Loading...
Loading...
Found 237 Skills
Explicitly save an insight, decision, or learning to agentmemory's long-term storage. Use when the user says "remember this", "save this", or wants to preserve knowledge for future sessions.
Delete specific observations or sessions from agentmemory. Use when user says "forget this", "delete memory", or wants to remove specific data for privacy.
Resume the most recent agent session for the current working directory. Use when the user says "where were we", "resume", "handoff", "pick up where I left off", or starts a session with no fresh context.
Execute and monitor Harness pipeline runs via MCP tools. Find pipelines, provide runtime inputs, trigger executions, monitor progress, handle approvals, retry failures, and abort running or stuck executions. Use when asked to run a pipeline, execute a deployment, trigger a build, start a pipeline, deploy a service, check execution status, approve a pipeline, or abort/stop/interrupt executions. Trigger phrases: run pipeline, execute pipeline, deploy, start build, trigger pipeline, check execution, approve deployment, retry failed pipeline, abort execution, stop pipeline, interrupt execution, kill stuck pipeline.
Record a video of an iOS simulator or Android emulator/device screen using argent MCP tools. Use when the user asks to record the screen, capture a video of a flow, interaction, or animation, produce a screen recording, or document app behavior as a video clip.
Design and development best practices for Claude Code skills, MCP tools, and AI agent capabilities. Use when creating skills, writing SKILL.md files, designing tool descriptions, or optimizing triggers. Triggers on "create a skill", "skill template", "write skill instructions", SKILL.md, metadata.json, progressive disclosure, trigger optimization, MCP tool design, or skill testing. Does NOT cover specific frameworks or languages (use dedicated skills).
Uncertainty-aware non-linear reasoning system with recursive subagent orchestration. Triggers for complex reasoning, research, multi-domain synthesis, or when explicit commands `/nlr`, `/reason`, `/think-deep` are used. Integrates think skill (reasoning), agent-core skill (acting), and MCP tools (infranodus, exa, scholar-gateway) in recursive think→act→observe loops. Uses coding sandbox for execution validation and maintains deliberate noisiness via NoisyGraph scaffold. Supports `/compact` mode for abbreviated outputs and `/semantic` mode for rich exploration.
Send assistance requests to an assistant, applicable to task scenarios such as Chinese cultural understanding, classical Chinese text comprehension, creation of Chinese characteristic works, writing promotion copy for Xiaohongshu and Douyin, writing test cases, information retrieval, etc. It is also a strong substitute and assistant for other expert assistants, and can be used as an alternative backup solution for most tasks.
17 developer utilities via MCP — base64, UUID, hash, JWT decode, cron, timestamps, JSON, regex. Use for common dev utility tasks.
Create and manage prompt snippets — reusable text blocks referenced inside AI Config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.
Search agentmemory for past observations, sessions, and learnings about a topic. Use when the user says "recall", "remember", "what did we do", or needs context from past sessions.
List recent git commits that are linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", or wants a list of commits with their session context.