From csdlc
Generate a CSDLC Step 0 design doc for a feature, epic, or project. Includes bundled templates for three levels (project, epic, subsystem). Use when the user says "doc", "design doc", "Step 0", "write a design doc", or passes a feature description.
How this skill is triggered — by the user, by Claude, or both
Slash command
/csdlc:csdlc-docThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create a Step 0 design doc for: **$ARGUMENTS**
Create a Step 0 design doc for: $ARGUMENTS
Step 0 is the design doc. It defines the WHAT and WHY before anyone writes a line of code. The output is a doc ready for refinement (/refine) and then story breakdown (/breakdown).
Design docs come in three levels (from PROCESS.md):
| Level | When to use | Template |
|---|---|---|
| Project | New project, full architecture | templates/project-design.md |
| Epic | New feature/epic within an existing project | templates/epic-design.md |
| Subsystem | Architectural boundary or capability | templates/subsystem-design.md |
The test: If you removed it, would multiple unrelated features break? → Subsystem. Would one specific capability disappear? → Epic. Is it a whole new project? → Project.
If the level isn't clear from $ARGUMENTS, ask one question: "Is this a new project, a new feature within an existing project, or defining an architectural boundary?"
If $ARGUMENTS is terse (just a name), ask 2-3 clarifying questions FIRST:
If $ARGUMENTS is already descriptive, proceed — don't over-ask.
Before writing from scratch, check for existing docs:
search_docs) for related design docsRead the appropriate template from templates/ in this skill's directory. Fill it in using the information gathered. Follow these principles:
Output the draft in the conversation so the user can react. Ask:
After user feedback, ask where to save:
create_doc at the appropriate path (projects/{project}/design for project-level, projects/{project}/epics/{epic-name} for epic-level).md fileThen suggest: "Ready for /refine to challenge this, or /breakdown to extract stories?"
npx claudepluginhub danhannah94/claymore-plugins --plugin csdlcProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.