agentleFS
metratonmetraton/gaia/skills/fast-queries/SKILL.md

fast-queries

Skill4 starsChanged 4 months agoMITView on GitHub

Use when diagnosing an issue, checking system health, or validating state before deeper investigation

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start with supplied evidence, not a fixed diagnostic script.

    line 8
  2. Very specific:

    Read the injected dispatch kernel: # Your Contract (goal, project, your can_read menu) and # Project context, the dispatch project's …

    line 10
  3. Distinctive:

    Run the smallest authoritative read-only CLI query for the surfaced domain.

    line 18
  4. Distinctive:

    Use native output/filter flags and one command per call.

    line 19
  5. Very specific:

    Do not invoke helpers from .claude/.

    line 23

≈ “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

Fast Queries

Start with supplied evidence, not a fixed diagnostic script.

  1. Read the injected dispatch kernel: # Your Contract (goal, project, your can_read menu) and # Project context, the dispatch project's can_read sections, whole when they fit, else one get-contract pointer per section, else a single count line. A component the goal names that the block does not carry is fetched first (investigation, evidence ladder step 1).
  2. Pull the rest of what the goal needs from the persistent substrate, narrowly scoped. The read vocabulary -- which verb opens which coordinate, what each returns, and the workspace rule -- is in agent-protocol/read-map.md.
  3. Run the smallest authoritative read-only CLI query for the surfaced domain. Use native output/filter flags and one command per call.
  4. Record the query, result, and uncertainty in the contract checkpoint.
  5. Deep-dive only where the evidence identifies a gap or inconsistency.

Do not invoke helpers from .claude/; that tree is an installed/protected surface, not Gaia source. Do not treat a broad health command's exit code as proof of a specific desired state. If investigation forecasts mutation, switch to investigation and collect predictable exact T3 commands before requesting consent.

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.