agentleFS
rumoiirumoii/rumo-engineering-skills/skills/rumo-project-profile/SKILL.md

rumo-project-profile

Skill7 starsChanged 14 days agoMITView on GitHub

Resolve and validate optional private project profiles for other Rumo skills. Use when a workflow needs project-specific repository, frontend, backend, runtime, data, document, or credential configuration that the current repository does not provide, or when creating or checking a profile. Do not use for ordinary repository discovery.

  • Reads credentials

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. Distinctive:

    Use this infrastructure skill when a reusable skill needs project-specific facts that must not be embedded in the public capability …

    line 8
  2. Very specific:

    Run scripts/resolve_profile.py from this skill directory.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Project Profile

Use this infrastructure skill when a reusable skill needs project-specific facts that must not be embedded in the public capability instructions. A profile is optional and can be created before the project or its Git repository exists.

Create a local profile

The public skill includes a generic template and an initializer. It creates a local profile under the user's home directory; it does not create a Git repository, inspect the current Git repository, or write credentials.

py -3 <skill-dir>\scripts\init_profile.py --profile my-project
py -3 <skill-dir>\scripts\verify_profile.py --profiles-root "$env:USERPROFILE\.rumo-skill-profiles"
python3 <skill-dir>/scripts/init_profile.py --profile my-project
python3 <skill-dir>/scripts/verify_profile.py --profiles-root "$HOME/.rumo-skill-profiles"

The initializer creates project.json, the optional section templates, a references/ directory, and a credentials example with empty values. Fill in repository paths, commands, runtime facts, and references only as they become known. Empty arrays and partially completed sections are valid.

Teams may place the same profile directory in a private checkout when they need to share it. That checkout is optional; individual users can keep profiles local.

Resolution

Run scripts/resolve_profile.py from this skill directory. The resolver checks, in order:

  1. --profiles-root.
  2. RUMO_SKILL_PROFILES_REPO.
  3. The profiles repository persisted by the installer in $HOME/.rumo-engineering-skills/config.json.
  4. A sibling rumo-skill-profiles checkout next to the skills repository.
  5. $HOME/.rumo-skill-profiles.

Select a profile with --profile, RUMO_PROJECT_PROFILE, or a unique match against the current Git repository name or origin URL, declared in project.json as match.repository_names, match.remote_contains, or repositories[].name (see templates/README.md). Never guess when multiple profiles match.

py -3 <skill-dir>\scripts\resolve_profile.py --cwd <project-path> --section runtime
python3 <skill-dir>/scripts/resolve_profile.py --cwd <project-path> --section runtime

The command prints JSON metadata only. It never prints credential values. A missing profile is not an error for a generic workflow: continue from repository discovery and ask only for facts that cannot be established safely.

Profile Contract

Each profile directory contains project.json, frontend.json, backend.json, runtime.json, and data.json. Their contents may remain empty until the corresponding project facts exist. documents.json is optional. Large project guidance belongs under references/ and is referenced by relative path from those JSON files.

Credentials may exist only in a local ignored file or a private profiles checkout. Treat credentials.md, credentials.env, and equivalent files as secrets: load only when the requested operation needs them, never print them, and never copy them into the skills repository, logs, reports, tests, or generated evidence.

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.