agentleFS
elxecutorelxecutor/skills/acquaint/SKILL.md

acquaint

Skill3 starsChanged yesterdayMITView on GitHub

Read AGENTS.md and its linked guidance to identify a workspace's conventions, workflows, constraints, and environment rules. Use at the start of a session or when the user asks to review project instructions.

The file

We split this skill into the rules it gives an agent

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

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If neither exists, ask the user for the path

    line 17
  2. Very specific:

    Read AGENTS.md and extract relative links (e.g., ./docs/COLLABORATION.md)

    line 19
  3. Distinctive:

    Only surface issues (broken links, ambiguities) that affect the ability to work

    line 32

≈ “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

Acquaint

Goal

Know what to do in the context of this project — not to summarize files, but to extract actionable guidance for how to behave, what workflows to follow, and what constraints apply.

Steps

  1. Locate AGENTS.md
    • Try ./AGENTS.md (workspace root)
    • Try ~/.local/share/opencode/AGENTS.md (opencode config)
    • If neither exists, ask the user for the path
  2. Read AGENTS.md and extract relative links (e.g., ./docs/COLLABORATION.md)
    • Resolve paths relative to the file's location
    • Skip broken links; note them for the user
  3. Extract actionable knowledge:
    • Behavioral expectations — how should the agent act? (proactive vs reactive, when to ask, when to act)
    • Workflows — git branching, testing, linting, commit conventions, PR process
    • Constraints — what NOT to do (no sudo, no committing secrets, no unprompted commits)
    • Environment — venv paths, tool locations, system-specific rules
    • Missing/broken files — report any linked docs that couldn't be read
  4. Internalize, don't recite
    • The output of this skill is the agent's understanding, not a report to the user
    • Only surface issues (broken links, ambiguities) that affect the ability to work

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.