By manutej
Compositional prompt engineering for Claude Code. Chain commands, iterate with quality gates, swap strategies. Five commands, four operators (→ || ⊗ >=>), seventeen skills. Inspired by category theory.
Execute a sequence of slash commands using categorical composition operators.
Comonad W operations for context extraction, meta-observation, and context-aware transformations
Apply categorical meta-prompting to solve a task with strategy selection based on complexity
Execute Recursive Meta-Prompting loop with quality convergence
Natural transformation α: F ⇒ G for strategy switching between prompting functors
Systematic analysis patterns for categorical AI papers (Gavranović, de Wynter, Bradley, Zhang). Use when analyzing academic papers on categorical deep learning, extracting categorical structures from AI research, mapping meta-prompting concepts to category theory, or building comprehensive literature reviews on categorical approaches to AI.
Property-based testing for functor laws, monad laws, and naturality conditions using fp-ts and fast-check. Use when validating categorical implementations in TypeScript, testing algebraic laws in functional code, verifying functor/monad/applicative instances, or building test suites for categorical abstractions.
CC2.0 seven-function research workflow (observe, reason, create, orchestrate, learn, verify, deploy) for categorical AI research. Use when conducting systematic research on categorical AI topics, coordinating multi-stream research workflows, applying categorical foundations to research methodology, or implementing the L5 meta-prompting research framework.
Master reference for categorical meta-prompting unified syntax. Contains all modifiers, operators, composition patterns, and execution protocols. Use this skill for self-reference when executing any prompt workflow, ensuring consistent syntax across all commands and skills.
Spivak-Niu polynomial functor implementations for learner composition and dynamical systems. Use when modeling learning systems as categorical structures, composing machine learning components with polynomial functors, implementing the categorical framework from Polynomial Functors - A Mathematical Theory of Interaction, or building compositional dynamical systems with lenses and charts.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Five commands. Four operators. Category theory under the hood.
quickstart · commands · composition · skills · theory/chain [/meta→/rmp→/review] @quality:0.9 "add rate limiting to /api/login"
flowchart LR
U(["user intent"]) -->|"/meta"| M["classify + strategy"]
M -->|"then"| R["/rmp iterate"]
R -->|"then"| V["/review"]
V --> F(["final answer"])
style U fill:#fef3c7,stroke:#d97757,color:#1e293b
style M fill:#ede9fe,stroke:#8b5cf6,color:#1e293b
style R fill:#e0e7ff,stroke:#6366f1,color:#1e293b
style V fill:#cffafe,stroke:#06b6d4,color:#1e293b
style F fill:#d1fae5,stroke:#10b981,color:#1e293b
Output of one is input to the next. Quality gates catch the weak link. Loops stop when they're good enough.
Inside Claude Code — the plugin is its own marketplace:
/plugin marketplace add manutej/meta-prompting-plugin
/plugin install meta-prompting-plugin@manutej
Type /meta and you're in.
Local clone (test or develop against a working copy):
git clone https://github.com/manutej/meta-prompting-plugin
claude --plugin-dir ./meta-prompting-plugin
Pin to a tag (recommended for stability):
/plugin marketplace add manutej/[email protected]
Legacy symlink install (the INSTALL.sh path, kept for pre-marketplace setups):
git clone https://github.com/manutej/meta-prompting-plugin ~/.claude/plugins/meta-prompting
cd ~/.claude/plugins/meta-prompting && ./INSTALL.sh
[!NOTE]
v0.1.0— early release. Repo is private during dogfood; once you flip it public (gh repo edit --visibility public), anyone can install with the two commands above.
| Command | Symbol | Does | In one line |
|---|---|---|---|
/meta | F | Functor Task → Prompt | Classify task complexity, pick a strategy. |
/rmp | M | Monad Prompt →ⁿ Prompt | Iterate with a quality gate until converged. |
/context | W | Comonad History → Context | Extract the slice of history relevant to the task. |
/transform | α | Natural transformation F ⇒ G | Swap strategy without changing the task. |
/chain | ∘ | Composition | Pipe commands with → || ⊗ >=>. |
Four operators. Each has a precise algebraic meaning, but you only need the one-liner.
npx claudepluginhub manutej/meta-prompting-plugin --plugin meta-prompting-pluginSenior-engineer guardrails that stop AI coding agents from shipping slop. Nine composable skills + an always-on rules constitution + a /senior-review gate with an execution-evidence Definition of Done. Forces strategic (durable) code over tactical (fast-but-disposable) code, grounded in The Pragmatic Programmer, Fowler's Refactoring, Ousterhout's A Philosophy of Software Design, and empirical AI-code-quality research.
Category theory-based meta-prompting framework with functors, monads, comonads, natural transformations, error handling, and quality visualization. Implements F (Functor), M (Monad), W (Comonad), α (Natural Transformation), E (Exception Monad), and [0,1]-enriched categories for rigorous, composable prompt engineering.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications