mula-refine
Unified prompt engineering and requirements planning. Use when exploring ideas, improving prompts, creating PRDs, generating task breakdowns, or iterating on…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
25,663 results
Unified prompt engineering and requirements planning. Use when exploring ideas, improving prompts, creating PRDs, generating task breakdowns, or iterating on…
Use xno-mcp as a private blackbox “purse” service (named accounts, addresses-only; no seed leakage).
Orchestrate two or more locally independent workers with independent boundaries, using Orca Run/Task/Dispatch, independent worktree/session, or tmux fallback, with the PM responsible for decomposition, dispatch, inspection, 429 stall recovery, independent acceptance, PR closure, and cleanup of temporary resources; also used when the user explicitly requests "parallel advancement", "multiple workers", "PM overall control", "Wave…
Harden a written plan by iterating it through an independent agent panel until it converges. Use this skill whenever the user wants a plan repeatedly reviewed…
Template-driven workflow coordinator with minimal state tracking. Executes command chains from workflow templates OR unified PromptTemplate workflows. Supports…
Lightweight skill generator with style learning - creates simple skills using flow-based execution and style imitation. Use for quick skill scaffolding, simple…
Meta-skill for creating new Claude Code skills with configurable execution modes. Supports sequential (fixed order) and autonomous (stateless) phase patterns.…
Unified team skill for issue resolution. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers…
Unified team skill for performance optimization. Coordinator orchestrates pipeline, workers are team-worker agents. Supports single/fan-out/independent…
Create, revise, and format thesis or dissertation Word documents with strict academic formatting control. Use when an AI agent needs to generate or revise…
Create/scaffold agent skills (SKILL.md outline, file layout/folder structure, quick scaffold). Use when asked to create or scaffold a skill, to package…
Find evidence-backed TypeSafe Jev opportunities in the user's recent Claude Code or Codex work. Use when asked to audit recent workflows, task history, or the…
Manage what enters and stays in the context window — pruning, compaction, summary fidelity, ordering — so the agent stays coherent on long runs without…
Use prompt caching correctly across Anthropic, OpenAI, Bedrock, and Gemini to cut cost and latency on hot paths. Use when the user is building a production LLM…
(builtin) Initialize hierarchical AGENTS.md knowledge base
Binding ultrawork mode directive for omo on Codex. When a prompt contains ultrawork or ulw, the omo UserPromptSubmit hook injects a short bootstrap that points…
Research AI agent runners/platforms (Claude Code, Copilot, Cursor, Windsurf, Codex, Kiro, Gemini, Amp, Goose, etc.) to track config format changes, new…
Activates a triple-agent development loop combining a strategic Project Manager (Robert), a cautious Junior developer (Jekyll), and a brutally honest Senior…
Run a two-model code review panel over a pull request — a Fable subagent and a codex gpt-5.6-sol reviewer at xhigh reasoning — save each verdict to a scratch…
Use when clarifying requirements with a user before planning or coding — sequencing which questions to ask (dependency strength × implementation impact),…
Best practices for designing Claude Code agent files (.claude/agents/*.md). This skill should be used when writing or reviewing agent markdown files to ensure…
Evaluates user prompts for effort and complexity on a 1-10 scale. This skill should be invoked on every user request to determine if the request warrants…
Repurpose LinkedIn content across formats and leverage creator tools. Use when the user asks about repurposing content, turning posts into carousels, LinkedIn…
Opik Agent Configuration — Blueprints, get_agent_config() with selectors, environment tags, Prompt/ChatPrompt fields, deploy_to(), MaskIDs, and config…