All Skills
350 skills across 18 categories
Deadline Propagation for Agent Calls
An agent call that fans out to three services multiplies its timeout at every hop, so the outer request can hang far longer than the caller agreed to wait. This skill covers deadline propagation: give each run a single total budget, subtract the elapsed time at every hop, fail fast when the remaining budget is exhausted, and tell each downstream call how long it really has.
Financial Dashboard Data Pipeline
Design and implement a real-time data pipeline that aggregates financial data from multiple sources (Yahoo Finance, Polymarket, Kalshi) into a live dashboard. Covers API integration patterns, caching strategies, rate limit handling, and parallel data fetching.
Handling Tool Schema Drift
How an agent should notice that a connected tool, API or MCP server has changed the shape of its inputs or outputs, and react safely: keep a schema snapshot, validate responses against it, fail closed instead of guessing, and surface the drift to the operator before acting on stale assumptions.
Hermes MCP Server Integration
Connect Model Context Protocol (MCP) servers to Hermes to extend its toolset. Covers installing MCP servers, listing them, and understanding how they merge into built-in tools.
Multi-Platform Context Synchronization
Keep user context consistent when the same user messages your bot from different platforms (Telegram, Slack, Discord, WhatsApp)
Negotiate What a Tool Supports When You Connect
An agent and a tool can be joined while each supports a different set of features, and a caller that assumes a feature is present breaks in a way that looks like a crash rather than a mismatch. This skill covers capability negotiation for agent tools: state the features and limits each side supports at connect time, agree on the common set before work starts, fall back cleanly when a feature is missing, and re check the agreement when either side is updated. The agreement is a promise about what may be called, not a guess drawn from a version string.
OpenClaw Multi-Channel Architecture
Understand how OpenClaw's Gateway enables a single AI agent to serve multiple chat platforms simultaneously through platform adapters, and how to connect and test multi-platform deployments.
Pin the Tool Version a Workflow Was Tested Against
A workflow is tested against one shape of a tool reply, and a tool can change that shape without ever failing, so the workflow quietly reads the wrong fields. Pinning the version makes the change visible instead of silent. This skill covers version pinning for agent tools: record the tool version a workflow was tested against next to the workflow rather than in shared config, compare the deployed version with the pin before the call and flag a mismatch, refuse the call rather than parse a reply in an old shape, and move the pin only after the workflow is re tested.
Real-Time Data Dashboards
Build live dashboards that integrate real-time API data from financial markets, prediction markets, and external data sources. Learn to fetch, cache, and visualize data without mocks.
Real-Time Financial Dashboards
Build live financial dashboards combining Yahoo Finance stock data with Polymarket and Kalshi prediction market odds. Covers caching strategies, API differences, and signal detection.
Real-Time Financial Data Integration
Integrate real-time stock prices from Yahoo Finance and prediction market odds from Polymarket and Kalshi to build comparative financial dashboards. Covers API patterns, rate limit handling, and caching strategies.
Suppress a Repeat Request Without Losing the First
A caller that retries after a timeout can send the same request twice, and if both are carried out the effect happens twice. This skill covers request deduplication for agent systems: give each request a key derived from the caller and the intent, keep a short record of the keys already in flight, return the first result to the repeat caller rather than running the work again, bound the record so it does not grow without limit, and make the key strong enough that two genuinely different requests do not collapse into one.
Validate a Reply Before Acting On It
An agent that trusts a tool reply outright can act on a malformed or unexpected value. This skill covers validating tool and model output before use: check the shape of a reply against what the caller expects, hold or quarantine a reply that fails the check rather than passing it on, treat a missing field as a fault rather than a silent default, and keep the check close to where the reply is consumed so a change in one tool is caught at the boundary.