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
- ontology-of-everything/concept-skillsword for word, first seen Nov 1, 2026
- gwonvibe/gwonvibe-agent-skillstheir own version, first seen Oct 3, 2026
- Abhinavbwj/Skills-Architectstheir own version, first seen Apr 15, 2026
Other versions3 projects use a version of this.
Word for word · 1
- ontology-of-everything/concept-skills★ 14100% same
Edited · 0
None found.
Wrote their own version · 2
- Abhinavbwj/Skills-Architects★ 291same name
- gwonvibe/gwonvibe-agent-skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-dx-cliSkill
- architect-4cSkill
- architect-4rSkill
- architect-frontend-feature-firstSkill
- architect-frontend-fsdSkill
- concept-modelSkill
- data-knowledge-architectSkill
- personal-knowledge-architectSkill
- read-it-reframe-it-own-itSkill
- simplify-javaSkill
- agent-dx-cli-cnSkill
- architect-4c-cnSkill
- architect-4r-cnSkill
- architect-frontend-feature-first-cnSkill
- architect-frontend-fsd-cnSkill
- concept-design-cnSkill
- concept-model-cnSkill
- data-knowledge-architect-cnSkill
- personal-knowledge-architect-cnSkill
- read-it-reframe-it-own-it-cnSkill
- simplify-java-cnSkill
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
- Distinctive: line 17
Start from user needs. Concepts define independent behavior.
- Distinctive: line 48
Use the reading version by default.
- Distinctive: line 49
Read the tool encoding when running the checker or generating diagrams.
- Distinctive: line 50
Use Mermaid in Markdown for diagrams.
≈ “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.
Files
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.
| Mode | Purpose |
| design | Design concepts and synchronizations |
| settle | Consolidate discussions and decisions |
| prd | Write the PRD, specifications, and acceptance criteria |
| build | Implement or refactor against confirmed specifications |
| review | Review design and implementation |
| guard | Audit, reconstruct, check drift, specify pipelines, and generate diagrams |
| refine | Compare improvements and apply authorized corrections |
| explain | Explain 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.
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
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.

