-form.ps1 -MissingFields "name,description" -OutputPath "./doc-metadata.json"

Interpretation:

  • On success, read doc-metadata.json and continue the documentation workflow.
  • On failure or no submission, fall back to one consolidated clarification message instead of repeated questions.

scripts/launch-repo-settings.ps1

Run when the user wants to edit repository description, homepage, or topics through the local form before applying changes with GitHub CLI.

Command:

pwsh -File scripts/launch-repo-settings.ps1 -SuggestedTopics "react,typescript,node" -OutputPath "./repo-settings.json"

Interpretation:

  • On success, read repo-settings.json, then apply the values with GitHub CLI if the user asked for automation.
  • On failure or no submission, provide the fields to edit manually and do not assume values.

Supporting assets:

  • scripts/form.html
  • scripts/repo-settings.html

Output Policy

  • Keep generated prose aligned with references/writing-standards.md.
  • When the task maps to a repository file, write or update the file in the correct repository location.
  • When the task is a GitHub issue or commit message, return the final content in a fenced Markdown block unless the user explicitly asked for direct file edits.

File Index

All files in this skill folder and their roles:

FileRole
SKILL.mdRouter and entry point
QA.txtQA checklist for this skill
walkthrough.mdEnd-to-end usage walkthrough
evals/evals.jsonEvaluation prompts and expected outputs for QA testing
references/writing-standards.mdProse style and language rules
references/generate-docs.mdDocumentation generation and improvement workflow
references/github-community-standards.mdGitHub community health file rules
references/issue-writer.mdGitHub issue drafting and template authoring
references/commit-messages.mdConventional Commit message writing
references/repo-settings.mdRepository metadata editing workflow
references/ms-engineering-playbook-docs.mdMicrosoft/Azure DevOps wiki conventions
references/design-log.mdDesign decisions and research notes
references/templates/CODE_OF_CONDUCT.mdCanonical Contributor Covenant v2.1 text
references/templates/CONTRIBUTING.mdCanonical contributing guide template
references/templates/LICENSE-Apache-2.0.txtApache 2.0 license text
references/templates/LICENSE-GPL-3.0.txtGPL 3.0 license text
references/templates/LICENSE-MIT.txtMIT license text
scripts/launch-form.ps1Collects missing metadata via a local form
scripts/launch-repo-settings.ps1Collects repository settings via a local form
scripts/form.htmlSupporting HTML for launch-form.ps1
scripts/repo-settings.htmlSupporting HTML for launch-repo-settings.ps1

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.