npx claudepluginhub codagent-ai/agent-skills --plugin codagentThis skill uses the workspace's default tool permissions.
Help turn specs into fully formed technical designs through natural collaborative dialogue.
Generates architecture/design documents from approved SRS docs when no prior design exists, proposing 2-3 approaches with trade-offs and securing section-by-section approval.
Explores project context, asks clarifying questions, proposes 2-3 design approaches with trade-offs, presents designs section-by-section for approval, and writes spec docs before implementation.
Turns ideas into designs before coding features, components, or changes by exploring user intent, requirements, codebase, and alternatives via investigation agents.
Share bugs, ideas, or general feedback.
Help turn specs into fully formed technical designs through natural collaborative dialogue.
Start by reading all spec files in the change's specs/ directory to understand settled requirements, then brainstorm architecture by asking questions one at a time. Once the architecture is clear, present the design and get user approval. When writing the design doc, also apply any spec edits identified during the conversation.
Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.
The spec stage has already settled what the system should do. Do NOT ask questions about behaviors, boundaries, error conditions, or edge cases — those are for the spec skill. Focus exclusively on architecture, patterns, and technical trade-offs.
If you discover a gap in the specs during the design conversation, surface it as a spec implication ("This decision means we need a new scenario in spec Y") rather than re-opening the requirement discussion.
You MUST create a task for each of these items and complete them in order:
specs/ directory before asking any architecture questions. Skip any you just wrote in this session.design.md in the change directory, then edit any spec files identified during the conversationdigraph design {
"Read all spec files" [shape=box];
"Explore project context" [shape=box];
"Ask clarifying questions" [shape=box];
"Propose 2-3 approaches" [shape=box];
"Present design sections" [shape=box];
"User approves design?" [shape=diamond];
"Write design doc + apply spec edits" [shape=box];
"Read all spec files" -> "Explore project context";
"Explore project context" -> "Ask clarifying questions";
"Ask clarifying questions" -> "Propose 2-3 approaches";
"Propose 2-3 approaches" -> "Present design sections";
"Present design sections" -> "User approves design?";
"User approves design?" -> "Present design sections" [label="no, revise"];
"User approves design?" -> "Write design doc + apply spec edits" [label="yes"];
}
Reading the specs:
specs/**/*.md files in the change directory<!-- deferred-to-design: ... --> markersUnderstanding the context:
Asking clarifying questions:
codagent:ask-questions skill for how to ask questions (tool to use, batching strategy, question quality)Tracking spec implications:
Exploring approaches:
Presenting the design:
Write the design document using the Artifact Template below.
Then apply any spec edits identified during the conversation: add new scenarios, revise existing ones, or complete deferred-to-design scenarios. Edit the relevant spec files directly. Only add or revise scenarios — do not restructure the file.
This skill does not invoke other skills or manage sequencing.
codagent:ask-questions — For tool choice and batching strategy when gathering informationUse this structure when writing design.md. Scale each section to its complexity — omit sections that don't apply, keep simple sections to a few sentences.
## Context
<!-- Background and current state -->
## Goals / Non-Goals
**Goals:**
<!-- What this design aims to achieve -->
**Non-Goals:**
<!-- What is explicitly out of scope -->
## Approach
<!-- The design itself: components, how they interact, data flow.
Use diagrams where they help. This is the "what are we building" section. -->
## Decisions
<!-- Key design decisions and rationale -->
## Risks / Trade-offs
<!-- Known risks and trade-offs -->
## Migration Plan
<!-- Steps to deploy, rollback strategy (if applicable) -->
## Open Questions
<!-- Outstanding decisions or unknowns to resolve -->