planning-with-files
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,666 results
prompt-optimizer
Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt needs…
ralph
Create PRDs and automate the RALPH BUILD LOOP workflow with Claude Code. Use when starting a new project and want Claude Code to follow structured PRD-based…
rss-ai-reader
📰 RSS AI Reader — Automatically fetch subscriptions, generate summaries with LLM, and push to multiple channels! Supports Claude/OpenAI generating Chinese summaries and pushing to Feishu/Telegram/Email. Trigger conditions: user requests to subscribe to RSS, monitor blogs, fetch news, generate summaries, set up scheduled fetching, "help me subscribe", "monitor this website", "push news daily", RSS/Atom…
skillguard
Security scanner for AgentSkill packages. Scan skills for credential theft, code injection, prompt manipulation, data exfiltration, and evasion techniques…
storyboard-generator
Convert scripts into shot lists and still-frame prompts, supporting Jimeng/banana models. Use when shot breakdowns, shot list creation, or batch image prompt generation is needed.
super-helper
A helpful utility skill for agents
swiggy
Order food, groceries, and book restaurants in India via Swiggy's MCP servers. Food delivery, Instamart groceries, and Dineout restaurant bookings with…
task-orchestrator
Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large…
whisper
End-to-end encrypted agent-to-agent private messaging via Moltbook dead drops. Use when agents need to communicate privately, exchange secrets, or coordinate…
review-skills
Review project AI skills for duplication, stale references, mistakes, and structural issues. Use when the user asks to review skills, audit skills, check for…
webmcp-cli-skill
Installation and execution guide for third-party AI Agents: how to use webmcp-cli to interact with browser pages. Includes descriptions of domain-specific tools for pages that have WebMCP tools injected.
neo4j-cypher-guide
Comprehensive guide for writing modern Neo4j Cypher read queries. Essential for text2cypher MCP tools and LLMs generating Cypher queries. Covers…
grace-migrate
Agent-applied GRACE 3 to GRACE 4 migration workflow. CLI validates the result but does not convert or delete files.
handoff-that-to-agent-pane
Hand off a bounded task to a chosen coding agent in a right-hand Herdr pane using a conversation snapshot.
hilos-handoff
Hand work from this session to the room's agents — one ask, or a plan of rows a person approves. Use when asked to hand off, delegate, split up, or ask an…
agents-connect
Uses the agents-connect hub (`aconn` CLI or MCP tools) to publish agent-to-agent events on channels, notify humans by push/email, and ask humans…
add-skill
Authors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use…
engineer-agent-loop
Designs and diagnoses the control flow of agentic loops - pattern selection, supervisor-enforced caps and terminal states, no-progress detection, external…
evaluate-prompts
Builds standalone prompt evaluations - test sets from real failures, paired A/B comparisons with sample-size math, deterministic checks before LLM judges,…
write-agent-goal
Drafts or fixes the goal text for an autonomous agent run (/goal, unattended sessions) - checkable success conditions, evidence requirements, scope and…
add-skill
Authors or improves an Agent Skill in the current repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate,…
liquidity-lcr
Activate for: LCR, liquidity coverage ratio, HQLA, high quality liquid assets, net cash outflow, run-off rate, Level 1 assets, Level 2A, Level 2B, 30-day…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…