agentleFS
Sign inStart free
mmaripanguecmmaripanguec/dev-sdd-kit/.claude/skills/as-is/SKILL.md

as-is

Skill2 starsChanged 4 months agoMITView on GitHub

Query the repository's real as-is map (modules, dependencies, APIs, data). Use when asked how the application is structured, what depends on what, which APIs exist, or before designing (F5).

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    If the question is about INTENT (why it is this way, where it is heading), complement with specs/ and knowledge/decisions/ — the as-is says …

    line 31

≈ “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

LIVE state (computed now, not persisted)

  • Registered repos: !. scripts/repo-lib.sh 2>/dev/null && registry_repos | tr '\n' ' '
  • Working tree: !git status --short 2>/dev/null | head -15
  • Latest map seal: !head -2 knowledge/as-is/INDEX.md 2>/dev/null | tail -1

Instructions

  1. Compare the seal date with the latest change in the repos (git -C repos/<repo> log -1 --format=%cs). If the map fell behind, WARN that it may be outdated and suggest /as-is-sync before architecture decisions.
  2. CODE GRAPH FIRST: for fine-grained structure questions (which functions exist, who calls whom, call chains, impact of a change) use the codebase-memory MCP — search_graph, trace_path, get_architecture, get_code_snippet — over the indexed repos (list_projects to see which ones). If a repo is not indexed, say so and suggest /repo-add or index_repository.
  3. The markdown map is the persisted, citable backup. Load ONLY the view relevant to the question:
    • System overview / which repo does what / who calls whom → knowledge/as-is/system.md
    • Structure of ONE repo → knowledge/as-is/<repo>/modules.md
    • Contracts/endpoints of ONE repo → knowledge/as-is/<repo>/api-surface.md
  4. Answer citing the source (file and seal, or graph query) — traceability always.
  5. If the question is about INTENT (why it is this way, where it is heading), complement with specs/ and knowledge/decisions/ — the as-is says WHAT THERE IS, the ADRs say WHY and the to-be WHAT THERE SHOULD BE. Point out gaps.

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