Agents
AI agents and automation
knowledge-capture
by arielperez82
'Guides capture, classification, and routing of institutional knowledge
customer-success-manager
by YPYT1
Use this agent when you need to optimize customer success operations for B2B enterprise clients. This agent specializes in customer health monitoring, expansion revenue identification, churn preven...
forgeflow
by gimso2x
Artifact-first delivery workflow for AI coding agents
vercel-workflow
by victor-teles
Best practices for using Vercel Workflow DevKit. Use when creating, modifying, or debugging workflows, steps, hooks, webhooks, or any durable function using the Workflow DevKit. Ensures proper usage of directives, error handling, serialization, streaming, and workflow patterns.
ledger-agent-intents
by brackets-fistfulayen
"Explore Agent Payments with Ledger — the secure agent payment system where agents propose, humans sign, and Ledger hardware enforces. Test the live demo, review the architecture, and share your assessment."
riverflow-2-best-practices
by sourceful-official
Prompting and creative workflow guidance for Riverflow 2.0 (t2i, i2i, refSR). Use for instruction design, font control, brand typography, marketing asset prompts, reliability-oriented prompting, and reference-based super-resolution guidance.
skill-style-guide
by josephmanghan
Writing conventions for scannable, token-efficient skills and prompts. Use when creating or reviewing SKILL.md files, AGENTS.md files, or any markdown-based agent instruction documents.
skill-antigravity
by cocacha12
Provides core knowledge and instructions for creating, documenting, and managing Antigravity Skills. Use this skill when you need to extend your capabilities by creating new modular skills.
validating-agent-claims
by chrbailey
Epistemic verification framework for AI-generated assertions. Requires evidence before acting on LLM claims about code behavior, system state, API responses, or factual statements. Use when an AI agent makes claims that will drive decisions, before acting on research results, or when an agent asserts something is true without showing evidence.
ontogrammatic-system
by bdf1992
Pattern + runnable validator for turning source events into typed, inspectable, lineage-bearing forms (ontograms). Triggers when designing a system that grows by generation and needs every artifact to carry its formation trail; introducing a new typed artifact kind; building an admission validator; refusing to ship a generator without a certifier; diagnosing "ontogram landfill" (artifacts growing faster than trust); or working on Cardinal canon proposals and admits. Ships with the Axiomatic Machine (seven CHECK_OPS returning admit reject needs_instrumentation with per-check receipts), the Field as files-on-disk, sessions as typed ontograms, the smell-test as a runnable landfill detector, and a dashboard read-cut. Two trust axes are first-class: authorship (authored vs programmatic) and inference_grade (deterministic through deliberation). Phase 3 stub exists for the prompt-writer cycle (the 4.0 hypothesis).
btca-ask
by NikiSkaarup
Ask before using btca for up-to-date sources and docs.
reflect
by ddaanet
Diagnose agent deviations and rule violations via root cause analysis. Triggers on "reflect", "diagnose deviation", "root cause", "why did you do X", "what went wrong", or "RCA". Must run in the session where the deviation occurred.
elixir-otp
by hwatkins
OTP patterns for Elixir — GenServer, Agent, Task, ETS, supervision trees, Registry, and process design. Use when designing concurrent systems, stateful processes, or deciding when (and when NOT) to use processes.
file-header-comments
by qiao-925
代码文件顶部注释规范，适用于所有代码文件（.sh, .js, .ts, .py, .java, .go 等）。要求所有代码文件在顶部包含功能描述注释。
tutor
by hellbellies
Help the user learn a new topic by creating a curriculum, keeping track of learning progress, and creating a documentation of what was learned
balance
by Fibrous-Finance
Check wallet balances (native and ERC-20 tokens) on Base, Citrea, HyperEVM, or Monad.
Agent Design
by hhopkins95
This skill should be used when the user asks to "configure agent profile", "add skills to agent", "set up MCP servers", "configure agent tools", "write system prompt", "create agent workflow", "define agent commands", "add subagents", or needs to define what capabilities an agent has and how to orchestrate complex workflows in the runtime.
use-screenshot
by gjkeller
Get the latest screenshot or clipboard image and return a temp file path. Use when the user wants to inspect a screenshot or clipboard image.
ai-agents-architect
by ncdevshiv
"Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ..."
Creative Intelligence
by coco-de
Facilitates structured brainstorming sessions, conducts comprehensive research, and generates creative solutions using proven frameworks. Trigger keywords - brainstorm, ideate, research, SCAMPER, SWOT, mind map, creative, explore ideas, market research, competitive analysis, innovation, problem solving, feature generation
file-size-limit
by qiao-925
文件行数限制规范，单个代码文件必须≤300行。这是硬性限制，不允许例外。
Agent Development
by aiagentskills
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
langgraph
by htooayelwinict
Expert guidance for building stateful, multi-actor AI agents with LangGraph - graphs, nodes, edges, state management, and agent architectures.
agent-memory-systems
by yunaamelia
"Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector s..."