Find the right capability for your agent. Browse by category, explore skills, or search what you want to accomplish.
New to skills? Learn how they workBuild, run and coordinate AI agents, prompts and LLM workflows.
Your AI helps you create new skills or improve existing ones by drafting, testing, evaluating, and rewriting them. It runs test prompts, analyzes results quantitatively and qualitatively, and guides you through iterative refinement.
Turn manual workflows into agent skills, improve existing skills, or evaluate their quality. Your AI guides you through skill creation, benchmarking, and targeted improvements using best-practice patterns.
Your AI audits your repo, servers, plugins, and environment to reveal current capabilities and recommend next steps. It identifies available skills, hooks, agents, and missing integrations without exposing secrets.
Your AI runs a multi-step verification for Claude Code projects before completion. It checks builds, types, linting, tests, security scans, and code diffs to ensure quality and readiness for pull requests.
Your AI shares and resumes work state across different agents using the ECC Memory Vault. It stores and retrieves portable Markdown context files to hand off tasks and search project knowledge across sessions.
Your AI lets you browse and select multiple agent personas to form a team for a task. It organizes agents by domain folders or filename prefixes and shows descriptions to help you pick the right mix.
Your AI coordinates multiple agents as a team using work items, ownership, Kanban states, and merge gates. It manages shared workflow visibility, branch isolation, and control pane handoffs for multi-agent project collaboration.
Your AI suggests manual context compaction at logical task boundaries to preserve important information through multi-phase workflows. It monitors token usage and prompts compaction after milestones or before major context shifts.
Your AI audits all Claude skills and commands for quality using quick or full scan modes. It evaluates changed or all skills with batch subagent checks and caches results for ongoing quality control.
Get a list of existing skills matching your workflow needs before creating new ones. It searches local, marketplace, GitHub, and web sources using keywords and synonyms to avoid duplication.
Your AI checks if agents truly follow given skills, rules, and definitions by running scenarios at different prompt strictness levels. It captures and classifies tool call sequences and generates detailed compliance reports with timelines.
Your AI uses two independent reviewers to check output before delivery, reducing bias and errors. Both must approve the content, ensuring compliance and accuracy for published or production-ready results.
Your AI scans installed skills to extract recurring principles and distills them into or updates rule files. It collects facts exhaustively, cross-reads for matches, and revises rules to keep knowledge consistent and complete.
Your AI decides when to use regex or an LLM to parse structured text, saving cost and improving accuracy. It starts with regex for consistent patterns and adds LLM only for uncertain edge cases in quizzes, forms, or invoices.
Your AI manages repeated rollouts and recursive reasoning with explicit decision and coherence marks. It records trial data, search spaces, and candidate evaluations in append-only ledgers for transparent evidence trails.
Turn large feature requests into verified, manageable work units for multi-agent execution. It organizes RFC intake, DAG decomposition, unit validation, merge queues, and integration checks.
Get clear, improved prompts ready to paste and run without executing tasks. It analyzes your draft, matches ECC components, and rewrites prompts based on your intent and gaps in phrasing.
Get ready-to-paste orchestrate commands for each step of a multi-step plan document. It reads your plan, decomposes it into steps, and designs agent chains from the ECC catalogue without executing them.
Your AI speeds up tasks by splitting work into parallel lanes with isolated writes and coordinated merges. It batches reads, runs concurrent tests or builds, and manages dependencies to ensure correctness and faster completion.
Your AI runs the gated Research-Plan-TDD-Review-Commit pipeline used by orch-* skills. It classifies task size, delegates phases to agents, and manages human approval gates for feature addition, fixes, changes, and refactors.
Your AI designs goal-driven agent loops and reviews them for failure risks like infinite spinning or cheating. It defines decidable goals, selects loop types, and checks for runaway behavior or flawed judgment layers.
Your AI manages ingestion, syncing, deduplication, and retrieval across local files, MCP memory, vector stores, and Git repos. It organizes multi-layered knowledge systems for saving and searching information beyond simple memory recall.
Progressively improve context for subagents by iteratively dispatching, evaluating, and refining information. It solves missing or excessive context problems in multi-agent workflows and code exploration.
Your AI pauses before making edits to investigate relevant files and data schemas. It runs searches and inspects importers to ensure changes fit existing code patterns and data formats, improving output quality by over 2 points.