agentleFS
therealtinhtutetherealtinhtute/mono-harness/skills/tools/mono-write/SKILL.md

mono-write

Skill5 starsChanged 5 days agoMITView on GitHub

Polish a research or learn draft (EN/VI) so it reads naturally, and write CHANGELOG entries and release notes from a commit list. Not for UI copy, marketing or tone changes.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Prefer plain, active, specific words: name the actor.

    line 20
  2. Very specific:

    Follow the file's existing format and sections (Keep a Changelog here, under ## [Unreleased]).

    line 28
  3. Distinctive:

    Write the user-visible effect, not the commit subject.

    line 30
  4. Distinctive:

    Add only changes the commits show.

    line 31

≈ “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

mono-write does two jobs for the mono playbooks (research, ship) and learn. Any other writing (UI copy, marketing, tone changes, Notion reports, prose from scratch) belongs to write from monoclaudian: use it when it is installed; otherwise say it is not installed and stop.

Defer to: git for commit messages and PR text.

Both jobs change wording, never meaning. Keep every fact, caveat, number, citation, link, code span and heading. Source text missing → ask for it and stop. Return the final prose only; explain changes only when asked.

Polish a draft

Edit lightly: cut filler and repetition, fix rhythm within a paragraph, and keep the outline and the author's voice. Restructure sections only when asked.

  • Cut throat-clearing openings, meta-writing (in this section we will explore), and conclusions that restate the body.
  • Cut filler: it is worth noting that, in today's fast-paced landscape, moving forward, this highlights the importance of.
  • Replace formulaic patterns with direct statements: not X, but Y, rhetorical questions, fake suspense, stacked tricolons, bold claims without evidence.
  • Prefer plain, active, specific words: name the actor; use over utilize, show over demonstrate.
  • Vietnamese: cut có thể thấy rằng, điều này cho thấy, nhằm mục đích, đóng vai trò quan trọng, trong bối cảnh hiện nay, một cách hiệu quả; use active voice and avoid calques of English structure; no em-dash; keep common English terms (API, prompt, token); one form of address and one term per concept.
  • Mixed EN/VI: apply each language's rules to its own text and use the same term for the same concept throughout.

CHANGELOG and release notes

Input: the commit list since the last tag (git log --oneline <tag>..HEAD) and the current CHANGELOG.md.

  • Follow the file's existing format and sections (Keep a Changelog here, under ## [Unreleased]).
  • Breaking changes first. Each entry states what changed and the exact migration step the user runs.
  • Write the user-visible effect, not the commit subject. Combine the commits behind one change into one entry; drop CI-only and chore commits unless users see the effect.
  • Add only changes the commits show; an unclear commit → read its diff, not guess.
  • Release notes: the same entries, shortest form, breaking changes on top.

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.