agentleFS
ontology-of-everythingontology-of-everything/SemanticSkills/skills/en/concept-design/SKILL.md

concept-design

Skill14 starsChanged 22 days agoApache-2.0View on GitHub

Use only when explicitly invoked. Design, specify, implement, review, refactor, or explain software with Daniel Jackson's concepts and synchronizations. Check CONCEPT.md/SYNCS.md structure and generate Mermaid relationship diagrams.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start from user needs. Concepts define independent behavior.

    line 17
  2. Distinctive:

    Use the reading version by default.

    line 48
  3. Distinctive:

    Read the tool encoding when running the checker or generating diagrams.

    line 49
  4. Distinctive:

    Use Mermaid in Markdown for diagrams.

    line 50

≈ “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

Concept design

Summary of Daniel Jackson's concept design: Application = Concepts + Synchronizations.

“With the concepts in hand, we now associate their actions through synchronizations:” — Daniel Jackson, Concept composition and sync (2022-09-14)

Start from user needs. Concepts define independent behavior; external synchronization rules compose that behavior by specifying which action completions, under which conditions, trigger subsequent actions.

Core constraints

  • Each concept owns state and actions for one purpose; concepts do not invoke one another or read one another's state. External identities carry no internal structure from another concept.
  • The operational principle (OP) illustrates how the purpose is fulfilled through a representative history; it does not replace the full contract or guarantee progress.
  • Composition may restrict behavior but must preserve each concept's contract. Check contracts, OPs, purposes, and application scenarios separately.
  • Each definition has one authoritative source. Distinguish confirmed, proposed, inferred, and open statements; test decisions with evidence, assumptions, and counterexamples. Keep unresolved matters open and unexecuted checks unverified.
  • Compare alternatives, including no change or removal; revisit assumptions after repeated failures. Refactoring preserves behavior; state intentional changes explicitly.

For engineering design, implementation, review, or project rules, apply the architecture contract for directories, naming, responsibilities, and dependencies.

Choose a mode

Select a mode from the request and read only that mode and references needed for the current step. Inspect read-only when intent is unclear; carry existing authorization across modes.

ModePurpose
designDesign concepts and synchronizations
settleConsolidate discussions and decisions
prdWrite the PRD, specifications, and acceptance criteria
buildImplement or refactor against confirmed specifications
reviewReview design and implementation
guardAudit, reconstruct, check drift, specify pipelines, and generate diagrams
refineCompare improvements and apply authorized corrections
explainExplain behavior from specifications and source code

Review, audit, drift, and plan-only requests remain read-only; other changes stay within authorized scope. Do not change specifications to conceal implementation defects.

Expression and verification

Use the reading version by default; expand the specification notation when precision is needed. Read the tool encoding when running the checker or generating diagrams; report unsupported content as unchecked. Use Mermaid in Markdown for diagrams; passing syntax checks does not establish purpose fulfillment, contract conformance, or runtime correctness.

References

  • Concepts and synchronizations: Daniel Jackson, Beyond Objects.
  • Engineering execution: Meng and Jackson, WYSIWID.

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.