agentleFS
thesawdawgthesawdawg/agent-skills/constructor/SKILL.md

constructor

Skill2 starsChanged 57 days agoMITView on GitHub

Design application architecture, folder structure, dependencies, specifications, and implementation milestones from an existing brief or user requirements.

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. Distinctive:

    When specifications or milestones are requested, use spec and plan with the agreed requirements.

    line 26
  2. Very specific:

    Default output: constructor-output/architecture-doc.md, with sections for needs, architecture, folder structure, dependencies, security, …

    line 30
  3. Distinctive:

    Use the architecture template selectively.

    line 32

≈ “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

Constructor

Turn agreed requirements into a maintainable design and, when requested, an implementation plan. Read supplied artifacts first; an ideator-generated brief is optional. Ask only for missing constraints that affect a decision.

  1. Identify state, request shape, trust boundaries, expected scale, team capacity, and operational constraints. Respect existing stack decisions.
  2. Recommend an architecture with its costs, alternatives where meaningful, and conditions for revisiting it. Consult architecture patterns as needed.
  3. Include a concrete folder tree, entry points, domain/data boundaries, configuration, and test locations. Use the folder template if useful.
  4. Recommend only needed dependencies, checking current primary documentation for compatibility and maintenance. The catalog is a starting point, not proof of current versions. Explain replacement cost.
  5. Identify security/data-protection decisions and unresolved risks. Incorporate an existing security plan; request specialist input only when it changes the design. No mandatory agent handoff.
  6. When specifications or milestones are requested, use spec and plan with the agreed requirements. Include ordered tasks, acceptance criteria, dependencies, and a first vertical slice.

Default output: constructor-output/architecture-doc.md, with sections for needs, architecture, folder structure, dependencies, security, and optional plan. Use the architecture template selectively. Split documents only for independent consumption, size, or user preference. Existing separate output files remain supported inputs; do not rewrite them just for consistency. Implementation is a separate action governed by the user's task.

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.