agentleFS
Sign inStart free
edilson-silvaedilson-silva/codride/.agents/skills/warm-up/SKILL.md

warm-up

Skill2 starsChanged 2 months agoMITView on GitHub

Load product and engineering context before starting work

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are 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.

  • 5

    Very specific

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

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

    If it doesn't exist yet, say so and skip this step — it can be generated with meta-preferences.

    line 14
  2. Very specific:

    Read docs/business-context/index.md if it exists.

    line 18
  3. Very specific:

    If docs/business-context/ doesn't exist yet, say so and skip this step — it can be generated with bootstrap-business-docs.

    line 20
  4. Distinctive:

    Keep in mind what other files it points to (ADRs, conventions, tech stack) without reading those yet either.

    line 28
  5. Very specific:

    If docs/technical-context/ doesn't exist yet, say so and skip this step — it can be generated with engineer-discover (lightweight) or …

    line 30
  6. Very specific:

    Read the root README.md. Keep a list of the files under docs/ in context so you can refer to them later as needed, without reading all of …

    line 34
  7. Distinctive:

    If the user named a specific project (in a monorepo or multi-project workspace), focus this warm-up on that project.

    line 36

≈ “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

Warm-up

Load both the product and engineering context for this project before starting work — not everything, just the entry points, so you know what exists and can pull in the rest later as the need arises.

1. Project preferences (docs/PROJECT_PREFERENCES.md)

Read docs/PROJECT_PREFERENCES.md if it exists, and apply its settings for the rest of this session — e.g. the language for any docs/ or .codex/work/ artifact you write (context.md, architecture.md, plan.md, business-context files, etc.). This doesn't affect conversational language — keep replying in whatever language the human writes in, as usual.

If it doesn't exist yet, say so and skip this step — it can be generated with meta-preferences.

2. Product context (docs/business-context/)

Read docs/business-context/index.md if it exists. Keep in mind what it points to (product strategy, customer personas, competitive landscape, feature catalog, etc.) without reading those files yet.

If docs/business-context/ doesn't exist yet, say so and skip this step — it can be generated with bootstrap-business-docs.

3. Engineering context (docs/technical-context/)

This folder can take two different shapes depending on which skill generated it — read whichever of these exists:

  • docs/technical-context/project-briefing.md — from engineer-discover. Compact (~150 lines), meant to be read in full.
  • docs/technical-context/index.md — from bootstrap-tech-docs. Points to a fuller set (project charter, ADRs, codebase guide, business logic, API spec, etc.) — read the index, not everything it links to.

Keep in mind what other files it points to (ADRs, conventions, tech stack) without reading those yet either.

If docs/technical-context/ doesn't exist yet, say so and skip this step — it can be generated with engineer-discover (lightweight) or bootstrap-tech-docs (comprehensive).

4. Project overview

Read the root README.md. Keep a list of the files under docs/ in context so you can refer to them later as needed, without reading all of them up front.

If the user named a specific project (in a monorepo or multi-project workspace), focus this warm-up on that project.

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.

Reviews can't be read right now.

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.

Check your setup, free