GPT-Prompt-Hub
CLAUDE.md2.4k starsChanged 7 months agoMITView on GitHub
This repo is a curated hub of 222 prompts for Claude/GPT/Gemini, organized under prompts/ by category: Each prompt file uses frontmatter (title, category, tags, model, use_case) and a structured body (Role / Objective / Inputs / Output / Constraints / Example). Do not edit prompts without updating frontmatter. Root README.md is the source of truth for the full catalog; each category has its own README.md as a per-folder TOC. _analysis/popular-patterns.md holds the strategy analysis behind the 222-prompt curation — read…
The file
Show its rules and text
We split this CLAUDE.md into the rules it gives an agent
25 rules. About 0 are common, 24 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈24
Distinctive · estimate
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
- Distinctive: line 36
No clever tricks - choose the boring solution
- Distinctive: line 37
If you need to explain it, it's too complex
- Distinctive: line 52
Update status as you progress
- Distinctive: line 53
Remove file when all stages are done
- Distinctive: line 58
Test: - Write test first (red)
- Distinctive: line 84
Remove abstraction instead of adding?
- Distinctive: line 90
Composition over inheritance: - Use dependency injection
- Distinctive: line 93
Test-driven when possible: - Never disable tests, fix them
- Distinctive: line 101
Follow project formatting/linting
- Distinctive: line 106
Ensure commit message explains "why"
- Distinctive: line 113
Never silently swallow exceptions
- Distinctive: line 117
When multiple valid approaches exist, choose based on:
- Distinctive: line 131
Use same libraries/utilities when possible
- Distinctive: line 132
Follow existing test patterns
- Distinctive: line 136
Use project's existing build system
- Distinctive: line 137
Use project's test framework
- Distinctive: line 138
Use project's formatter/linter settings
- Distinctive: line 139
Don't introduce new tools without strong justification
- Distinctive: line 154
Test behavior, not implementation
- Distinctive: line 157
Use existing test utilities/helpers
- Very specific: line 163
Use --no-verify to bypass commit hooks
- Distinctive: line 165
Commit code that doesn't compile
- Distinctive: line 169
Commit working code incrementally
- Distinctive: line 170
Update plan documentation as you go
- Distinctive: line 172
Stop after 3 failed attempts and reassess
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Repository Structure
This repo is a curated hub of 222 prompts for Claude/GPT/Gemini, organized under prompts/ by category:
prompts/business/(25) — strategy, PRDs, venture plans, unit economicsprompts/career/(15) — resume, cover letter, ATS, interview prepprompts/creative/(25) — music, visual, games, multimediaprompts/engineering/(25) — code review, architecture, simulatorsprompts/health-life/(7) — CBT, clinical reasoning, wellness (non-diagnostic)prompts/learning/(25) — tutoring, language coaching, mock interviewsprompts/marketing-seo/(25) — paid media, SEO, landing pages, brandprompts/productivity/(25) — PRDs, planning, PR review, app specsprompts/research/(25) — literature review, market analysis, paper readingprompts/writing/(25) — editing, translation, long-form, screenplayprompts/legacy/(4) — original 2024 custom GPTs, kept for historical record
Each prompt file uses frontmatter (title, category, tags, model, use_case) and a structured body (Role / Objective / Inputs / Output / Constraints / Example). Do not edit prompts without updating frontmatter. Root README.md is the source of truth for the full catalog; each category has its own README.md as a per-folder TOC.
_analysis/popular-patterns.md holds the strategy analysis behind the 222-prompt curation — read before adding new prompts.
Development Guidelines
Philosophy
Core Beliefs
- Incremental progress over big bangs - Small changes that compile and pass tests
- Learning from existing code - Study and plan before implementing
- Pragmatic over dogmatic - Adapt to project reality
- Clear intent over clever code - Be boring and obvious
Simplicity Means
- Single responsibility per function/class
- Avoid premature abstractions
- No clever tricks - choose the boring solution
- If you need to explain it, it's too complex
Process
1. Planning & Staging
Break complex work into 3-5 stages. Document in IMPLEMENTATION_PLAN.md:
## Stage N: [Name]
**Goal**: [Specific deliverable]
**Success Criteria**: [Testable outcomes]
**Tests**: [Specific test cases]
**Status**: [Not Started|In Progress|Complete]- Update status as you progress
- Remove file when all stages are done
2. Implementation Flow
- Understand - Study existing patterns in codebase
- Test - Write test first (red)
- Implement - Minimal code to pass (green)
- Refactor - Clean up with tests passing
- Commit - With clear message linking to plan
3. When Stuck (After 3 Attempts)
CRITICAL: Maximum 3 attempts per issue, then STOP.
- Document what failed:
- What you tried
- Specific error messages
- Why you think it failed
- Research alternatives:
- Find 2-3 similar implementations
- Note different approaches used
- Question fundamentals:
- Is this the right abstraction level?
- Can this be split into smaller problems?
- Is there a simpler approach entirely?
- Try different angle:
- Different library/framework feature?
- Different architectural pattern?
- Remove abstraction instead of adding?
Technical Standards
Architecture Principles
- Composition over inheritance - Use dependency injection
- Interfaces over singletons - Enable testing and flexibility
- Explicit over implicit - Clear data flow and dependencies
- Test-driven when possible - Never disable tests, fix them
Code Quality
- Every commit must:
- Compile successfully
- Pass all existing tests
- Include tests for new functionality
- Follow project formatting/linting
- Before committing:
- Run formatters/linters
- Self-review changes
- Ensure commit message explains "why"
Error Handling
- Fail fast with descriptive messages
- Include context for debugging
- Handle errors at appropriate level
- Never silently swallow exceptions
Decision Framework
When multiple valid approaches exist, choose based on:
- Testability - Can I easily test this?
- Readability - Will someone understand this in 6 months?
- Consistency - Does this match project patterns?
- Simplicity - Is this the simplest solution that works?
- Reversibility - How hard to change later?
Project Integration
Learning the Codebase
- Find 3 similar features/components
- Identify common patterns and conventions
- Use same libraries/utilities when possible
- Follow existing test patterns
Tooling
- Use project's existing build system
- Use project's test framework
- Use project's formatter/linter settings
- Don't introduce new tools without strong justification
Quality Gates
Definition of Done
- Tests written and passing
- Code follows project conventions
- No linter/formatter warnings
- Commit messages are clear
- Implementation matches plan
- No TODOs without issue numbers
Test Guidelines
- Test behavior, not implementation
- One assertion per test when possible
- Clear test names describing scenario
- Use existing test utilities/helpers
- Tests should be deterministic
Important Reminders
NEVER:
- Use
--no-verifyto bypass commit hooks - Disable tests instead of fixing them
- Commit code that doesn't compile
- Make assumptions - verify with existing code
ALWAYS:
- Commit working code incrementally
- Update plan documentation as you go
- Learn from existing implementations
- Stop after 3 failed attempts and reassess
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
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.

