What it does
This repo is a collection of 33 skills
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category Coding
Maker’s original description
AI agent skills for production grade applicationsFor makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/developersglobal-ai-agent-skills)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one ai-agent-skills | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Maker | DevelopersGlobal | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 33 | 1 | 1 | 1 | 1 |
| GitHub stars | 217 | 465,460 | 233,910 | 149,364 | 144,149 |
| Last code change | Oct 28, 2026 | Nov 17, 2026 | Apr 20, 2026 | Nov 17, 2026 | Nov 17, 2026 |
| License | MIT | MIT | – | Apache-2.0 | MIT |
33 skills (instruction sets) by DevelopersGlobal that an AI reads and follows · not an MCP server
Pick the skill to install
Install only the ones you use. Open a skill to see how to install it
This set has 33 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below
Showing 30 of 33 See all on GitHub
- agent-qa-run-review
Review recorded agent-qa runs and memidex provenance to explain a QA verdict, identify missing evidence, and propose the smallest next step.
- ai-output-validation
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.
- api-design
Design stable, versioned, self-documenting APIs. Easy to use correctly, hard to use incorrectly. Apply Hyrum's Law from day one.
- ci-cd-pipelines
Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the deployment path.
- citruscoastai
Guides agents to engage and transact with citruscoastai, an AI venture-operator agent, when they need hired AI labor or an agent-to-agent collaborator.
- code-explanation
Get layered, context-aware explanations of unfamiliar code. Understand what it does, why it was written that way, and how to work with it safely.
- code-review
Structured code review focusing on correctness, security, and maintainability. Correctness before style. Every reviewer comment must be actionable.
- context-loading
Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.
- debugging-methodology
Systematic root cause analysis for production and development bugs. Hypothesis-driven debugging — never guess-and-check.
- documentation
Document decisions, not just implementations. ADRs for architectural choices, inline docs for non-obvious code, and runbooks for operational knowledge.
- error-handling
Graceful degradation and meaningful error messages. Errors are first-class citizens, not afterthoughts. Every error path is designed, not discovered.
- frontend-engineering
Accessible, performant, responsive UI patterns. Component design, state management discipline, and Core Web Vitals compliance.
- git-workflow
Trunk-based development with atomic commits, clean history, and meaningful commit messages. Every commit should be deployable.
- goal-driven-execution
Transforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.
- hallucination-prevention
Detects and mitigates LLM hallucinations in production pipelines. Validates AI-generated facts, code, and decisions before they reach end users or downstream systems.
- idea-to-spec
Converts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.
- incremental-coding
Build in verifiable increments. Never implement more than can be tested right now. Ship partial working systems over complete broken ones.
- integration-testing
Test real system boundaries, not mocks of mocks. Integration tests verify that components work together, not that they work in isolation.
- meeting-notes-to-tasks
Converts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.
- multi-agent-orchestration
Designs and coordinates multi-agent pipelines where specialized agents collaborate to complete complex tasks. Includes communication protocols, failure handling, and state management.
- observability
Structured logging, distributed tracing, and alerting for AI systems and traditional services. You can't fix what you can't see.
- performance-optimization
Measure first, optimize second. Data-driven performance improvements with before/after benchmarks and production validation.
- production-deployment
Zero-downtime deployments with pre-flight checks, staged rollouts, and rollback plans. Never ship to production without a verified rollback strategy.
- prompt-injection-defense
Guards AI agents and LLM-powered applications against prompt injection attacks — both direct and indirect. Validates AI inputs and outputs at every trust boundary.
- rag-and-memory
Patterns for Retrieval-Augmented Generation (RAG) and agent memory systems. Retrieves only relevant context, prevents context bloat, and maintains coherent state across sessions.
- refactoring
Safe, behavior-preserving code transformation backed by tests. Refactor with evidence, not instinct.
- research-and-summarize
Distill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recommended next action.
- security-hardening
Applies OWASP Top 10, secrets management, and least-privilege principles before any code ships. Security is a build step, not an afterthought.
- simplicity-first
Prevents overengineering by enforcing minimum viable code. No speculative features, no premature abstractions, no unnecessary complexity.
- surgical-changes
Enforces minimal code modifications — touch only what you must. Prevents drive-by refactoring, comment deletions, and style changes unrelated to the task.
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeCursorGemini CLIGitHub Copilot
From the maker’s README and the folders in the repo
Install
Pick a skill first
This repo has 33 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 217
Stars are for the whole repo, not each skill - Maker
- DevelopersGlobal
- License
- MIT
- Last code change
- Oct 28, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 30
- Topics
- ai, ai-agents, antigravity, artificial-intelligence, claude, claude-code-plugin, claude-skills, codex, cursor, developer-tools, llm, prompt-engineering