agentleFS
Microsoft AzureKnown publisherAzure/osdu-spi-stack/.github/skills/prime/SKILL.md

prime

Skill0 starsChanged 42 days agoApache-2.0View on GitHub

Orient in the osdu-spi-stack repo: where decisions and designs live, what is currently changing. Run at session start or when re-orienting after a pause.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research.

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.
  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    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:

    If the shell is unavailable in this environment, say so in one line and go straight to the report using AGENTS.md alone.

    line 35
  2. Very specific:

    Leave out ADR rulings, test and workflow listings, file counts beyond the two index totals, and dependency versions.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 6 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

Prime

Load enough context to navigate osdu-spi-stack and to know where to look for anything else.

AGENTS.md is already in context. It covers the repository map, setup, validation commands, conventions, and scope rules. Do not re-derive or restate any of it. Prime adds what AGENTS.md lacks: the live indexes and the current state of the tree.

Budget: once this skill is loaded, run exactly one shell batch, then write the report, under 20 lines. Nothing in between. No file reads.

1. Capture current state

Run one command:

git log --oneline -8; git status --short --branch; ls docs/decisions docs/design src/spi

The log shows what is moving. The listings are the indexes: ADR and design-doc filenames carry their titles, and src/spi module names describe the CLI's concerns, so nothing needs opening. The CLI's full surface is defined in src/spi/cli.py; open it only when a task touches the CLI.

Translate to the local shell if needed, keeping the three listings labeled per directory the way ls labels them.

If the shell is unavailable in this environment, say so in one line and go straight to the report using AGENTS.md alone. Do not reconstruct the batch with directory-listing tools, web fetches, or subagents; the information is not worth a second attempt.

2. Report

Answer in this shape, then stop. The shape applies to the prime report only; answer later questions in the session normally, without repeating it:

  • Stack one sentence on what the repo deploys and by what mechanism (restating AGENTS.md here is the intentional exception; it makes the report self-contained).
  • Indexes where decisions and designs live, how many of each (count numbered ADRs and substantive design docs, not READMEs or templates), and the rule that a change to the deployment model starts with the governing ADR.
  • In flight the branch, the last few commit subjects, and whether the tree is clean, naming the dirty paths if not.
  • Next two or three candidate entry points, drawn from the stated task if there is one, otherwise from what the recent commits touch.

Leave out ADR rulings, test and workflow listings, file counts beyond the two index totals, and dependency versions. Point at docs/decisions/ rather than reproducing the register; the user will ask for a specific record when they want one.

Out of scope

Source files, test bodies, Bicep modules, Kubernetes manifests, README.md, pyproject.toml, docs/architecture.md, and individual ADRs and design docs stay closed during prime. Open them when a task needs them.

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.