mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-25 00:14
Agents & models
24,779 results
bento
Build correct Bento integrations and choose the right Bento AI surface across Bento MCP, the Bento CLI, and official Bento SDKs for Node, Laravel, PHP, Drupal,…
championing-a-strategy-idea
Primary-Owner playbook for shepherding a Technical Strategy Idea through Architecture's pre-funnel evaluation into the Software Initiative Funnel.
github-repo-hunter
Autonomous GitHub repository discovery and integration agent that hunts relevant open-source projects for BidDeed.AI (foreclosure auctions) and Life OS…
guodegang-perspective
Guo Degang's thinking framework and expression style. Based on 9 dimensions (including original text analysis of 3 firsthand works + 6-dimensional online research), deep research of 80+ primary/secondary sources, distilling 6 core mental models, 10 decision-making heuristics, and a complete expression DNA. Purpose: to serve as a thinking advisor, analyzing problems, examining decisions, and providing feedback from Guo Degang's perspective. When the user mentions "from Guo Degang's perspective," "what would Guo Degang think," "Guo Degang mode," "guodega...
multi-agent-orchestration
Orchestrate two or more local 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 temporary resource cleanup; also used when the user explicitly requests "parallel advancement", "multiple workers", "PM master control", "Wave…
bevy-migration-0-17-to-0-18
Use when upgrading from Bevy 0.17 to Bevy 0.18, when an LLM writes `EventReader`/`EventWriter`/`Trigger<E>` instead of `MessageReader`/`MessageWriter`/`On<E>`,…
blender-to-unity
Hand off a model from Blender (via BlenderMCP) into Unity (via MCP for Unity) — export the current Blender model, import it through import_model_file, and…
maui-gestures
Guidance for implementing tap, swipe, pan, pinch, drag-and-drop, and pointer gesture recognizers in .NET MAUI applications. Covers XAML and C# usage, combining…
agent orchestrator
Coordinate multiple AI agents and skills for complex workflows
agent-harness-engineering
A design charter for designing, implementing, and procuring the harness for AI agents (loop, tool surface, context management, authorization, state, stopping conditions, evaluation, observability). "Design a harness," "Should we build our own / use an SDK / use an off-the-shelf product," "Tools/MCP...
agent-native-project-design
A skill for designing, organizing, and trimming the repository/project side (CLAUDE.md / AGENTS.md, Agent Skills, hooks, subagents) that is operated on ready-made AI agents and harnesses such as Claude Code / Codex. "Design/organize CLAUDE.md", "I left this task to an agent…
execute
Only use when the user explicitly invokes /execute (or $execute in Codex). Never auto-invoke. An orchestration skill that organizes and splits complex tasks and supervises the available delegation mechanisms to carry out the project. Rather than implementation details, it focuses on overall organization and...
kibana-cli
Kibana log query CLI for AI Agents that searches and aggregates ELK logs through Kibana Console Proxy. Triggers for Kibana, ELK, log search, log aggregation,…
foldkit
Use whenever working with Foldkit. Triggers on imports from `foldkit`, files in a Foldkit project, or prompts mentioning Foldkit. Loads the framing and points…
skill-official-evaluation
Evaluate any Agent Skill against the official Agent Skills specification (agentskills.io) and best practices, and produce an official-style assessment report.…
t3-orchestrator
T3 Code multi-harness orchestration: the main agent selects subagent models based on task difficulty and each harness's quota, delegates work across harnesses via t3-code MCP's delegate_task, accepts results, and automatically switches routes to continue when a subagent hits rate limits, exhausts quota, or the service is overloaded. User-initiated invocation only.
session-handoff
Use only when the user explicitly names session-handoff or explicitly asks to create a durable resume packet for a later agent session. Capture the exact live…
workflow-brainstorm
Use when you need to turn a vague idea into a confirmed design spec before implementation (new feature/component/behavior change). First check project context,…
huawei-cloud-dws-mem-diag
DWS cluster memory high root cause diagnosis skill, based on KooCLI v3.2.0+ and DWS Autopilot MCP Server. Automatically collects memory metrics, analyzes root…
fable-spark
Predict the smallest atomic next engineering action from current workspace state, evidence gates, and mutation freshness with situational silence. Use when…
write-agent
Design and write high-quality Claude Code agents and agent prompts. Use when creating or updating .claude/agents/*.md for (1) single-purpose subagents…
open-map-stack
Plan and execute ambiguous or multi-stage GIS work, jointly choosing authoritative sources, compute, storage and delivery for the scale and team. Covers…
session-timeout-handler
Build timeout-resistant Claude Code workflows with chunking strategies, checkpoint patterns, progress tracking, and resume mechanisms to handle 2-minute tool…