Prompt Engineering Patterns
This skill should be used when the user asks to "optimize a prompt".
Works in any agent
2 static scans, 0 counted findings.
Recorded for this package revision; Edge checks the exact bundle again when your agent loads it.
What this skill does for you
This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", "debug prompt issues", "use chain-of-thought", "structured prompting", "few-shot prompting", or wants to apply advanced prompt engineering patterns for production LLM applications.
Quoted from the skill description in the pinned sourceUse it with Edge
Set up Edge for me: read getedge.cc/SKILL.md and follow it. Then use Edge to load the prompt-engineering-patterns skill from wshobson/agents.
Paste it into Claude, ChatGPT, Codex or Cursor.
Or read the skill source first.
Security evidence
| Scanner | Date | Result | Findings |
|---|---|---|---|
| Edge static checks | 2026-09-29 | Pass | 0 |
| Edge committed-secret checks | 2026-09-29 | Pass | 0 |
Static scans check the code, not how well the skill works.
Scanner scope, raw findings and mirrored provider records
Edge static checks (Edge-run): edge-static/1.0.0. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Revision: 156b7a5e7a8b93642628a339ee4039c925b34c7f. Raw findings: not supplied. Counted findings: .
Edge committed-secret checks (Edge-run): edge-secrets/1.0.0. Scope: Credentials committed in the skill's files (values never shown). Revision: 156b7a5e7a8b93642628a339ee4039c925b34c7f. Raw findings: not supplied. Counted findings: .
Socket (skills.sh mirror): Version unavailable. Scope: Not supplied by the mirrored record. Revision: not supplied. Raw findings: not supplied. Counted findings: Not supplied.
Snyk (skills.sh mirror): Version unavailable. Scope: Not supplied by the mirrored record. Revision: not supplied. Raw findings: not supplied. Counted findings: Not supplied.
Source and licence
- Repository
- https://github.com/wshobson/agents
- Pinned skill file
- View source at revision
- Revision
- 156b7a5e7a8b93642628a339ee4039c925b34c7f
- Package hash
- sha256:15d8ac97cd42adeb35d37a50476da80e829bc2cf9679add2ceead59bddebba07
- Licence
- MIT
Files in the scanned package
| File | Size |
|---|---|
| SKILL.md | 5.1 KB |
| assets/few-shot-examples.json | 4.1 KB |
| assets/prompt-template-library.md | 3.2 KB |
| references/chain-of-thought.md | 9.2 KB |
| references/details.md | 9.0 KB |
| references/few-shot-learning.md | 10.9 KB |
| references/prompt-optimization.md | 12.5 KB |
| references/prompt-templates.md | 11.1 KB |
| references/system-prompts.md | 5.3 KB |
| scripts/optimize-prompt.py | 9.3 KB |
Try Prompt Engineering Patterns in your agent.
This skill should be used when the user asks to "optimize a prompt".