agentleFS
javiarmestojaviarmesto/ALDC-AL-Development-Collection/skills/al-spec-create/SKILL.md

al-spec-create

Skill115 starsChanged 14 days agoMITView on GitHub

Create or revise the canonical AL technical specification through AL Spec Agent, preserving approved architecture and human approval.

The file

We split this skill into the rules it gives an agent

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

  • 1

    Very specific

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

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

    Use al-spec-agent for the requirement name and complexity given after the command (ask if missing).

    line 10
  2. Distinctive:

    Read and follow the canonical specification contract in full before authoring.

    line 11
  3. Distinctive:

    Do not change the root requirement name to the unit slug or write an aggregate spec.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

AL specification entrypoint

Use al-spec-agent for the requirement name and complexity given after the command (ask if missing). Read and follow the canonical specification contract in full before authoring. This entrypoint does not define another specification workflow. Resolve the role link from this installed skill's directory.

Pass the approved requirement/architecture, current spec path if revising, and any Architect-assigned scope. If this host cannot route to the named custom agent, read that same role contract in the current session and state the routing limit; do not claim another agent executed. Preserve the role's write scope and approval gate. For single-spec the output remains .github/plans/{req_name}/{req_name}.spec.md. For multi-spec pass one assigned SPEC-ID, its exact output path from the approved architecture, architecture revision and required approved predecessor contracts. Do not change the root requirement name to the unit slug or write an aggregate spec. Follow approved authoring groups and preserve both dependency types. Return the assigned spec for current joint consistency review and human approval.

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.