agentleFS
fmindfmind/dotfiles/skills/trim/SKILL.md

trim

Skill13 starsChanged 4 days agoMITView on GitHub

Shorten docs, prompts, skills, or configs without losing meaning or behavior.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Report: before/after lines, words, and tokens with the percentage, the categories removed, and any candidate cut you kept because it seemed …

    line 34

≈ “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

Trim

Treat /trim <path> or "too verbose", "too complex", "simplify this" as a request to remove words, lines, and settings that carry nothing, while every fact, behavior, and the author's voice survive. Trimming is not summarizing: when the text is the deliverable (an article, a talk) and the user did not ask for a length, tighten sentences but keep its substance and length class. Arguments can set a target (to 300 words, -40%) or a scope. For code, full-review owns dead code and abstractions; apply these rules only with tests proving behavior.

Workflow

  1. Measure: record lines, words, and estimated tokens (characters / 4) before editing; for skill catalogs and instruction files also run dot agent context --project . --details (add --source . inside the fmind/dot checkout).

    wc -lwm <path>
  2. Map what must survive: list each claim, rule, number, command, flag, link, warning, and authority boundary. For configuration, capture the effective result so the trim can prove it changed nothing: mise tasks ls --json --hidden, mise ls --current --json, mise env --json, and mise settings, dprint resolved-config, ruff check --show-settings <file>, docker compose config, chezmoi cat <target>, or yq -o json for plain data.
  3. Cut, in this order:
    • Duplication: the same rule stated twice; keep it at its owner and link from elsewhere.
    • Restated defaults: settings equal to the installed tool's default, after verifying that default in its current docs or --help (defaults change between versions).
    • Filler: introductions, hedges, recaps, "note that", tool narration, history ("previously…"), and generic tutorials the reader's tools already know.
    • Dead entries: options for tools, paths, or features that no longer exist (prove absence with rg or fd).
    • Verbose constructions: lists that can be one sentence, sentences that can be a clause, examples that only repeat the rule.
  4. Never cut: facts with their evidence, numbers and dates, exact commands and flags, non-obvious gotchas with their reason, security and authority boundaries, links and citations, required structure (frontmatter, anchored headings, generated-index markers), the documentation URL comment at the top of a configuration, comments explaining a non-default choice, and anything the user asked to keep. Preserve the author's voice and stance; do not rewrite into a different style.
  5. Prove equivalence: re-capture the effective configuration and diff it (it must be identical); re-run affected checks and tests; for prose, walk the survival list and confirm each item is still present or deliberately dropped with a reason. Run the repository's formatter and link checks for edited files.
  6. Report: before/after lines, words, and tokens with the percentage, the categories removed, and any candidate cut you kept because it seemed necessary. Ask before removing anything ambiguous instead of guessing.

Gotchas

  • Short is not simple: replacing three explicit lines with a clever one-liner or a dense regular expression makes the file harder to maintain; prefer deleting to compressing.
  • Defaults drift: a setting equal to today's default can still be intentional pinning; keep it when a comment or commit explains it.
  • Search before rewording shared phrases: phrases reused verbatim across files (triggers, error messages, test fixtures) may be matched by tests or other agents; search before rewording.

Documentation

  • Companion skills: repository-docs (documentation ownership), skillify (skill size rules), system-prompts (application prompts).

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.