agentleFS
podopodo/design-agent-skills/skills/design-sprint/SKILL.md

design-sprint

Skill32 starsChanged 6 months agoMITView on GitHub

Deeply researches a codebase, designs a feature through an annotated plan file, then decomposes it into an implementable issue hierarchy (parent + sub-issues with dependencies) on GitHub or Backlog. Nothing is published until you approve the exact content. Installs upstream's create-issue skill, which absorbed the earlier design-sprint skill.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

design-sprint

Catalogue stub — full skill: aoshimash/skills (create-issue)

<!-- das:install:start — generated from stub.yaml by `npm run generate`; edit stub.yaml, not this block -->

Decision tree

  1. Is the full skill already installed? Upstream names this skill create-issue, so it installs next to this pointer (the pointer is not replaced).
    • Global: f=~/.agents/skills/create-issue/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
    • Project: f=.agents/skills/create-issue/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
    • installed → the skill is installed as create-issue, invoke it and proceed
    • pointer → go to step 2
  2. Detect scope, then install:

    [ -e ~/.agents/skills/design-sprint ] && echo "global" || echo "project"

    Global:

    npx skills add aoshimash/skills --skill create-issue -g -y

    Project:

    npx skills add aoshimash/skills --skill create-issue -y

    Claude Code: send a command as a chat message starting with ! to run it without leaving the conversation.

Claude Code plugin route:

/plugin marketplace add aoshimash/skills
/plugin install aoshimash-skills@aoshimash-skills

Heads-up

  • Requires: gh CLI installed and authenticated (GitHub issues) or the bee CLI authenticated (Backlog issues); Creates issues on your tracker, only after you approve the exact content
  • License: MIT
  • Name collision: design-sprint is also written by wondelai-skills (its install or its catalogue pointer); installing both overwrites the earlier one.
<!-- das:install:end -->

Invoke after install

  • Skill name: create-issue
  • Trigger phrases: "design sprint", "design and decompose", "create an issue", "plan and create issues"

What it does

Upstream folded its design-sprint workflow into create-issue, which has two flows. The Lightweight Flow files a single well-scoped issue after one batched question round and one draft approval. The Design Flow is the former design sprint:

StepOutput
SetupDetect the issue tracker (GitHub or Backlog) and the repository's issue templates
Research and designDeep codebase reading, then one consolidated plan file (research, design, open questions, split proposal)
Annotation cycleYou annotate the plan inline in the markdown file; the agent revises until it is right
Issue creationAfter one final approval, a parent issue plus sub-issues with dependencies; research findings are kept as an issue comment

Core principles: issues describe motivation and proposal, never implementation steps; ambiguity is resolved before an issue is created; nothing is published without explicit approval; splitting into sub-issues is always a proposal. Needs the gh CLI (GitHub) or the bee CLI (Backlog) authenticated.

When NOT to use

  • Design sprint workshop facilitation (Crazy 8s, HMW, voting) → use pm-skills (Design Sprint section) or wondelai-skills (Knapp's Design Sprint skill)
  • PM discovery without code → use deanpeters-pm-skills or pm-skills
  • Feature planning without issue creation → use plan-design-review
  • Implementing the issues afterwards → upstream's separate implement-issue skill (not installed by this pointer)

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.