agentleFS
alex-voloshin-devalex-voloshin-dev/ai-skills/.agents/skills/prompt-engineering/SKILL.md

prompt-engineering

Skill2 starsChanged 6 months agoMITView on GitHub

Prompt engineering knowledge base — technique taxonomy with decision tree, prompt template patterns and formatting conventions, OWASP LLM Top 10 security checklist, eval frameworks and testing guide, context engineering, structured output contracts, multi-agent orchestration patterns, cost optimization. Use when designing prompts, reviewing prompt quality, building AI features, creating AI assets, or auditing LLM security.

89 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use security-checklist, multi-agent-orchestration and 9 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.
  • atuljha23Skill

    security-checklist

    OWASP-style quick reference — authn/authz, injection, secrets, sessions, crypto, dependencies. Use during code review and before committing security-sensitive changes.

    Also in 3 projects that use this

  • javalenciacaiSkill

    multi-agent-orchestration

    Design and coordinate multi-agent systems where specialized agents work together to solve complex problems. Covers agent communication, task delegation, workflow orchestration, and result aggregation. Use when building coordinated agent teams, complex workflows, or systems requiring specialized expertise across domains.

    Also in 4 projects that use this

  • xfstudioSkill

    llm-evaluation

    Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

    Also in 3 projects that use this

  • GoogleSkill

    coding-principles

    Enforces engineering, architecture, public API, and code quality standards distilled from human reviewer feedback across A2UI pull requests. Use when authoring new code, refactoring, addressing review feedback, or reviewing PR diffs. Don't use for release publishing or spec blueprint generation without code or PR changes.

    Also in 3 projects that use this

  • pproencaSkill

    refactoring

    Code refactoring best practices based on Martin Fowler's catalog and Clean Code principles. This skill should be used when refactoring existing code, improving code structure, reducing complexity, eliminating code smells, or reviewing code for maintainability. Triggers on tasks involving extract method, rename, decompose conditional, reduce coupling, or improve readability.

    Also in 6 projects that use this

  • mjunaidcaSkill

    tool-design

    Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 78 edited versions we read keep these.

  • 2

    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:

    Grounding: Prefer citations and verifiable data over unanchored claims

    line 55
  2. Distinctive:

    Cost awareness: Every token costs money and time.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 78 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 Engineering

Comprehensive prompt engineering knowledge base. Provides actionable patterns, checklists, and guides for designing, securing, evaluating, and optimizing LLM prompts and agent systems.

When to Use

  • Designing or reviewing prompt templates (system, developer, user prompts)
  • Building tool calling schemas and structured output contracts
  • Evaluating prompt quality — accuracy, safety, cost, latency
  • Auditing LLM security against OWASP LLM Top 10
  • Designing multi-agent orchestration and handoff protocols
  • Optimizing prompt cost and latency
  • Creating or reviewing Codex AI assets (rules, workflows, skills — all are prompts)
  • Setting up prompt versioning and observability

When NOT to Use

  • Implementing backend/frontend code (use software-engineer role + stack-specific role)
  • Infrastructure and deployment (use devops-engineer role)
  • Writing code tests (use qa-engineer role + test-strategy skill)
  • Content writing (use content-writer role)
  • Context pipeline design, memory engineering, agent harness, RAG architecture, multi-agent orchestration, production AI checklists → use context-engineering skill

Key Concepts

Prompt as System

A prompt is not a string — it is a system composed of:

  1. Instruction hierarchy: System prompt > Developer prompt > User prompt > Retrieved content
  2. Context assembly: What enters the context window, in what order, with what priority
  3. Output contract: Schema, format, constraints, error handling, fallback behavior
  4. Tool interface: Available tools, their schemas, permissions, composition patterns
  5. Guard rails: Safety filters, refusal policies, output validators
  6. Versioning: Immutable versions, deployment tags, audit trail

Core Principles

  1. Eval-first: Define how to measure before changing anything
  2. Simplest technique: Zero-shot → few-shot → CoT → chaining. Escalate only when simpler fails
  3. Explicit over implicit: Spell out constraints, output format, edge cases. Never assume the model "knows"
  4. Separation of concerns: Instructions vs data vs examples — always delimited
  5. Grounding: Prefer citations and verifiable data over unanchored claims
  6. Least privilege: Minimal tool permissions per agent. HITL for high-impact actions
  7. Cost awareness: Every token costs money and time. Compress, cache, route

Resource Files

FileContents
technique-guide.mdTechnique selector overview and reading map
technique-guide-core.mdZero-shot, few-shot, CoT, self-consistency, constrained generation
technique-guide-agentic.mdToT, ReAct, chaining, reflection, RAG, meta-prompting, provider guidance
prompt-template-patterns.mdPrompt structure overview and pattern index
prompt-template-foundations.mdDelimiters, system prompt architecture, few-shot formatting, CoT formatting
prompt-template-contracts.mdOutput schemas, tool schemas, prompt registry, provider-specific adaptations
security-checklist.mdOWASP LLM Top 10 mapped to prompt-level mitigations with checklist
eval-and-testing-guide.mdEval workflow overview and decision map
eval-datasets-and-graders.mdDataset curation, grader types, grader selection
eval-deployment-and-monitoring.mdRegression gates, A/B testing, deployment rollout, monitoring

Integration

  • Follows rules: prompt-engineer role (prompt system architecture, security, eval-first quality)
  • Used by workflows: ai-skills skill (all assets are prompts), feature-dev skill (AI features), code-review skill (prompt quality review)
  • Companion skills: context-engineering skill (context pipeline design, memory engineering, agent harness, RAG architecture, multi-agent orchestration, production checklists), asset-validation skill (AI asset format validation), code-review skill (review checklists)
  • Collaborates with roles: software-engineer role (prompt integration), qa-engineer role (prompt regression tests), product-manager role (success metrics)

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.