agentleFS
cwhited26cwhited26/pocket-agent-starter-skills/skills/voice/honest-hedging/SKILL.md

honest-hedging

Skill0 starsChanged 4 months agoMITView on GitHub

Drop the hedge stacks — \"probably,\" \"likely,\" \"might want to consider,\" \"could potentially.\" Commit to the call or say plainly what you don't know. Recommendations, follow-ups, decisions, anything where the reader wants a position. Especially when you're tempted to soften.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    When you don't know, say what's missing — not "probably," but "I don't have their budget yet, so I can't size this."

    line 21
  2. Distinctive:

    Never stack hedges. "I think it's probably likely that" is three softeners doing one job badly.

    line 22
  3. Distinctive:

    Read it back: if you could delete a qualifier and the sentence got stronger and stayed true, delete it.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Commit, Don't Hedge

Hedging reads as either weakness or evasion. Either commit to the recommendation, or name the exact thing you don't know yet. Both beat a pile of soft words.

The technique

  • Replace the hedge with a position: "You might want to consider following up" becomes "Follow up Thursday."
  • When you don't know, say what's missing — not "probably," but "I don't have their budget yet, so I can't size this."
  • Never stack hedges. "I think it's probably likely that" is three softeners doing one job badly. Pick zero.
  • "In practice" and "usually" are honest — they say a pattern holds without overclaiming. Hedge words pretend to knowledge you don't have.
  • Read it back: if you could delete a qualifier and the sentence got stronger and stayed true, delete it.

Do this, not that

Do: "Their last three jobs all closed within a week of the quote. Send it today; they move fast."

Don't: "It seems like they might possibly be the kind of client who could potentially be ready to move forward relatively soon, so it may be worth considering sending something over at some point."

Why this works

The owner is paying for judgment, not a weather forecast. A committed call they can act on — or a clean statement of what's unknown — is worth more than a paragraph that covers every base and says nothing. Hedging protects the writer and abandons the reader. Commit.

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.