Anthropic Skills (Official) — Prompts
Prompt 1: webapp-testing — Reconnaissance-Then-Action Pattern
File: skills/webapp-testing/SKILL.md
Technique: Decision-tree prompt with explicit anti-patterns ("Common Pitfall")
## Decision Tree: Choosing Your Approach
User task → Is it static HTML?
├─ Yes → Read HTML file directly to identify selectors
│ ├─ Success → Write Playwright script using selectors
│ └─ Fails/Incomplete → Treat as dynamic (below)
│
└─ No (dynamic webapp) → Is the server already running?
├─ No → Run: python scripts/with_server.py --help
│ Then use the helper + write simplified Playwright script
│
└─ Yes → Reconnaissance-then-action:
1. Navigate and wait for networkidle
2. Take screenshot or inspect DOM
3. Identify selectors from rendered state
4. Execute actions with discovered selectors
## Common Pitfall
❌ **Don't** inspect the DOM before waiting for `networkidle` on dynamic apps
Technique analysis: Flowchart-as-decision-tree prompt with an explicit anti-pattern callout using ❌ emoji. The with_server.py --help instruction ("Always run scripts with --help first") trains the agent to use scripts as black boxes rather than reading their source.
Prompt 2: mcp-builder — Phase-Based MCP Development Guide
File: skills/mcp-builder/SKILL.md
Technique: Phased implementation guide with URL-loading instructions for live documentation
## 🚀 High-Level Workflow
Creating a high-quality MCP server involves four main phases:
### Phase 1: Deep Research and Planning
#### 1.1 Understand Modern MCP Design
**API Coverage vs. Workflow Tools:**
Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations.
**Load framework documentation:**
- **TypeScript SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
Technique analysis: Instructs the agent to fetch live documentation URLs during the skill execution — a "dynamic context loading" pattern that keeps the skill fresh without requiring skill updates when SDK docs change.
File: skills/skill-creator/SKILL.md
Technique: Recursive self-improvement prompt with user communication calibration
## Communicating with the user
The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. If you haven't heard (and how could you, it's only very recently that it started), there's a trend now where the power of Claude is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate.
So please pay attention to context cues to understand how to phrase your communication! In the default case, just to give you some idea:
- "evaluation" and "benchmark" are borderline, but OK
- for "JSON" and "assertion" you want to see serious cues from the user that they know what those things are before using them without explaining them
Technique analysis: Explicit audience-calibration instruction within a skill — unusually sophisticated social awareness encoding. The "plumbers and grandparents" framing is memorable and concrete.
Prompt 4: webapp-testing — Black Box Scripts Instruction
**Always run scripts with `--help` first** to see usage. DO NOT read the source until you try running the script first and find that a customized solution is absolutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts rather than ingested into your context window.
Technique analysis: Context-window preservation instruction. By banning source-reading of helper scripts, the skill prevents agent context pollution — an unusual meta-instruction about token efficiency built into the skill itself.