Prompt engineer

Skill IrfanSadiqRahat/constellation/agents/prompt-engineer

200 role-specific AI agents across 20 teams with typed artifact pipelines, 14 methodology skills, and 15 pre-baked team formations. The virtual engineering org for Claude Code, Cursor, Codex CLI.

Install

npx -y skills add IrfanSadiqRahat/constellation --skill prompt-engineer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

System prompts, few-shot, chain-of-thought, structured output design.

SKILL.md

1.5 KB, as published. Nobody here has run it

prompt-engineer

The deliverable: `PromptLibrary`

prompts:
  - id: <name>
    version: <semver>
    role: system | developer | tool_choice
    template: <text with {placeholders}>
    schema: <output schema if structured>
    fewshot: [<example>, ...]
    evals: [<eval_id>, ...]
    metadata: { intent, persona, constraints }

Operating principles

Specify role, task, format, constraints — in that order.
Constrain outputs with schemas, not adjectives. "Return JSON matching this Zod" beats "be concise".
Few-shot beats instruction-bloat for format adherence.
One change per eval cycle. Tunable variable count: 1.
Avoid negative instructions. "Do X" beats "don't Y".
Tool-use beats reasoning for facts. Don't ask the model to compute; give it a calculator.
Versioned + git-backed. No production prompts living in DBs without history.
PII in templates is a leak vector. Never bake identifiers into system prompts.

Smell-check

Prompts > 4k tokens without a reason → trim
Multiple personas in one prompt → split
"Always", "never", "must" with no enforcement → guardrail or remove
"Step by step" with no schema → free-form drift

Hand-off contract

eval-engineer runs the suite on every prompt change. ai-engineer integrates into the orchestration layer.

Gives 0 of the 12 instructions most prompt engineering skills give

Counted across 563 of the 626 authors here whose files we hold, read 2026-08-06

ask at most three clarifying questionsin 22 of 563, across 15 files
respond in the user input languagein 14 of 563, across 9 files
preserve the original intentin 13 of 563, across 11 files
Establish baseline metrics and collect representative examplesin 12 of 563, across 2 files
Identify failure modes and prioritize high-impact fixesin 12 of 563, across 2 files
Apply prompt and workflow improvements with measurable goalsin 12 of 563, across 2 files
Roll back quickly if quality or safety metrics regressin 12 of 563, across 2 files
validate changes with tests and roll out in controlled stagesin 12 of 563, across 2 files
generate quantitative baseline performance reportsin 12 of 563, across 2 files
create representative test scenariosin 12 of 563, across 2 files
treat prompts as codein 12 of 563, across 5 files
test prompts on diverse inputsin 12 of 563, across 8 files

Said here and by no other author read

prefer few-shot examples over instructions
change one variable per eval cycle
prefer tool-use over model reasoning
trim prompts exceeding 4000 tokens
split prompts with multiple personas
enforce or remove absolute statements

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.