Prompt Engineer skill: what it does and how to install it
Designs and evaluates LLM prompts, refining instructions, examples and output schemas against test cases to improve reliability and efficiency.
Summary generated from the skill's documentation.
Warning. A security audit flagged this skill with a critical risk warning. Read its SKILL.md and scripts before you install it.
Install
$ npx skills add Jeffallan/claude-skills --skill prompt-engineerRun it in a terminal. If your agent is already running, start a new session so it picks the skill up.
About this skill
What it does. Defines requirements and success criteria, drafts a prompt pattern, tests it on varied cases, then iterates based on failures and token costs. It can produce prompt templates, structured output schemas, evaluation tests and deployment notes.
When to use it. For new LLM prompts, improving existing ones, debugging inconsistent outputs or moving prompts between models. It also applies to system prompts, few-shot examples and prompt evaluation frameworks.
History
Repo stars
12.1k+332 since 5 Oct 2026
Stars are counted for the whole repository, which holds 51 skills.
Show as a table
| Date | Repo stars |
|---|---|
| 26 Oct 2026 | 12,068 |
| 25 Oct 2026 | 12,050 |
| 24 Oct 2026 | 12,032 |
| 23 Oct 2026 | 12,017 |
| 22 Oct 2026 | 11,999 |
| 21 Oct 2026 | 11,974 |
| 20 Oct 2026 | 11,948 |
| 19 Oct 2026 | 11,940 |
| 18 Oct 2026 | 11,921 |
| 17 Oct 2026 | 11,909 |
| 16 Oct 2026 | 11,895 |
| 15 Oct 2026 | 11,881 |
| 14 Oct 2026 | 11,865 |
| 13 Oct 2026 | 11,850 |
| 12 Oct 2026 | 11,838 |
| 11 Oct 2026 | 11,819 |
| 10 Oct 2026 | 11,806 |
| 9 Oct 2026 | 11,791 |
| 8 Oct 2026 | 11,776 |
| 7 Oct 2026 | 11,756 |
| 6 Oct 2026 | 11,746 |
| 5 Oct 2026 | 11,736 |
Installs
5.6k+131 since 19 Oct 2026
Installs via skills.sh
Show as a table
| Date | Installs |
|---|---|
| 26 Oct 2026 | 5,613 |
| 25 Oct 2026 | 5,601 |
| 24 Oct 2026 | 5,587 |
| 23 Oct 2026 | 5,571 |
| 22 Oct 2026 | 5,543 |
| 21 Oct 2026 | 5,514 |
| 20 Oct 2026 | 5,499 |
| 19 Oct 2026 | 5,482 |
Similar skills
- Systematic DebuggingMakes the agent find the root cause of a bug, test failure or unexpected behaviour before it proposes a fix.
- Test-Driven DevelopmentMakes the agent write a failing test before any implementation code, for features and bug fixes alike.
- Verification Before CompletionRequires the agent to run verification commands and confirm the output before it claims that work is complete or passing.