agentleFS
cezarafcezaraf/avc-template/.agents/skills/avc-scout/SKILL.md

avc-scout

Skill0 starsChanged 3 months agoMITView on GitHub

Explore an active AVC/XP story read-only to establish the smallest factual code, test, command, runtime, prior-memory, and risk surface before a build or amendment decision.

The file

We split this skill into the rules it gives an agent

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

  • 2

    Very specific

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

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

    Follow .avc/roles/scout.md.

    line 8
  2. Distinctive:

    Run the cheapest safe command that establishes the baseline.

    line 13
  3. Very specific:

    Do not edit. Return every key from .avc/templates/agent-result.yaml with exact argv and exit code.

    line 18

≈ “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

Scout the next signal

Follow .avc/roles/scout.md. Require the active run id, revision, tree/HEAD, question, and stop condition. Search targeted symbols and files first. Query ai-memory for prior decisions or gotchas when they may change the next decision, then verify them in the current tree.

Run the cheapest safe command that establishes the baseline. Separate observed facts, configuration, general capability, hypotheses, and unproved behavior. Identify confirmed risk impacts separately from keyword/path signals. Recommend only the next one to three observable nodes and their minimal paths.

Do not edit. Return every key from .avc/templates/agent-result.yaml with exact argv and exit code. Stop when the requested baseline and surface are factual.

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.