AI Agent Skills Marketplace

Turn your AI agent into a coordinator that manages parallel subagents for complex coding and research tasks.

ai-productivity

by Roy Yuen

Popular

Free

High-speed intake for shaping vague prompts, triaging complex tasks, and compressing context for efficient execution.

Automate deep research by decomposing complex topics into parallel sub-tasks and generating a structured report.

Automatically decompose complex epics into structured sprint tasks with story points, AC, and dependency maps.

ai-trace-runner

by Roy Yuen

$5

or 25 cr

Transform ambiguous AI tasks into auditable execution traces with verified evidence and AI-smell detection.

Stop burning expensive model tokens on repetitive subtasks. This skill delegates mechanical work to cheaper models and writes handoff snapshots so you never lose context switching between sessions.

Turn vague goals into actionable 7-day marketing sprints with daily tasks and measurable outcomes for small businesses.

Intelligently delegate tasks to Claude, Codex, or Gemini based on cost, model strengths, and rate limits.

Master subagent orchestration in Grok Build CLI to parallelize complex coding tasks and maintain context focus.

Spec2Code

by JustHandled Labs

$19

or 95 cr

Turn messy PRDs, Notion docs, and user stories into a structured implementation plan: tasks with dependencies, complexity estimates, file paths, and acceptance criteria, plus GitHub-ready issues you can post with one command. Flags the unresolved questions to settle with stakeholders before code starts.

A high-performance wrapper to route security tasks directly to the Anthropic-Cybersecurity-Skills library.

Agent Coordination Protocol — Orchestrate Multi-Agent Workflows Without Loops or Lost Tasks

by PubsProToolkit

$16

or 80 cr

A structured protocol for AI agents to orchestrate sub-agents with role contracts and disciplined handoffs.

Meeting Notes & Action-Item Gate — Turn Messy Notes into an Accountable Action List

by PubsProToolkit

$12

or 60 cr

An adversarial gate that audits meeting notes or a transcript summary before you share them — catching missed decisions, vague or unowned action items, and tasks with no deadline — and returns a structured PASS/REVISE verdict plus a cleaned action list where every task has an owner and a date.

A disciplined execution framework to force your AI to complete multi-step tasks with verifiable, review-ready results.

Automation scene routing, toolchain decision, 10 script templates, error handling, scheduled tasks.

Automated vetting for GitHub bounties and paid tasks to identify high-value opportunities and avoid scams.