agentleFS
Sign inStart free
ericpardeeericpardee/agent-files/skills/deliverable-check/SKILL.md

deliverable-check

Skill3 starsChanged 4 months agoMITView on GitHub

Use before any client-facing or stakeholder-facing deliverable ships (report, email draft, Jira/Slack post, doc) - lints for metaspeak (references to prior drafts, revisions, feedback, the writing process), em/en dashes, and the "isn't just" trope. Triggers on "check this before I send it", "lint the report", "is this clean", or /deliverable-check <file>.

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:

    Run the linter on the deliverable file(s).

    line 21
  2. Distinctive:

    Only then present, post, or send the deliverable.

    line 25

≈ “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

Deliverable Check

Deliverables must read as standalone artifacts written by a fresh author. This skill makes that rule mechanical instead of remembered.

Usage

python3 ~/.claude/skills/deliverable-check/scripts/lint.py <file> [<file> ...]

Exit 0 clean, 1 findings (printed as file:line: [rule] text), 2 read error.

Workflow

  1. Run the linter on the deliverable file(s).
  2. Fix every finding by rewriting the sentence as if no prior version ever existed. Do not delete content the reader needs; restate it standalone.
  3. Re-run until clean.
  4. Only then present, post, or send the deliverable.

What it catches

  • Metaspeak: "as discussed", "per your feedback", "updated to reflect", "previous draft", "I've revised", "now includes", and similar references to drafts, revisions, reviewers, or process.
  • Em and en dashes (house style bans them).
  • The "isn't just X, it's Y" trope.

Limits

The regex list is a floor, not a ceiling. After a clean lint, do one human-eye pass for subtler process references the patterns cannot catch (for example a paragraph that only makes sense if the reader saw an earlier version). Add any new offender you meet to scripts/lint.py in the same turn.

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.

Check your setup, free