nats-design-subject
Design NATS subject hierarchies for messaging patterns (pub/sub, request/reply, streaming). Apply naming conventions, segmentation strategies, and wildcard…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-26 00:15
Agents & models
24,831 results
uipath-mcp-servers
UiPath Agent Gateway MCP servers (`uip agenthub mcp` / `uip agenthub mcp-tools`). Register, update, refresh tools, list, get, delete MCP servers: uipath…
work-log-claude
Generate work log reports based on Claude Code / Codex conversation records. Supports daily review, weekly reports, and real-time queries. Usage: /work-log-claude today | /work-log-claude this-week | /work-log-claude 2026-03-01 2026-03-11
router-engineering
Master orchestration for routing technical problems through the engineering skill set (AI/ML, software, data, APIs, Claude Code)
k8s-storage-exploit
Kubernetes storage and file sharing exploitation. Use when a Pod has mounted NFS/EFS/PV/ConfigMap/Secret, when /efs or /mnt directories are discovered, or when the mount output contains remote filesystems. Covers NFS mount exploitation, AWS EFS uid/gid spoofing, nfs-cat mountless reading, PV…
ai-agentic-workflow
Defines the analyse-plan-execute workflow that the agent must follow for non-trivial tasks.
ai-create-skill
Guides the agent through creating a new AI skill following the agentskills.io format and this repository's conventions.
hermes-dojo
Continuous self-improvement system for Hermes Agent. Analyzes your past sessions to find recurring failures and skill gaps, then automatically creates or…
glm-master-skill
Documentation-only master skill for GLM ecosystem discovery and installation. This skill does not execute scripts or subprocess commands. It provides a curated…
zr-review-discoveries
Review one discovered-task report and approve, reject, or escalate it when dispatched a ReviewDiscovery action.
multi-agent-architecture
Multi-Agent architecture design and intelligent Spawn system. Use this skill when you need to design a multi-Agent system, configure specialized Agents, implement intelligent task distribution, or optimize concurrent processing capability.
composio-mcp
Use when the user asks to connect an AI agent to external apps via Composio, or when Composio CLI or MCP setup fails.
pi-durable-dev-rules
Developer reference for building applications, tools, and agents on the Pi Durable agent harness (@earendil-works/pi-durable) and the pi-ai model layer. Use…
creating-claude-agents
Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and…
ralph-wiggum
Implements the Ralph Wiggum autonomous iteration technique with deliberate context management. Use when building greenfield projects, iterating on well-defined…
ghost-browser
Manus-level AI browser agent that drives Dhruv's REAL logged-in Chrome (any profile — AIV, Onsite, etc.) via natural-language commands. Persistent,…
turn-based-discovery
Use the AskUserQuestion tool (the same multiple-choice mechanism plan mode uses) to get clarity from the user. Each question is multiple-choice plus a…
agent-decision-receipts
Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified…
perplexity-api
Perplexity Sonar API for real-time web answers, citations, and search-augmented LLM.
help
Select a specialist for engineering, agent systems, writing, research, planning, or project work when the workflow is unclear.
doris-repo-review
Review an Apache Doris PR from a local clone with the same multi-agent, shared-ledger convergence workflow as the CI Code Review Runner. Use when the user…
create-skill
Scaffolds and validates new superpowers skills. Use when creating a new skill for this repository.
mcp-harness-repo-maintainer
Maintains repo-local action contracts and harness repositories where product CLI and MCP adapters stay thin over core libraries. Use when adopting or improving…
mixture-of-experts
Run a Mixture of Experts (MoE) audit on any topic, plan, codebase, evidence archive, or process. Dynamically spawns specialized subagents with different…