agentleFS
bastosbastos/skills/technical-writer/SKILL.md

technical-writer

Skill7 starsChanged 10 months agoMITView on GitHub

Writes and revises clear, precise, accessible technical content for any medium. Use for manuals, wikis, README files, developer and user documentation, tutorials, references, specifications, RFCs, feature requests, issues, commit messages, code comments, review comments, pull request messages, release notes, runbooks, decision records, status updates, email, Slack, and other workplace or agent-facing communication.

46 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

We split this skill into the rules it gives an agent

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 40 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow explicit user instructions and project-specific conventions.

    line 24
  2. Distinctive:

    Follow verified product, code, issue, diff, test, and platform terminology.

    line 25
  3. Distinctive:

    Follow this skill and its references.

    line 26
  4. Distinctive:

    Use the source guide to resolve remaining editorial questions.

    line 27
  5. Distinctive:

    Use one term for one meaning.

    line 33
  6. Distinctive:

    Use direct, active, concrete language.

    line 34
  7. Distinctive:

    Use a conversational, friendly, and respectful voice without filler, hype, slang, or frivolity.

    line 37
  8. Distinctive:

    Prefer concise writing, but never remove necessary conditions, consequences, exceptions, or recovery steps.

    line 38
  9. Distinctive:

    When the artifact type is known, read only the relevant section of the artifact patterns.

    line 46
  10. Distinctive:

    When revising existing writing, preserve valid meaning and domain terminology.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 40 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

Produce the smallest complete artifact that helps the intended reader understand, decide, or act correctly. Preserve technical truth, author intent, and the conventions of the project and medium.

Define the writing contract

Identify from the request and available context:

  • the audience, the audience's knowledge, and the audience's immediate need;
  • the purpose and the outcome the writing must produce;
  • the medium, expected lifespan, publication scope, and required format;
  • the source of truth, known facts, proposals, assumptions, and unknowns;
  • the requested tone, length, terminology, and constraints.

Infer what the evidence supports. Ask only when a missing answer would materially change the result. Do not invent behavior, verification, dates, owners, metrics, compatibility, or status.

Apply guidance in this order:

  1. Follow explicit user instructions and project-specific conventions.
  2. Follow verified product, code, issue, diff, test, and platform terminology.
  3. Follow this skill and its references.
  4. Use the source guide to resolve remaining editorial questions.

Draft for the reader

  • Lead with the answer, outcome, decision, or task.
  • Include the context the reader needs, and remove context the reader does not need.
  • Use one term for one meaning. Match exact names and identifiers from the source of truth.
  • Use direct, active, concrete language. Name the actor, action, object, condition, and success state.
  • Make requirements and limits observable. Preserve uncertainty when the evidence is incomplete.
  • Organize information in the order the reader needs it. Make important information easy to scan.
  • Use a conversational, friendly, and respectful voice without filler, hype, slang, or frivolity.
  • Prefer concise writing, but never remove necessary conditions, consequences, exceptions, or recovery steps.

For detailed language, ambiguity, accessibility, global-audience, normative-wording, and formatting rules, read the core style rules.

Adapt to the medium

Match the structure, detail, tone, and formatting to the artifact. Durable material must remain correct and findable without conversational context. Short-lived messages must make the answer and next action immediately clear.

When the artifact type is known, read only the relevant section of the artifact patterns. Treat each pattern as guidance, not a mandatory template.

When revising existing writing, preserve valid meaning and domain terminology. Do not silently add requirements or factual claims. Surface an ambiguity when the evidence cannot resolve it.

Verify the result

Judge the result by five questions:

  1. Correct: Does every factual claim match the evidence?
  2. Relevant: Does the content address this audience and purpose?
  3. Findable: Can the reader locate the answer or action quickly?
  4. Understandable: Are the language, structure, terms, and references unambiguous?
  5. Usable: Can the reader complete the intended action or decision safely?

Confirm that the writing distinguishes current facts from proposals and unknowns. Check exact names, links, commands, paths, UI labels, dates, units, requirements, and reported verification. Remove repetition and unsupported confidence. Return publishable text unless the user asks for editorial notes.

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.