nw-ai-workflow-tutorials
AI workflow tutorial patterns — non-deterministic output handling, outcome-based verification, and agent workflow step design
npx skills add majiayu000/claude-skill-registry --skill nw-ai-workflow-tutorials --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# AI Workflow Tutorial Patterns Tutorials for AI-powered tools face a unique challenge: output is non-deterministic. Traditional tutorials show exact expected output; AI workflow tutorials define success by outcome. ## The Non-Determinism Contract State this early in any AI workflow tutorial: ```markdown > **AI output varies between runs.** Your output will look different from > the examples in this tutorial. That is normal. We define success by > what your code *does*, not what the agent *says*. ``` ## Timing Expectations AI agents work in cycles with processing pauses. Users interpret silence as failure. Always set timing expectations: ```markdown ## Step 3: Let the Agent Work (~5 minutes) \`\`\` /nw:deliver "feature description" \`\`\` This takes 3-5 minutes. The agent works in phases with 20-60 second pauses between visible output. This is normal processing, not a hang. ``` Provide a "is it stuck?" diagnostic: ```markdown > **If you see no output for 2+ minutes**: Check the status bar at > the bottom of Claude Code. A pulsing indicator means it is still > working. If the indicator is gone, press Enter to prompt it. ``` ## Output Reading Guide Teach users to read agent output by
- The Non-Determinism Contract
- Timing Expectations
- Output Reading Guide
- Messages You Can Safely Ignore
- Success Verification
- Progressive Trust Building
- Level 1: Micro-success (Step 1-2)
- Level 2: Small feature (Step 3-4)
- Level 3: Full workflow (Step 5+)
- Handling Divergence
- Recovery Patterns
What does the nw-ai-workflow-tutorials skill do?
AI workflow tutorial patterns — non-deterministic output handling, outcome-based verification, and agent workflow step design
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill nw-ai-workflow-tutorials --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.