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

writing-editorial

Skill3 starsChanged 3 months agoMITView on GitHub

Use whenever drafting or revising an email, a Slack message, a decision request, a follow-up, or a summary for a PO, manager, C-level, or customer, in German or English (Mail schreiben, Slack-Nachricht, Zusammenfassung, Executive Summary, Management-Update). Use it even for a two-line mail or ping; it carries the point-context-ask structure, tone rules, and golden examples. Not for marketing copy, product status or roadmaps, PRs, or commits.

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:

    Default order: observation, meaning, implication, recommendation, next step.

    line 30
  2. Distinctive:

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

    line 45

≈ “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

Editorial

Move a relationship or a decision forward with the least reading effort. Not for marketing campaigns or web copy (writing-marketing), product status or roadmaps (writing-product), or PRs and commits (writing-engineering), because those formats have different jobs.

Shared contract

Apply writing-core when it is installed; in short: purpose before prose, one primary reader change, direct and specific language, no defensive explanation, no invented facts, idiomatic target language (US English by default, native German, never translated).

Route

  • Email (personal, business, request, follow-up, decline, escalation): read references/emails.md.
  • Slack: read references/slack.md.
  • PO, management, C-level, or customer summary: read references/summaries.md.

Communication model

Default order: observation, meaning, implication, recommendation, next step. For sensitive messages keep observation and inference visibly apart, because a reader who feels judged stops reading the facts.

Compression

Cut a detail only when it does not change decision, risk, timing, cost, ownership, customer impact, reversibility, or uncertainty. Executive writing is decision compression, not just a shorter technical text.

Gate

From this skill's directory, run python3 ../writing-core/scripts/quality_gate.py --artifact <type> --lang <de|en> FILE with type one of business_email|slack|po_summary|executive_summary. 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 reader knows what matters and what happens next, who does it, and by when, without reconstructing it from background.

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.