agentleFS
srikanth-manivannansrikanth-manivannan/claude-agent-factory/skills/ai/prompt-engineer/SKILL.md

prompt-engineer

Skill1 starsChanged 5 months agoMITView on GitHub

Use this to design or refine a production prompt with an explicit contract, structure, and rationale.

74 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use idea-validator, debugger and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • dipaulavsSkill

    idea-validator

    Validates app ideas before building. Analyzes market saturation, competitors, real demand vs stated interest, solo builder feasibility (2-4 weeks timeline), and monetization potential. Use when user asks to validate an idea, evaluate a concept, check if idea is worth building, or before starting a new project.

    Also in 3 projects that use this

  • JohnJBorenSkill

    debugger

    Systematic debugging workflows, root cause analysis, and troubleshooting patterns

    Also in 3 projects that use this

  • VercelSkill

    technical-writer

    Write, review, and edit developer documentation for SDKs, libraries, and frameworks, including sites such as ai-sdk.dev and chat-sdk.dev. Use for getting-started guides, tutorials, API references, conceptual explanations, integration guides, migration guides, troubleshooting, and code examples.

    Also in 3 projects that use this

  • JetBrainsSkill

    webapp-testing

    Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

    Also in 4 projects that use this

  • JetBrainsSkill

    doc-coauthoring

    Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

    Also in 3 projects that use this

  • MicrosoftSkill

    api-design

    Guide for designing and documenting RESTful APIs. Use when asked to design an API, create endpoints, or document an API.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 65 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add guardrails: Treat external/tool input as untrusted.

    line 53
  2. Distinctive:

    Add few-shot examples: only when they materially improve reliability.

    line 56
  3. Distinctive:

    Refine for reliability + cost: Remove ambiguity and redundancy.

    line 58

“Common” is measured: kept by at least 6 in 10 of the 65 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Prompt Engineer

Use this to design or refine a production prompt with an explicit contract, structure, and rationale.

Tech profile — Technology: LLM application · Language: n/a · Stack: any model API · Toolchain: any · Domain: ai (Model-aware but portable; defaults to the latest Claude models per the AI standard.)

When to use this skill

  • Writing a new production prompt for an LLM feature.
  • Refining a prompt that is unreliable, verbose, or unsafe.
  • Hardening a prompt's output format or injection resistance.

When NOT to use this skill

  • Building the surrounding evaluation — use ai/llm-eval-harness.
  • Retrieval design — use ai/rag-pipeline-builder.
  • Agent loops/tools — use the agentic-ai skills.

Prerequisites

  • The task the prompt must accomplish and how its output is consumed (human vs. machine).

Inputs

InputRequiredDescription
taskyesWhat the prompt must make the model do
output_consumernohuman / machine (drives structure & format)
constraintsnoTone, length, safety, format requirements
existing_promptnoA prompt to refine, if any

Instructions

  1. Define the prompt contract. State the goal, the inputs the prompt receives, and the exact expected output (format + shape). Follow /standards/prompt-engineering.md.
  2. Choose a structure. Role/instructions/inputs/output sections; imperative, ordered instructions; keep the body technology-neutral and pass specifics as variables.
  3. Specify the output format. For machine consumers, require structured output (e.g. JSON to a stated schema); for humans, specify tone/length.
  4. Add guardrails. Treat external/tool input as untrusted; defend against prompt injection; include a refusal path for unsafe/out-of-scope requests (/standards/security.md).
  5. Add few-shot examples only when they materially improve reliability; keep them minimal and representative.
  6. Refine for reliability + cost. Remove ambiguity and redundancy; shorter is better when it doesn't lose precision.
  7. Document rationale + provide a test plan. Explain key choices; list cases that should pass (pair with ai/llm-eval-harness). Recommend the latest Claude model for the task (per the AI standard).

Output

A production-ready prompt with: an explicit contract, a clear structure, a specified output format, guardrails, optional minimal examples, a one-paragraph rationale, and a suggested eval/test plan.

Constraints & safety

  • Injection-aware: untrusted input is never treated as instructions.
  • Refusal path: unsafe/out-of-scope requests are declined cleanly.
  • No hidden technology lock-in: stack specifics are variables, not hardcoded.

Examples

Minimal below; full examples in EXAMPLES.md.

Given: task = "classify a support ticket into {billing, technical, other}", consumer = machine. Produces: a prompt enforcing JSON output {"category": "..."}, an injection guardrail, one few-shot example, and a 5-case test plan.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.