agentleFS
Sign inStart free
troskatertroskater/flowdeck-claude/skills/fd-map/SKILL.md

fd-map

Skill0 starsChanged 23 days agoMITView on GitHub

Maps the current project's tech stack, module layout, entry points, conventions and dependencies in a read-only subagent. FlowDeck's fd-task calls this once to build the project-level architecture summary.

The file

We split this skill into the rules it gives an agent

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

  • 2

    Very specific

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

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

    Read the package and build manifests (package.json, pyproject.toml, requirements.txt, Cargo.toml, go.mod, pom.xml, build.gradle, and …

    line 12
  2. Very specific:

    If an LSP tool is available, use its document symbols to outline large entry-point files.

    line 16
  3. Distinctive:

    Put anything you could not determine under Unknown.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Map the codebase in the current working directory. Report only what you can see in the files. Do not guess, and do not write or edit anything.

  1. Read the package and build manifests (package.json, pyproject.toml, requirements.txt, Cargo.toml, go.mod, pom.xml, build.gradle, and similar) for the stack, versions and dependencies.
  2. Glob the source tree (src/, app/, lib/, cmd/, or whatever the project uses) to get the module layout. Ignore node_modules, target, dist, build, .git and vendored code.
  3. Find the entry points: the main files, server or CLI bootstraps, route tables, and scripts in the manifest.
  4. Note the conventions you can see: naming, layering, where tests live and what runner they use, lint and format config.
  5. If an LSP tool is available, use its document symbols to outline large entry-point files. Otherwise Read with offset and limit, or Grep the definition keywords. Do not read whole large files.

Return a Markdown summary with these sections, citing a file path for each claim:

Tech stack

Module layout

Entry points

Conventions

External dependencies

Test setup

Unknown

Put anything you could not determine under Unknown. Do not pad the other sections.

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.

Check your setup, free