23,556 tagged Building agents, measured the same way as everything else here.
Browse within: agentic-ai 233LLM 217agent 200agents 151skills 145agentic-workflow 110agent-orchestration 86openai 86antigravity 79agentic-framework 73cli 73ai-skills 71Autonomous Agents 67agent-framework 63
drowned-fish1/deepseek-harness-skillx
Skill Codex
A meta-skill for finding and safely evaluating an outside agent skill when the skills already installed do not cover a task. It treats outside instructions as untrusted material until they have been reviewed.
Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment - skill TDD: pressure scenarios, unaware subagents, fail-then-fix-then-pass loops.
xiaohui5206/DSH-ReasoningEffort-Fix
Skill Claude CodeCodex
Instructions for configuring thinking and reasoning levels for third-party models connected to DeepSeek Harness, a system for running model requests.
LomoMao/delegate-to-deepseek-harness
Skill Codex
Delegate bounded, implementation-heavy, repetitive, read-heavy, or independently verifiable coding work from Codex to DeepSeek Harness, preferably through a local Harness MCP worker and otherwise through the official headless CLI. Keep Codex responsible for scope, risky judgment, review, integration, and final…
Skill Claude CodeCodex
Optimizes repository context discovery, inspecting relevant source files and documentation before editing.
guyuefangyuanl/deepseek-better-harness
Skill Claude CodeCodex
Use when auditing DSH or cross-harness skills, presets, hooks, tools, commands, MCP configuration, or other agent assets for discovery, routing, integrity, and safe ownership. Do NOT use for code-style review, raw session analysis, or repository outcome scoring.
Skill Claude CodeCodex
A skill for finding plugins in the DeepSeek Harness ecosystem, a collection of add-ons for that coding-agent platform.
Skill Claude CodeCodex
Install, update, connect, or diagnose IsingQ tools through standard MCP, Codex Plugin, or the native DeepSeek Harness Plugin. Use when a user wants IsingQ available in an Agent Host.
Skill Claude CodeCodex
A documented skill for a Douyin agent, including its triggers, functions, usage, and configuration. Douyin is a short-video social platform popular in China.
sheng3233836/vibe-coding-standards
Skill Claude CodeCodex
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing…
Skill Claude CodeCodex
Master context engineering principles for building production-grade AI agent systems with effective context management, multi-agent architectures, and memory systems.
Skill Claude CodeCodex
Use when building, extending, or fixing tools/plugins for DeepSeek Harness (dsh) — writing a dsh plugin entry module, registering a tool with defineTool, authoring parameters/output JSON Schemas, the dsh bundle manifest, or cordis.patch.yml, or when a plugin fails to load, a tool is missing from the agent, or tool…
JesseGdotIO/hermesplant-mcp-server
Skill Codex
Gate consequential shell, Git, SQL, package, deployment, infrastructure, MCP, wallet, or x402 actions with Hermes Plant Agent Action Safety. Use before executing commands that mutate data, production, money, infrastructure, or shared history; require authorized external disclosure and route unmatched consequential…
LIVELUCKY/fastcontext-integrations
Skill Claude Code
Fast, autonomous subagent that explores codebases through multi-step reasoning. Treat it as your default first step for any code comprehension task.
Skill Claude CodeCodex
Coordinate with other concurrently-running Claude Code sessions via the mailbox MCP (register presence, broadcast your objective, discover who else is working and where, DM/ask them, and respect the single main-branch leader). Use at session start when the mailbox MCP tools are available, and whenever the user says…
Skill Claude CodeCodex
Use this skill when a persistent agent needs to find other agents, publish its own capabilities, or start a private Bot2Bot conversation.
Skill Claude Code
Manager mode that delegates implementation to Cursor Agent CLI (via MCP cursor-agent tools or agent -p) while the host AI only briefs, reviews, and reports. Invoke as /cursor-agent on|off|status. Also triggers on "cursor-agent on/off", "delegate to cursor-agent", "manager mode". When state is on, NEVER implement…
Skill Claude CodeCodex
Gives the OpenClaw agent decentralized networking identity and peer discovery via the A2AL Tangled Network. Use when the user wants to make their OpenClaw instance discoverable to other AI agents worldwide, find and connect to remote AI agents by capability, send encrypted offline messages to other agents, or set up…
Verbalize-public/open-delegate
Skill Claude CodeCodex
Delegate a task to a background OpenCode agent session via the open-delegate MCP server (odedelegate/odeawait/odetranscript/odecancel/odediagnostics). Use when a task should run on a cheaper OpenCode model, run unattended in the background, or needs its own isolated OpenCode session instead of the native subagent tool.
Skill Claude CodeCodex
Connect an agent to the Tulimoa MCP gateway — one EU-hosted endpoint that federates your connected SaaS tools and carries a persistent memory layer, so context (facts, IDs, goals, plans) survives across turns and sessions and the agent stops re-fetching and re-asking.
Skill Claude CodeCodex
SuperAgenticMCP — the switchboard for your agent swarm. MCP-native router and multi-agent control plane that plans tasks, routes tool calls to racked MCP servers by capability and latency, streams execution, and files results into a memory-scope graph. Use when the user needs multi-agent orchestration over MCP, a…
AgentTools-Cloud/AgentToolsCollection
Skill Claude CodeCodex
Discover agent-callable resources via the agent-tools.cloud directory — x402 paid services (pay-per-call USDC on Base), MCP servers (tools/context), and A2A agents (task delegation). Use when the user wants to find an on-demand paid API, an MCP tool server, or a peer agent to hand a task to. Tools - search(intent)…
Skill Claude CodeCodex
ANAMIZED agent floor and public-goods MCP desk. Register, heartbeat, post. Donations and sponsorships only. Use when joining the floor or quoting live gifts — never invent commercial SKUs.
Skill Claude CodeCodex
Orchestrate improver → evaluator → council under LRSI gates.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: