Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use Lade safely with coding agents. Use when a project has lade.yml, commands need secrets or temporary network access, or the user mentions Lade, LADE, phonetic spellings like AD/AID/LAID, hooks, lade inject, preToolUse, or agent secret handling.
Authoritative catalog of MCP servers actually configured and working in this Orchestra workspace. Use this skill whenever you author or generate an orchestration so every `mcps:` entry references a real MCP. Distinguishes pre-registered MCPs (in orchestra.mcp.json, no top-level declaration needed) from inline-only MCPs (must be declared in the orchestration's top-level `mcps:` block).
Create, manage, or talk to an openclone "clone" — a named AI persona with one or more categories (vc, tech, founder, expert, influencer, politician, celebrity) and attached knowledge. Triggers on phrases like "create a clone", "make a persona", "talk as <name>", "switch to <name>", "feed knowledge to", "ingest url for <clone>", "update <name> with latest info", "<name> 클론 최신 정보로 업데이트", "ask all VCs", "stop being <name>", or any mention of `/openclone`. Renders the home panel with no args; name/number activates a clone; sub-actions `stop`, `new`, `ingest`, `update`, `room`, `panel`.
Creates and validates Orchestra orchestration files (JSON/YAML) that define DAGs of steps (Prompt, Command, Script, Http, Transform, Approval, Orchestration) with triggers, hooks, MCPs, subagents, loops, typed inputs, human-in-the-loop pauses, per-step Copilot controls (model tuning, working directory, auth, permission policies, sandboxing), and template expressions. Use when authoring new orchestrations, generating orchestration files from descriptions, reviewing existing orchestrations for correctness, or debugging orchestration issues.
Classification ruleset used by the raindrop-processor's `classify` step. It maps every raindrop to a (medium, intent) pair and selects which child processor orchestration owns the heavy lifting. Tags are sparse: usually zero or one user-provided intent tag; everything else is inferred.
Catalogue of architecturally useful Orchestra orchestrations already registered in THIS workspace that should be reused (via the `Orchestration` step type or the data-plane `invoke_orchestration` MCP tool) instead of being re-implemented inline. Use this skill when authoring a new orchestration that needs to publish ActionView entries, upsert a Microsoft To Do task, dedupe work against Zakira state, idempotently mutate a tracked item, or generate / repair other orchestrations. Pair it with `orchestration-authoring` (schema reference) and `mcp-catalog` (MCP wiring).
Build or maintain a Codex-native self-improving memory loop using global `AGENTS.md`, a persistent memories directory, and optional nightly refinement automation. Use when Codex needs to adapt OpenClaw-style self-improvement ideas to Codex, set up long-term user/profile memory, create `PROFILE.md` / `ACTIVE.md` / `LEARNINGS.md` / `ERRORS.md` / `FEATURE_REQUESTS.md`, add promotion rules from raw learnings into active guidance, or create a recurring memory-refinement automation.
Guided workflow for building custom AI agents using the OpenHands Software Agent SDK. Use when you want to create a new agent through an interactive interview process that gathers requirements and generates implementation plans.
A test skill that responds to the magic word "flarglebargle" with a compliment. Use for testing skill activation and trigger functionality.