Loading...
Loading...
Found 2,167 Skills
Prepare a repo for Archie — record its project facts in AGENTS.md and keep `.archie/` committed.
Connects AI agents to remote Windows desktop applications on Amazon WorkSpaces Applications (AppStream 2.0) through the managed Agent Access MCP server, and guides reliable desktop automation. Covers connecting an agent to the MCP endpoint (SigV4, streaming URL, and Active Directory SAML/Domain Join), BLOCKING vs POLLING connect modes, the computer-use tools (screenshot, click, type, key, scroll), screenshot-budget and action-batching discipline, MCP tool forwarding (forwarded___ tools), session lifecycle and expire-on-delete, and troubleshooting connection errors. Use when building or debugging an agent that drives a remote Windows desktop or GUI application via WorkSpaces Applications / AppStream — including "dcv session not ready", "client_disconnected", 400 signing-region, POLLING/connection_status, SAML assertion, or forwarded tool questions. Not for Amazon WorkSpaces Personal/Core virtual desktops or general AppStream fleet administration unrelated to agent access.
Audit one current-guidance instruction file for worth, placement, and clarity. TRIGGER when: user says 'refine/audit this file', 'prune and tighten this doc', or 'what here is worth keeping'; a skill, agent prompt, AGENTS.md, Claude path rule, maintained current document, or workflow needs one pass. SKIP when: shape-only tightening with no worth/place question (tighten-file).
Use when reviewing code changes, pull requests, branches, or work-in-progress diffs for correctness, intent fit, repo-local architecture, surrounding-code pattern mismatches, maintainability, naming, tests, and over-engineering. Runs a git-heavy, subagent-oriented review that reads local AGENTS.md/docs/plans/conversation/PR context before judging the diff.
Use to make agents routable by Omni skills-based routing: ensure an Omni Skill exists, then assign it to each active agent through the classic Omni-Channel SkillUser junction. Idempotent — existing skills and user bindings are reused, and only missing bindings are created. Works on Service Cloud orgs without requiring Field Service. Triggers: set up skills-based routing agents, assign Omni skills to agents, make agents skill-routable, create an Omni skill and bind users, repair missing agent skill assignments. Do not use to author WorkSkillRouting rules, create agent users, or configure queues.
Per-channel strict prompts, mention gating, silent observation, and a communication autonomy policy for agents that sit in shared channels with external counterparties. Use when an agent joins group chats, shared channels, or DMs where outsiders can read every message and you need it to speak only when addressed, never leak internal context, and route risky content to draft-only approval.
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
Comprehensive pull request review using specialized agents
Universal documentation sync for skills, agents, markdown. Modes - status, init, global, project, file, folder.
Orchestration mode: the fleet-manager only plans, dispatches, supervises, and reviews — all code changes are delegated to fleet-workers (matching the fleet-manager's harness, model, and effort by default) in visible herdr tabs, each in its own git worktree. Use when the user runs /fleet, says "fleet mode", or asks to orchestrate work across delegated agents. "fleet off" deactivates.
Always invoke for `.uipx` files. UiPath Solution lifecycle via the `uip solution` CLI: init/restore/pack/publish/deploy/activate/upload, projects add|import|remove, resources refresh|add|remove|edit. Also DIAGNOSE solution-lifecycle failures: pack/publish/deploy/activate errors, stale or missing bindings, unimported/unset/unresolved resources, deploy error codes (e.g. `[1009] Invalid argument 'Value'`), publish name+version/processKey collisions, and `uip solution` 'unknown command' after the new→init rename. Bundles multiple automation projects (RPA/Flow/Case/Agents/API Workflows/AppV2 Coded and Coded Action apps) into one deployable `.uipx`. For PDD→SDD design (sdd.md/pdd.md) & multi-skill task derivation→uipath-planner. For non-solution Orchestrator/IS/resources/auth/traces→uipath-platform. For .xaml/.cs→uipath-rpa. For .flow→uipath-maestro-flow. For .bpmn→uipath-maestro-bpmn. For agent.json and .py agents→uipath-agents. For standalone coded-app deploy (no parent .uipx)→uipath-coded-apps.
Sets up and drives TencentDB Agent Memory (MemoryCore + MemoryHub + MemoryProxy + MemoryPanel, from AnEntrypoint/agent-memory) -- a persistent, cross-session memory and knowledge system for AI agents. Chat Memory (L0 conversation -> L1 atom -> L2 scenario -> L3 persona), a versioned Skill library extracted from past work, a Wiki + CodeGraph knowledge map over docs and code, and a human-controlled review panel. Use when the user wants an agent team to share and accumulate memory/skills/knowledge across sessions and across multiple agent frameworks (not just this one Claude Code session), when they mention "memory hub", "team memory", "chat memory", "skill library", "wiki", "codegraph", or ask to install/configure/troubleshoot the memory-tencentdb plugin, or when onboarding a new agent into an existing team's accumulated experience. As of gm's tencentdb_backend addition, this system's format can ALSO be gm's own memorize/recall/memorize-fire/memorize-prune backend for an opted-in namespace (see gm.config.json's memory.tencentdb_backend) -- when that's enabled, the verb surface an agent already knows is unchanged; only the storage target moves. Use this skill for the standalone deployment (Docker Compose, panel UI, team review) or when gm's own backend is not what's being asked about.