agentleFS
egoxx1egoxx1/unified-master-harness/.agents/skills/project-context/SKILL.md

project-context

Skill1 starsChanged 17 days agoMITView on GitHub

Establish or refresh verified project commands, runtime facts, and repository layout when those facts are unknown, stale, or explicitly requested. Do not use for routine tasks when the existing project profile already answers the question.

34 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use code-review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 5

    Distinctive

    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:

    Use this skill to avoid rediscovering stable project facts every session.

    line 8
  2. Distinctive:

    Do not run it ritualistically before every edit.

    line 18
  3. Very specific:

    Read agent-core/project/profile.md if present.

    line 22
  4. Distinctive:

    If the needed fact is present and still consistent with the relevant files, use it.

    line 23
  5. Distinctive:

    Leave unknown values unknown rather than filling conventional defaults.

    line 32
  6. Distinctive:

    Keep the profile compact. Never store secrets or environment values.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 25 edited versions of this file we could read. “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

Project Context

Use this skill to avoid rediscovering stable project facts every session.

Trigger

Use when:

  • first bootstrapping this environment in a repository,
  • agent-core/project/profile.md is missing,
  • commands/runtime facts are stale or contradicted by the repository,
  • a task depends on a project fact that the profile does not establish.

Do not run it ritualistically before every edit.

Procedure

  1. Read agent-core/project/profile.md if present.
  2. If the needed fact is present and still consistent with the relevant files, use it.
  3. Otherwise run:

    python3 agent-core/scripts/bootstrap_project.py --write
  4. Inspect only source files needed to resolve remaining unknowns: manifests, lockfiles, task-runner files, compose files, relevant README/AGENTS files, and CI workflows when CI behavior matters.
  5. Record only facts supported by repository evidence or a command actually run.
  6. Leave unknown values unknown rather than filling conventional defaults.

Keep the profile compact. Never store secrets or environment values.

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.