hivemind
Orchestrate free opencode workers from Claude Code to cut token costs. Use when delegating grunt work to a single worker or a parallel swarm…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
alibabacloud-oss-multipart-upload-diagnosis
Read-only diagnostics for OSS multipart upload. Use when a multipart upload is stuck or interrupted, a large file upload fails, or multipart fragments occupy…
alibabacloud-oss-ossfs-mount-diagnosis
Read-only diagnostics for ossfs and container OSS mounts. Use when an ossfs mount fails, a mounted directory disappears, an ACK/ACS storage volume mount…
hyper-execute
[Hyper] Use this skill when the user asks to run an existing written work plan to completion: executing a plan file under `.hyper/plans/` wave by wave in…
hyper-mass
[Hyper] Use this skill when the user asks for dependency-ordered multi-agent work as a graph: a task DAG, a mass run, "dependency graph", or "stage-by-stage parallel", where some tasks…
altimate-code
Delegates data engineering tasks to altimate-code, a specialized CLI agent with 100+ purpose-built data tools — SQL analysis, column-level lineage, dbt…
handoff
Compact the current conversation into a handoff document for another agent to pick up. Use when the user wants to pass work to a fresh session, hand off to a…
prd-review-panel
Multi-agent PRD review (7 perspectives)
precision-mode
Universal conciseness and precision directive for all LLM output. Prepend to any system prompt to eliminate verbosity, filler, and fluff from every response.
antinet-doc-parse
Software engineers and data scientists, when building RAG systems, need to handle complex documents in multiple formats such as PDF/Word/Excel. With this skill, a three-level parsing fallback can be automatically triggered, outputting high-confidence structured Markdown and metadata in one click, eliminating tedious cleaning and directly solidifying the data foundation of the enterprise knowledge base!
antinet-provenance
For software development engineers and information security analysts building multi-agent systems, use this skill when full-chain observability and security auditing are required. It automatically collects operation logs, generates a traceable chain of evidence and vector indexes, and delivers out-of-the-box system auditing and precise replay, making Agent operation secure and transparent.
ios-mcp-routing
Route Apple/iOS agent work between Argent MCP and XcodeBuildMCP (and when to combine both in one session). Use when choosing tooling for build, compile, test,…
agent-instruction-forge
Guide humans through creating effective instruction rules for coding agents (Copilot, Claude Code, Cursor, Windsurf, Aider, AGENTS.md, CLAUDE.md, .cursorrules,…
context-engineering-orchestrator
Entry point for context engineering work. Routes to the right skill based on what the user needs — creating instructions, debugging agent failures, building…
rule-quality-evaluator
Evaluate the quality of existing agent instruction rule sets — CLAUDE.md, AGENTS.md, .cursorrules, copilot-instructions.md, or any coding-agent context file.…
x-chat-provider
Focus on implementing custom Chat Provider, helping to adapt any streaming interface to Antdv Next X standard format
binder-gauntlet
Validation and developability gauntlet for de novo designed protein binders and miniproteins against any protein target. Use this skill when designed binders…
ecosystem-health
Detect drift between skills, agents, MCP servers, vault paths, and CLI tools. Read-only diagnostics with remediation pointers.
afk-team-workflow
Form a team for all sub-issues of a Spec (or an explicit set of issues) and run unattended until all are merged or explicitly paused.
arkiv-mcp
Use an already connected Arkiv MCP for source discovery, optional public-evidence verification and event preparation. Explain tools versus skills and diagnose…
trigger-agents
AI agent patterns with Trigger.dev - orchestration, parallelization, routing, evaluator-optimizer, and human-in-the-loop. Use when building LLM-powered tasks…
trigger-tasks
Build AI agents, workflows and durable background tasks with Trigger.dev. Use when creating tasks, triggering jobs, handling retries, scheduling cron jobs, or…
external-gitcode-ascend-vllm-tests-failure-analysis
Analyze and debug upstream vLLM test failures on Ascend NPUs. Adapt test cases from `vllm/tests/` for the vllm-ascend plugin, and identify tests that are…
openclaw-token-optimizer
Find potential token waste in OpenClaw or Hermes Agent. Use when asked to reduce AI costs, review model choices, check large instructions or audit recurring…