agentleFS
ldaumeldaume/agentic-engineering-harness/skills/writing/writing-engineering/SKILL.md

writing-engineering

Skill3 starsChanged 3 months agoMITView on GitHub

Use whenever writing a commit message, a pull request description, a Confluence technical page, developer or operational documentation, or an engineering decision summary (Commit-Message, PR-Beschreibung, technische Doku). Use it even for a one-line commit; it carries the subject rules, why-before-what, and honest validation reporting. Not for implementing or fixing code, or for deciding whether a change needs an ADR.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Before writing from code, read the repository instructions, the relevant diff or code, the tests, and any linked issue, ADR, or docs.

    line 16
  2. Distinctive:

    If the file is missing (this skill was installed alone), check the artifact's checklist in its reference by hand.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Engineering Writing

Technical writing shortens the distance between intent and correct action. Writing code is not this skill's job; describing it is. For ADR policy and when a decision needs a record, documentation-and-adrs owns the decision; this skill owns the prose.

Repository truth first

Before writing from code, read the repository instructions, the relevant diff or code, the tests, and any linked issue, ADR, or docs; keep established naming and conventions (commit style included), because reviewers check the text against the code and the house style.

Principles

Clear actor, active voice where responsibility matters, consistent terminology, one concept per section, explicit prerequisites, verifiable steps, exact claims. Never claim tests, benchmarks, incidents, deployments, or validation without evidence from the repository or user; write "not tested" instead, because a reviewer trusts the validation section to decide how hard to look.

Route

  • Confluence, durable technical docs: references/confluence.md and references/technical-writing.md
  • pull request description: references/pull-requests.md
  • commit message: references/commits.md

Gate

From this skill's directory, run python3 ../writing-core/scripts/quality_gate.py --artifact <type> --lang <de|en> FILE with type one of pull_request|commit|confluence. If the file is missing (this skill was installed alone), check the artifact's checklist in its reference by hand. Fix every error; judge each warning, because warnings are heuristics, not rules.

Done when

The text states the behavior, the reason, the relevant constraints, and the actual validation at the level its reader needs.

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.