agentleFS
BigY0shiBigY0shi/super-skills/skills/dispatch/SKILL.md

dispatch

Skill4 starsChanged 6 months agoMITView on GitHub

Master router and dispatcher for all skill suites. Identifies which suite to load based on the user's request and routes to it. Use this skill when the task domain is unclear, when a request spans multiple suites, or as the universal entry point before any specialized work begins. Covers all domains: UI/UX design, web development, visual art, marketing, copywriting, SEO, CRO, email, ads, DevOps, cloud infrastructure, CI/CD, Docker, Kubernetes, databases, coding, programming, architecture, APIs, testing, security, penetration testing, hacking, red team, blue team, startups, business strategy, product management, SaaS metrics, CRM, game development, Unity, Minecraft, AI agents, data science, machine learning, RAG, LLM, voice AI, productivity, task planning, ADHD, executive function, getting things done, organization. Trigger keywords: which skill, what suite, help me with, I need to, I want to build, I want to make, I'm working on, help me figure out, not sure where to start, route me, dispatch.

40 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use edge-detection, odds-analysis and 10 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.
  • noahowshSkill

    edge-detection

    Comparing a tennis model's probability with the market: no-vig close, expected value at the best available price, closing line value, fractional Kelly sizing, and the checks that separate an estimated edge from noise. Use when the user has a probability and wants to know whether a price is better than fair, how large a stake is reasonable, or whether an edge is real. Requires a probability the user trusts. Do not use for fetching prices: see odds-explorer. Do not use for devig math alone: see odds-analysis. Do not use for historical testing: see backtesting.

    Also in 4 projects that use this

  • noahowshSkill

    odds-analysis

    Odds math for two-way tennis markets: American to implied probability, margin, devigging (multiplicative, power, Shin), no-vig fair odds, consensus across books, favorite-longshot bias, and expected value of a price. Use when the user asks what a price implies, how to remove the vig, what the true probability is, or how to compare books. Do not use for fetching or comparing live prices: see odds-explorer. Do not use for deciding a bet against a model: see edge-detection.

    Also in 4 projects that use this

  • agiprolabsSkill

    walk-forward-validation

    Walk-forward validation framework for trading strategies and ML models with time-series-aware splits, overfit detection, and regime-aware validation

    Also in 4 projects that use this

  • Yahmez3Skill

    backtesting

    Use when backtesting a trading strategy — evaluating a signal series against historical price data and computing performance metrics (Sharpe, Sortino, max drawdown, CAGR, win rate, expectancy). Triggers on "backtest this strategy", "what's the Sharpe on X", "run a walk-forward test", or "compare strategies A and B". Produces equity curves, trade logs, and tear sheets.

    Also in 4 projects that use this

  • ffsshhttiikkSkill

    feature-engineering

    Machine learning feature engineering

    Also in 4 projects that use this

  • varun29ankuSSkill

    orchestrate

    This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.

    Also in 4 projects that use this

  • +3 more from noahowsh

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 38 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:

    Rule: Always complete the primary suite's work before loading the secondary.

    line 164
  2. Distinctive:

    Ask one question: "What is the primary deliverable?"

    line 186

“Common” is measured: kept by at least 6 in 10 of the 38 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

Dispatch

The master router. Every suite lives here. Read this first when you're not sure which expert to call.


How Dispatch Works

  1. Read the user's request
  2. Match to a suite using the routing table below
  3. Load that suite's SKILL.md — it contains the sub-skill routing table
  4. Execute following the suite's workflow

For multi-suite requests, identify the primary suite first, then note the secondary suites to involve.


Master Routing Table

🎨 design-studio

Load when: UI, UX, visual design, web design, landing pages, dashboards, data visualization, design systems, component libraries, accessibility, animation, motion, generative art, posters, print, typography, Figma, wireframes, prototypes, portfolio, creative direction.

"Make it look good", "design this", "build a landing page", "create a component", "audit this UI", "make something beautiful", "generate art"

Path: skills/design-studio/SKILL.md


📣 marketing-suite

Load when: Marketing copy, headlines, CTAs, email sequences, cold email, SEO strategy, SEO audit, CRO (landing pages, signup flows, onboarding, paywalls, popups, forms), A/B testing, paid ads (Google, Meta, LinkedIn, TikTok), social media content, content strategy, brand voice, churn prevention, referral programs, product launches, analytics (GA4, GTM, Mixpanel), attribution, sales decks, battlecards.

"Write copy for", "improve conversions", "A/B test this", "email sequence", "ad campaign", "content calendar", "reduce churn", "launch strategy"

Path: skills/marketing-suite/SKILL.md


🛠️ devops-suite

Load when: Cloud infrastructure (AWS, GCP, Azure, Vercel), Docker, Kubernetes, CI/CD pipelines (GitHub Actions, GitLab CI), databases (SQL, NoSQL, vector), observability (Prometheus, Grafana, logging), incident response, server management, shell scripting (Bash, PowerShell), cost optimization, microservices, service mesh, MLOps, workflow automation.

"Deploy this", "set up CI/CD", "Docker container", "Kubernetes cluster", "database schema", "monitoring", "incident", "automate this workflow"

Path: skills/devops-suite/SKILL.md


💻 coding-suite

Load when: Writing code, debugging code, code review, programming languages (Python, TypeScript, JavaScript, Rust, Go, Java, C#, C++, Swift, Kotlin), frameworks (React, Next.js, Vue, FastAPI, Django, Rails, Spring), testing, software architecture, backend APIs, LLM app development, authentication, performance profiling, refactoring, technical documentation.

"Write a function", "debug this", "review my code", "build an API", "architect this system", "optimize this", "help me code"

Path: skills/coding-suite/SKILL.md


🏗️ founders-suite

Load when: Startup strategy, business analysis, SWOT, SMART goals, OKRs, competitive analysis, pricing strategy, product management (RICE, PRD, roadmap), go-to-market, SEO foundations, programmatic SEO, GEO (AI search optimization), CRM development (Salesforce, HubSpot), Segment CDP, SaaS metrics (MRR, CAC, LTV, churn), HR workflows, hiring, micro-SaaS, indie hacker, AI product/wrapper businesses.

"Analyze this startup", "pricing strategy", "SWOT analysis", "PRD template", "Salesforce integration", "SaaS metrics", "hiring plan", "validate my idea"

Path: skills/founders-suite/SKILL.md


🎮 game-dev

Load when: Game development of any kind — 2D games, 3D games, Unity (C#), web games (Phaser, Three.js, WebGPU), mobile games (iOS/Android), PC/console games, VR/AR (Quest, PCVR), game design documents (GDD), core loop design, player psychology, game balancing, game art direction, sprite sheets, animation, sound design, FMOD, Wwise, multiplayer/netcode, Minecraft plugins (Bukkit, Spigot, Paper).

"Build a game", "Unity script", "game design doc", "Minecraft plugin", "VR experience", "multiplayer netcode", "game loop", "pixel art pipeline"

Path: skills/game-dev/SKILL.md


🔬 research-lab

Load when: Data science, machine learning, statistical analysis, A/B testing (ML context), predictive modeling, AI agent architecture, autonomous agents, multi-agent systems, CrewAI, LangGraph, agent memory, RAG (retrieval-augmented generation), prompt engineering, prompt caching, LLM application patterns, voice agents, voice AI, agent evaluation, research methodology, academic research engineering.

"Build an AI agent", "data analysis", "machine learning model", "RAG pipeline", "prompt engineering", "multi-agent system", "voice AI", "statistical analysis", "research this rigorously"

Path: skills/research-lab/SKILL.md


🟣 purple-team

Load when: Security of any kind — penetration testing, ethical hacking, red team, MITRE ATT&CK, reconnaissance (Shodan, OSINT), web app testing (SQLi, XSS, IDOR, Burp Suite), cloud pentesting (AWS, Azure, GCP), privilege escalation (Linux, Windows, Active Directory), post-exploitation, Metasploit, malware analysis, reverse engineering, firmware analysis, SAST/DAST, security auditing, dependency scanning, threat modeling (STRIDE), API security, secure coding, security hardening, bug bounty.

"Pentest this", "security audit", "find vulnerabilities", "red team", "STRIDE analysis", "is this code secure", "SAST scan", "privilege escalation", "reverse engineer this"

Path: skills/purple-team/SKILL.md


⚡ productivity-suite

Load when: Getting unstuck, task initiation, breaking down overwhelming tasks, project planning and roadmapping, working memory ("where was I?"), context save/restore, file organization, digital chaos, GSD (Get Shit Done) framework, execution with checkpoints, completion verification, ADHD support, executive function replacement, mode switching (brainstorm/implement/debug), autonomous project execution (Loki Mode).

"I don't know where to start", "break this down", "I'm overwhelmed", "where was I", "organize my files", "just get this done", "plan this project", "I keep forgetting", "help me focus"

Path: skills/productivity-suite/SKILL.md


Ambiguous Cases — Tie-Breaker Rules

Some requests could reasonably route to multiple suites. Use these rules:

Request TypePrimary SuiteWhy
SEO audit of a websitemarketing-suiteTactical execution focus
SEO as a business growth strategyfounders-suiteStrategic/business context
A/B test setup for conversionmarketing-suiteCRO is marketing
A/B test statistical analysisresearch-labStatistical methodology
Build a data dashboarddesign-studioVisual/UI output
Analyze data for insightsresearch-labML/statistical output
API security reviewpurple-teamSecurity is the output
Build a secure APIcoding-suiteCode is the output; security is a constraint
Launch strategy for a productfounders-suiteBusiness context
Launch strategy campaign copymarketing-suiteContent is the output
Referral program mechanicsfounders-suiteBusiness/growth strategy
Referral program copymarketing-suiteContent is the output
Cloud cost optimizationdevops-suiteInfrastructure focus
Pricing strategy for SaaSfounders-suiteBusiness strategy
Prompt engineering for an appcoding-suiteApp development context
Prompt engineering as a craftresearch-labLLM engineering focus
Agent memory architectureresearch-labAI systems design
Memory in a coding projectcoding-suiteImplementation context
Planning a coding projectproductivity-suiteExecution/workflow first
Architecting a coding projectcoding-suiteTechnical design first

When genuinely ambiguous: Route to the suite that owns the output, not the input.


Multi-Suite Requests

Some tasks span multiple suites. Sequence them:

TaskSequence
"Build and launch a SaaS"founders-suite → coding-suite → devops-suite → marketing-suite
"Build a game and market it"game-dev → marketing-suite
"Audit our security and fix the code"purple-team → coding-suite
"Design and build a dashboard"design-studio → coding-suite
"Build an AI product"research-lab → coding-suite → founders-suite
"I'm overwhelmed, help me build this app"productivity-suite → coding-suite
"Pentest our app then harden it"purple-team (red) → purple-team (blue)
"Launch campaign with copy and analytics"marketing-suite → devops-suite (tracking setup)

Rule: Always complete the primary suite's work before loading the secondary. Don't try to run both simultaneously.


Suite Quick Reference

design-studio    → Making things look and feel right
marketing-suite  → Getting people to notice, click, and convert
devops-suite     → Making systems run reliably at scale
coding-suite     → Writing correct, maintainable software
founders-suite   → Building and scaling a business
game-dev         → Making games people want to play
research-lab     → AI agents, data science, LLM engineering
purple-team      → Breaking things (red) and fixing them (blue)
productivity-suite → Getting things done when your brain won't cooperate

If Still Unsure

Ask one question: "What is the primary deliverable?"

  • A visual artifact → design-studio
  • Marketing content or a conversion → marketing-suite
  • Running infrastructure → devops-suite
  • Working code → coding-suite
  • A business decision or document → founders-suite
  • A game → game-dev
  • An AI system or data insight → research-lab
  • A security finding or fix → purple-team
  • A completed task or organized life → productivity-suite

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.