architect-4r
Skill14 starsChanged 22 days agoApache-2.0View on GitHub
Use only when explicitly invoked. Describe existing software architecture from code or context using Li Yunhua's 4R method. Align on views, roles, and key scenarios, then draw architecture and scenario diagrams.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ontology-of-everything/concept-skillsword for word, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- ontology-of-everything/concept-skills★ 14100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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-frontend-feature-firstSkill
- architect-frontend-fsdSkill
- concept-designSkill
- 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
2 rules. About 0 are common, 2 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Draw relations: After aligning on roles, draw one architecture diagram per view.
- Distinctive: line 32
When you start drawing, read the diagram reference for notation, diagram selection, and an example.
≈ “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
4R system modeling framework
Describe existing architecture from code or context the user provides. Use Li Yunhua's 4R method to explain the selected system's top-level structure and operating rules.
| Element | What to explain |
| Rank | The level of decomposition you are looking at. The top level is relative to the selected system. A role at one level can expand into a system at the next. |
| Role | The units that make up this level and the responsibilities each carries. |
| Relation | The connections between roles, such as calls, notifications, sharing, or dependencies. |
| Rule | How roles work together to deliver a system function, including triggers, order, outcomes, and failures that affect the result. |
A perspective sets the focus. The level determines how far you break down the system. Use one level of detail per architecture diagram. Ground roles, relations, and rules in code, configuration, documentation, or the user's account. Mark inferences and gaps where they appear. If a gap changes a role boundary or a key interaction, ask one focused question first.
Workflow
- Select views. State the question to answer. List relevant options, such as business, system, application, and physical deployment. Give each option a system boundary, level of detail, and question it answers. Recommend one or two options and invite the user to select one or more, add an option, or leave a note. Reuse any choices the user has made.
- Align on roles. After view selection, list every internal role supported by the evidence at that view's level. Give each role a one-sentence responsibility. Name the owner of any key state. List external participants separately and flag gaps. If the evidence supports different groupings, recommend one, offer one alternative, and explain how the responsibilities differ. Ask the user to review the roster and invite additions, merges, splits, or notes.
- Draw relations. After aligning on roles, draw one architecture diagram per view. Use its title and boundary for Rank, and nodes and directed edges for Role and Relation. Label edges by purpose and distinguish runtime communication from source dependencies as appropriate to the view.
- Select scenarios and draw rules. List supported key scenarios by view. Say which part of the collaboration each scenario explains and mark your recommendations. Let the user select multiple scenarios, add one, or name a branch to focus on. Reuse scenarios the user has specified. Draw one Rule diagram per selected scenario and choose the diagram type yourself. Use a sequence diagram for interactions, a flowchart for decisions, or a state diagram for transitions.
When you start drawing, read the diagram reference for notation, diagram selection, and an example. Before delivery, check that the architecture diagram covers the agreed roles, names match across diagrams, and key scenario interactions map to relations in the architecture diagram.
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.

