software-design-principles
Skill3 starsChanged 3 months agoMITView on GitHub
Capture, catalogue, and retrieve software design principles discovered during coding sessions. Use this skill when the user asks to "capture a design principle", "remember this principle", "what principles do we have", or "apply our design principles".
2 other projects use a version of this.
Adopted by
Most recently taken up by
- databricks-solutions/consorttheir own version, first seen Oct 25, 2026
- NTCoding/claude-skillztheir own version, first seen Mar 13, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- NTCoding/claude-skillz★ 342same name
- databricks-solutions/consort★ 38same 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 repository74 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adzic-bddSkill
- agent-md-refactorSkill
- agent-muxSkill
- agent-role-impersonatorSkill
- agilquest-reservationsSkill
- ai-text-humanizerSkill
- architecture-decision-recordsSkill
- asd-ste100Skill
- ast-grepSkill
- atacSkill
- aws-cliSkill
- bart-adversarial-reviewerSkill
- branch-doctorSkill
- c4-architectureSkill
- claude-sub-agentSkill
- codemap-config-setupSkill
- codemap-exploreSkill
- codemap-handoffSkill
- codemap-hub-safetySkill
- codemapSkill
- copilot-sub-agentSkill
- daily-standupSkill
- daily-statusSkill
- design-thinkingSkill
- docx-word-processorSkill
- farley-tddSkill
- gemini-sub-agentSkill
- git-commit-formatterSkill
- git-forensicsSkill
- github-actions-permissionsSkill
- github-cliSkill
- git-repo-discoverySkill
- git-safety-guardrailsSkill
- harness-idpSkill
- iteration-plannerSkill
- jira-issue-managerSkill
- justfile-assistantSkill
- kiro-sub-agentSkill
- lessons-learnedSkill
- lisa-planning-agentSkill
- lovejoy-release-agentSkill
- lsp-code-analysisSkill
- macro-to-microSkill
- marge-product-agentSkill
- meeting-notesSkill
- mermaid-diagram-generatorSkill
- modern-cli-overridesSkill
- native-web-searchSkill
- obsidian-notetakerSkill
- outlook-headlessSkill
- pdf-document-processorSkill
- pi-sub-agentSkill
- pptx-slide-processorSkill
- python-publishSkill
- ralph-build-agentSkill
- release-pleaseSkill
- skill-creatorSkill
- skill-managerSkill
- socratic-tutorSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
When the user asks to capture or remember a newly discovered design principle:
- Very specific: line 16
Read the existing catalogue in references/index.md to ensure no duplicates.
- Very specific: line 22
Create a new markdown file in references/principles/<kebab-case-name>.md with:
- Distinctive: line 31
When you are about to make an architectural decision, or the user asks what principles we have:
- Very specific: line 32
Read references/index.md to load the current registry into your context.
- Very specific: line 33
If a principle seems relevant, read its specific references/principles/<name>.md file.
- Distinctive: line 34
Follow Related Principles links — principles that cross-reference each other usually apply together.
≈ “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.
Files
Software Design Principles
Overview
This skill allows you to capture and retrieve software design principles discovered during coding sessions. By cataloging these principles (like the DWIM - "Do What I Mean" pattern), you can build a repository of context-specific architectural and UX patterns that can be re-applied to future problems.
Workflows
1. Capturing a New Principle
When the user asks to capture or remember a newly discovered design principle:
- Identify the core concept, context, and the problem it solves.
- Read the existing catalogue in
references/index.mdto ensure no duplicates. - State the problem and solution in domain-agnostic terms — no specific language, framework, or vendor. The concrete discovery context belongs in the Example, not in the statement of the principle.
- Identify Tags (e.g. UX, Architecture, Refactoring, Security) and any Related Principles already in the catalogue, for cross-referencing.
- Create a new markdown file in
references/principles/<kebab-case-name>.mdwith:- Tags and Related Principles (immediately under the title)
- Context/Problem
- Solution/Pattern
- Example (Use the exact coding context where it was discovered)
- Append a link and a one-sentence summary to
references/index.md. - Confirm with the user that the principle has been saved and summarize it briefly.
2. Retrieving and Applying Principles
When you are about to make an architectural decision, or the user asks what principles we have:
- Read
references/index.mdto load the current registry into your context. - If a principle seems relevant, read its specific
references/principles/<name>.mdfile. - Follow Related Principles links — principles that cross-reference each other usually apply together.
- Suggest the relevant principle(s) based on the user's current task.
- Apply the principle directly to the code you are writing.
Reference Materials
- index.md: The lightweight registry of all captured software design principles.
references/principles/: Directory containing detailed files for each principle.
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.

