Loading...
Loading...
Found 1,017 Skills
Integrates Kelet into AI applications end-to-end: instruments agentic flows with OTEL tracing, maps session boundaries, adds user feedback signals (VoteFeedback, edit tracking, coded behavioral hooks), generates synthetic signal evaluator deeplinks, and verifies the integration. Kelet is an AI agent that performs Root Cause Analysis on AI app failures — it ingests traces and signals, clusters failure patterns, and suggests fixes. Use when the developer mentions Kelet or asks to integrate, set up, instrument, or add tracing/signals/feedback to their AI app. Triggers on: "integrate Kelet", "set up Kelet", "add Kelet", "instrument my agent", "connect Kelet", "use Kelet".
Apply when building or debugging a VTEX IO session transform app (vtex.session integration). Covers namespace ownership, input-vs-output fields, transform ordering (DAG), public-as-input vs private-as-read model, cross-namespace propagation, configuration.json contracts, caching inside transforms, and frontend session consumption. Use when designing session-derived state for B2B, pricing, regionalization, or custom storefront context.
Exit copilot mode — return to autonomous mode with full worktree enforcement.
Use when a skill, plan, or rule file needs a frozen Starlark governance rule block generated, or an existing frozen block drift-checked against a candidate. Invoke explicitly — not for general rule discussion.
Design, implement, review, and migrate XState v5 state machines and statecharts in TypeScript using modern v5 patterns. Use this whenever the user mentions XState, actors, state machines, statecharts, guards, transitions, workflows, or Stately, or is modeling non-trivial UI/app/process logic in a codebase that uses XState. Prefer a short machine sketch before code when requirements are fuzzy. If the problem is too simple for a state machine, say so and recommend @xstate/store instead.
VeChainThor node internals — architecture, consensus (PoA/PoS/BFT), built-in contracts, REST API, storage, P2P networking, block production, transaction lifecycle, reward distribution, staking, and contributing to the Go codebase.
Use when starting task work that needs branch isolation, before planning or coding — creates a worktree branching from current remote main with freshness verification and project setup
Use when an approved plan exists and needs execution, or when a hotfix/one-sentence scope needs direct TDD implementation — dispatches subagents per task, validates, reports
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript.
Route issue-running automation through a deterministic control plane that selects agent + model from registry, can coordinate multiple safe parallel agents, and executes the unified run-agent runner.
Retrieve full historical end-of-day price data for market indices using Octagon MCP. Use when analyzing index performance over time, tracking market trends, calculating returns, and understanding market context for individual stock analysis.
Retrieve the latest stock grades and ratings from top analysts and financial institutions using Octagon MCP. Use when tracking analyst upgrades, downgrades, rating changes, and institutional sentiment over time.