agentleFS
anotbanotb/management-consulting-plugin/skills/writing-style/SKILL.md

writing-style

Skill62 starsChanged 12 days agoMITView on GitHub

Write and edit consulting analysis, recommendations, reports, decks, and client communications with direct language, proportional detail, and explicit evidence. Use to adapt a consulting deliverable to its audience and remove generic or unsupported claims.

29 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use changeset-scope, skill-prefixes and 5 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.
  • timmo001Skill

    changeset-scope

    Keep all scoped code work contained to the user-defined changeset. Use for implementation, fixes, diagnosis, refactoring, cleanup, and review when explicit instructions, named files, diffs, branches, pull requests, or injected work scopes define the boundary.

    Also in 3 projects that use this

  • timmo001Skill

    skill-prefixes

    Name skills with an owner prefix so they do not collide with shared, imported or other repositories' skills. Use when creating, renaming, importing or reviewing a skill name, especially for repository-local or tool-owned skills.

    Also in 3 projects that use this

  • NVIDIASkill

    testing

    Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 4 projects that use this

  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 3 projects that use this

  • +2 more from timmo001

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 28 edited versions we read keep these.

  • 2

    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 the user's requested voice, audience, format, and length.

    line 13
  2. Distinctive:

    Remove invented rhetorical contrasts, empty praise, question-and-answer headings, and conclusions that repeat the opening.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 28 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

Writing Style

Follow the user's requested voice, audience, format, and length. These are defaults for consulting work, not a requirement to imitate a role or overwrite an approved style.

Lead with the answer or decision the reader needs. Explain the evidence, consequence, trade-off, and action in the detail needed to assess them. Spend more words where the reasoning is difficult; omit routine sections that add no decision value.

Use concrete nouns, active verbs, and natural sentence variation. Define technical terms when the audience needs it. Remove ceremonial openings, inflated adjectives, and stock phrases such as “unlock value” or “in today's rapidly evolving landscape.” Replace them with the specific outcome or mechanism. Use periods, commas, or parentheses instead of em dashes in original prose; preserve quotations and supplied style when required.

Remove invented rhetorical contrasts, empty praise, question-and-answer headings, and conclusions that repeat the opening. A sentence should add a finding, explanation, trade-off, or action. Do not pad a short request into a standard consulting framework.

Use paragraphs for connected reasoning, lists for parallel items, and tables for comparison. Numeric cells can contain a number and unit. Do not enforce a sentence count in every cell, a fixed number of arguments, or a uniform section length. A title should help navigation or state a supported takeaway according to the artifact's purpose.

State supported judgments directly. Calibrate certainty to the evidence rather than stripping all qualifications. Distinguish facts, sourced claims, forecasts, estimates, and opinion. Quantify when defensible, with units, periods, and a basis. Do not turn an unknown into a directional number just to sound specific.

Never invent experience, quotations, research, benchmarks, or sources. “Organizations that do X tend to see Y” still asserts an empirical pattern and needs support. When evidence is absent, explain the mechanism as a hypothesis, mark an example as fictional, or state the missing input. Preserve material contradictions and limitations near the claim.

Put a material caveat beside the affected claim once, with its decision consequence. Keep drafting and validation notes outside client-facing prose when the reader does not need them. Evidence discipline should make the answer usable, not turn every deliverable into an audit of its own limitations.

For a proposed action, identify who would own it and what happens next when the task calls for execution detail. Label suggested owners and dates as proposals. Finish when the requested artifact is complete; avoid adding a menu of unrelated next services.

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.