agentleFS
lexvalolexvalo/riverscript-claude-plugin/skills/find-the-moment/SKILL.md

find-the-moment

Skill0 starsChanged 42 days agoMITView on GitHub

Find where something was said in the user's RiverScript transcripts. Use when they ask what was decided, agreed, promised or quoted, when they half-remember a conversation, or when they ask which meeting something came up in.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Call search_transcripts with the phrase the user would have heard, not a paraphrase of their question.

    line 8
  2. Distinctive:

    If two transcripts disagree, say so and give both, with their dates.

    line 13

≈ “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

People rarely remember which transcript holds the thing they are looking for. Start from the words, not from the list.

  1. Call search_transcripts with the phrase the user would have heard, not a paraphrase of their question. For "what did we agree about the price", search price, then pricing, then discount. The search matches the phrase as written, so short and literal beats long and clever.
  2. If nothing comes back, try the other word people use for the same thing, and only then fall back to list_transcripts to see what exists at all. Narrow with from and to when the user gives a time, such as "last month" or "before the launch".
  3. Answer from the passages that come back. Quote the words that settle the question, and say which transcript and date they came from, so the user can open it themselves.
  4. Fetch the full text with get_transcript only when the passage is not enough, for example when the user asks how the discussion went rather than what was decided.

If two transcripts disagree, say so and give both, with their dates. The later one is usually the decision, but say which is which rather than choosing silently.

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.