Loading...
Loading...
Found 82 Skills
Composes professional correspondence for development teams, technical announcements, stakeholder updates, and cross-functional communication. Analyzes audience, calibrates tone, structures content for clarity and actionability, and produces polished emails that convey technical concepts with precision and diplomacy. Like Hermes bearing messages between the gods, this skill ensures every missive arrives with clarity, purpose, and the weight of intent behind it.
Manage skills across 20+ AI platforms (Claude Code, Cursor, Copilot, Gemini, OpenClaw, Hermes, etc.). Use `list` as the unified entrypoint. Default behavior is listing skills only; only guide/recommend when the user explicitly asks what skill to use.
Use when the user wants to pair PocketClaw, install or upgrade ClawPilot, verify host runtime readiness, and generate a pairing code for OpenClaw, Hermes, or cc-connect Coding Agent hosts. Follow a strict pairing workflow and output the final pairing code on its own line when successful.
Install a single Skill or a collection of Skills to general Agents, Claude Code, Codex, WorkBuddy, Grok, Hermes Agent, Kiro, Qwen Code, Cline and other Agents. Use this when users request cross-Agent installation, synchronization, viewing, deduplication, or uninstallation of Skills.
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
Query-driven targeted ingest from a specific AI agent's raw history. Use this skill when the user invokes /wiki-claude, /wiki-codex, /wiki-hermes, /wiki-openclaw, /wiki-copilot — with or without a search topic. Different from wiki-history-ingest (which bulk-ingests everything new): this skill finds sessions about a SPECIFIC TOPIC in a specific agent's history and ingests just those, then returns a synthesized answer immediately usable in the current session. Primary use case: you're working in agent A and want to pull in how you solved X in agent B's history. Cross-referencing, not archiving. Also trigger on: "what did I work on in codex about X", "search my claude sessions for Y", "pull in hermes knowledge about Z", "find that conversation where I did X in codex".
Audit and reduce AI agent runtime spend in dollars. Use for AI costs, agent spend, token waste, runtime attribution, detector coverage, and FinOps. Works with OpenClaw, Hermes, QM, Claude Code, Cursor, and generic event ingest.
Maps pstack's delegation primitives to the current CLI (Claude Code, Codex, Hermes, or any other harness). Covers how to spawn a subagent, set a per-subagent model, parallelize arms, go read-only, ask a structured question (AskQuestion), open a todolist, loop, and locate the transcript store. Read whenever a pstack skill says spawn, Task tool, subagent_type, per-subagent model, AskQuestion, or todolist, or names a sibling skill you cannot find in your tool inventory. Every primitive is named differently per harness, so read this before concluding your harness has no such tool.
Agent-initiated spend via Stripe Link — requests purchases, issues virtual cards, owner approves in the Link mobile/web app. Hermes cannot self-approve. The 'spend' rail to complement stripe-payments.
Plan mode: write markdown plan to .hermes/plans/, no exec.
Himalaya CLI: IMAP/SMTP email from terminal.
Spotify: play, search, queue, manage playlists and devices.