agentleFS
Sign inStart free
karim-bhalwanikarim-bhalwani/agentic-harness/skills/prompt-library/SKILL.md

prompt-library

Skill0 starsChanged 4 months agoMITView on GitHub

Curated collection of high-quality prompts for various tasks - role-based templates, analysis frameworks, code review prompts, and brainstorming structures. Use when building prompts for specific roles, needing analysis or brainstorming frameworks, creating code review prompts, or searching for proven prompt patterns and structures. DO NOT USE FOR: LLM application architecture (use llm-app-patterns), actual code review execution (use guardian), deciding what features to build or exploring requirements (use brainstorming), or prompt injection defense (use security-boundaries). NOTE: This library supplies brainstorming-style prompt templates (e.g., 'Brainstorm Features') for use within a brainstorming session; it does not conduct the brainstorming itself.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the requested category is not listed above, suggest the closest alternative or recommend prompt-builder to create a new one.

    line 51
  2. Distinctive:

    Does NOT execute prompts or validate outputs (provides templates only)

    line 55
  3. Distinctive:

    Does NOT replace domain expertise (prompts need subject matter context)

    line 56
  4. Distinctive:

    Does NOT guarantee model behavior (outputs vary by model, temperature, and context)

    line 57
  5. Distinctive:

    Does NOT store sensitive data in prompt templates

    line 58

“Common” is measured: kept by at least 6 in 10 of the 5 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 Library

Version: 9.0 | Updated: 01-July-2026 | Architect: Karim Bhalwani |

Curated collection of high-quality prompts for various use cases, organized by task type.

Router

Load references/prompt-templates.md automatically whenever a user requests a specific prompt template. If the file cannot be loaded, inform the user and list the categories below.

Role-Based

  • Expert Developer - Code review and mentoring
  • Code Reviewer - Structured code feedback (Critical / Suggestions / Praise)
  • Technical Writer - Documentation clarity
  • System Architect - Design with trade-off analysis

Task-Specific

  • Debug This Code - Problem ID, root cause, fix, prevention
  • Explain Like I'm 5 (ELI5) - Simplified explanation with analogies
  • Code Refactoring - Readability-first refactoring with before/after
  • Write Tests - Happy path, edge cases, errors, boundaries
  • API Documentation - Endpoint specification (OpenAPI/Markdown)

Analysis

  • Code Complexity Analysis - Cyclomatic, coupling, cohesion, debt
  • Performance Analysis - Big-O, I/O bottlenecks, quick wins
  • Security Review - Input validation, auth, injection, dependencies (Critical/High/Med/Low)

Creative & Transformation

  • Brainstorm Features - 10 ideas + impact/effort ranking
  • Name Generator - Descriptive / Evocative / Acronyms / Metaphorical
  • Migrate Code - Cross-language/framework migration
  • Convert Format - Format-to-format conversion

If the requested category is not listed above, suggest the closest alternative or recommend prompt-builder to create a new one.

Constraints

  • Does NOT execute prompts or validate outputs (provides templates only)
  • Does NOT replace domain expertise (prompts need subject matter context)
  • Does NOT guarantee model behavior (outputs vary by model, temperature, and context)
  • Does NOT store sensitive data in prompt templates

Integration Points

  • prompt-builder: Uses templates from this library as starting points for new prompts
  • ai-engineer: Consumes prompt patterns for RAG and agent system prompts
  • brainstorming: Supplies brainstorming-style prompt templates for use inside a brainstorming session
  • guardian: Reviews prompts for security (injection resistance) and quality

References

Load these when building or reviewing prompts:

  • prompt-templates.md - Copy-ready prompt bodies for every category listed in the Prompt Catalog above (role-based, task-specific, analysis, creative). Load when you need the actual prompt text.
  • prompt-library.md - Curated prompt meta-catalog with prompt engineering best practices, customization guidance, and chaining patterns. Load for prompt design technique, not template bodies.
  • sample_prompt.md - Worked example of a well-structured prompt with all required elements. Load when the user needs a concrete reference for prompt format, section order, and quality criteria.

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.

Check your setup, free