agentleFS
Sign inStart free
Reraise-aiReraise-ai/reraise-kit-claude/skills/decision-proposals/SKILL.md

decision-proposals

Skill0 starsChanged 27 days agoApache-2.0View on GitHub

Use when the user makes or states a decision ("we do X", "I choose Y", "decided", "lo hacemos", "wir machen"), or when you notice one in the conversation. Captures it as a proposal with the user's exact words, for the user to confirm.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Only with both quote and ref is the user named as the decider.

    line 20
  2. Distinctive:

    Never give a decision a number (E-1, E-2, ...).

    line 26
  3. Very specific:

    Never write a decision with card_write.

    line 27
  4. Distinctive:

    Never capture your own suggestion as the user's decision.

    line 28

≈ “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

Decision proposals

A decision belongs to the human who made it. You only capture it.

When the user decides something

  1. Call proposal_create with:
    • question: what was decided, as a question.
    • proposal: the choice.
    • options: the alternatives, if they were named.
    • quote: the user's sentence, word for word, copied from their message. Never paraphrase, never invent.
    • ref: where it was said, as claude-code:<session>@<time> (use today's date and time if you have no session id).
    • expected_outcome and review_date if the user said what they expect and when to look again.
    • language: the language of the user's message.
  2. Only with both quote and ref is the user named as the decider. If you cannot quote the user exactly, leave both out: it then stays your proposal.
  3. Tell the user in one line: "Saved as proposal B-... for you to confirm." It is not a decision until they confirm it.

Never

  • Never give a decision a number (E-1, E-2, ...). Numbers come only from the decision log tool after confirmation.
  • Never write a decision with card_write.
  • Never capture your own suggestion as the user's decision.

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