daymade/claude-code-skills — Prompt Excerpts
Excerpt 1: skill-creator SKILL.md (Anthropic fork)
Technique: AskUserQuestion pattern + progressive iteration loop (meta-skill authoring)
---
name: skill-creator
description: Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
---
# Skill Creator
At a high level, the process of creating a skill goes like this:
- Decide what you want the skill to do and roughly how it should do it
- Write a draft of the skill
- Create a few test prompts and run claude-with-access-to-the-skill on them
- Help the user evaluate the results both qualitatively and quantitatively
Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages.
### Using AskUserQuestion (Critical — Read This)
**Use the AskUserQuestion tool aggressively at every decision point.**
Every AskUserQuestion MUST follow this structure:
1. **Re-ground**: State the skill name, current phase, and what just happened (1-2 sentences)
2. **Simplify**: Explain the decision in plain language. No function names or internal jargon.
3. **Recommend**: Lead with your recommendation and a one-line reason why.
4. **Options**: Provide 2-4 concrete, lettered choices.
Rules:
- One decision per question — never batch unrelated choices
- Accept the user's choice — nudge on tradeoffs but never refuse to proceed
- Skip the question if there's an obvious answer (just state what you'll do)
Analysis: AskUserQuestion structured invocation pattern is the most explicit UX design in any skill in this batch. Re-grounding instruction ("State the skill name, current phase") is a specific anti-context-loss technique.
Excerpt 2: qa-expert SKILL.md
Technique: One-command initialization + autonomous master prompt pattern
## Quick Start
**One-command initialization**:
```bash
python scripts/init_qa_project.py <project-name> [output-directory]
What gets created:
- Directory structure (
tests/docs/, tests/e2e/, tests/fixtures/)
- Tracking CSVs (
TEST-EXECUTION-TRACKING.csv, BUG-TRACKING-TEMPLATE.csv)
- Documentation templates (
BASELINE-METRICS.md, WEEKLY-PROGRESS-REPORT.md)
- Master QA Prompt for autonomous execution
For autonomous execution (recommended): See references/master_qa_prompt.md — single copy-paste command for 100x speedup.
**Analysis**: "Master prompt" as a separate reference file (loaded on demand) implements progressive disclosure for complex workflows. The "100x speedup" claim for autonomous execution is a rare concrete performance benchmark in skill documentation.