skill-manifest-generator
Generate MANIFEST.json files for Agent Skills, providing content integrity verification, file inventory, and external reference tracking.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Agents & models
25,573 results
soia-meta-sync-skills
Synchronize a shared skill source to a user-explicitly-selected AI tool directory via symlinks; supports preview, single-item sync, hard-dependency closure, and restricted cleanup.
sprite
Controls InnerClaude instances on Sprites.dev VMs for testing workflows, install patterns, and Claude-to-Claude interaction. INVOKE BEFORE any 'sprite exec',…
agentlens
Navigate and understand codebases using agentlens hierarchical documentation. Use when exploring new projects, finding modules, locating symbols in large…
gosu-review
Post-build value review, not a bug review. A real panel of 5-6 independent subagents re-examines a built feature, PR, plan, or skill from the vantage of its…
solidcraft-agent-tools
Use when running SolidCraft to see a change working, driving it through the control channel or CLI, or adding or changing an MCP tool, control method or…
telnyx-ai-assistants-javascript
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
telnyx-ai-inference-go
Access Telnyx LLM inference APIs, embeddings, and AI analytics for call insights and summaries. This skill provides Go SDK examples.
telnyx-messaging-python
Send and receive SMS/MMS, handle opt-outs and delivery webhooks. Use for notifications, 2FA, or messaging apps.
telnyx-voice-streaming-go
Stream call audio in real-time, fork media to external destinations, and transcribe speech live. Use for real-time analytics and AI integrations. This skill…
tempo
Use this skill when the user wants to call an API, make an HTTP request, discover available services, or access external data with automatic payments. Activate…
herdr-faq
Launch and drive coding agents (codex, claude, agy) through the Herdr CLI; requires a herdr pane (HERDR_ENV=1). Use before starting or prompting a herdr…
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…
mcp-management
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP…
orchestration-blackboard
Shared filesystem-backed blackboard for multi-agent runs. Parallel subagents append findings for a given run-id; subsequent-round subagents read them via MCP…
lyft-engineer
Expert skill for lyft-engineer
moderna-scientist
Expert skill for moderna-scientist
feishu-bridge
Connect a Feishu (Lark) bot to ThinkFleet via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a…
interview-me
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence…
skills-smart-manager
Meta-skill for skill lifecycle management. Monitors active skills, optimizes context window by unloading stale skills, detects dependency conflicts, recommends…
create-skill
Create new skills for Claude agents. Use when adding specialized knowledge, workflows, or commands. Guides through structure, frontmatter, and conventions.…
create-work-item-planning-skills
Use when: adding Planner-only ID-based bug and user-story planning skills that create or resume isolated session artifacts.
llm_evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance,…
claude-gladiator
Use after tool failures or user corrections to record patterns, and when accumulated observations need clustering into rule/hook/skill recommendations. Builds…