editorial-engineer
Plan, research, write, and edit blog posts end-to-end. Positions the agent as a senior content engineer; the user is the manager who directs intent and…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-02 00:09
Agents & models
25,461 results
agent-browser-aircall-local
Open a headless browser authenticated with Aircall staging credentials for localhost development
prose-gen
Generate valid OpenProse workflow code from plain English descriptions. Use when the user wants to create multi-agent workflows, orchestrate sessions, or…
SkillsMP API
Search and discover AI skills from the SkillsMP marketplace
ai-memory-obsidian
Portable workflows for persistent memory and Obsidian across macOS, Linux, and Windows. Use when the user asks to recall or save past context, record…
lancer
Use lancer CLI for LanceDB semantic and multi-modal search with document ingestion, vector embeddings, and MCP server integration for knowledge retrieval.
dnd
Coordinate drag-drop QA
flutter-marionette-usage
Explain what the `flutter-marionette` plugin does and how to drive a running Flutter app through Marionette MCP. Use when the user invokes…
engineering-ai-pipelines
AI/ML production workflows: embedding generation, vector storage, RAG patterns, LLM monitoring, and batch inference.
llm-generation
Use for application prompts, generateObject/generateText, model selection and generation tracing. Excludes provider adapters and agent snapshots.
dsh-plugin-publisher
Publish a validated DSH plugin package (`@deepseek-ai/dsh-*` or `@lovstudio/dsh-*`) to npm, git, or tarball channels and verify it loads in the DeepSeek…
polpo-agents
Design and configure current Polpo agents, including directory-based definitions, model profiles and routing, tool policies and loading, assigned skills and…
clickup
ClickUp task management via MCP. Use for task updates, comments, time tracking, workspace navigation. Always interact in English.
pr-swarm
Parallelizes two or more independent "own PR to green" loops for a single repository using isolated git worktrees and separate headless Claude Code sessions…
simulink-explain-missing-coverage
Use this skill when the user asks to summarize, or asks why Simulink Coverage objectives are missing, unsatisfied, or uncovered on a coverage result they…
validation
Validate code quality, test coverage, performance, and security. Use when verifying implemented features meet all standards and requirements before marking…
agent-specialization
Guide creation of focused single-purpose agents following the One Agent One Prompt One Purpose principle. Use when designing new agents, refactoring general…
model-selection
Choose appropriate model for custom agent tasks. Use when selecting between Haiku, Sonnet, and Opus for agents, optimizing cost vs quality tradeoffs, or…
self-improve-prompt-design
Write self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for agent experts, designing validation…
genshijin-crew
Delegation decision guide for the genshijin-style subagent.`genshijin-investigator` (code location pinpointing), `genshijin-builder` (1-2 file edits),`genshijin-reviewer` (diff review) as inline work or vanilla `Explore`…
install-skills
Install skills of the ai-maxxing package on the user's VPS so their Hermes agent (and Claude Code on the server) can use them - connect-tool, create-landing,…
create-skill
Create a new agent skill (or Claude Code slash command) from a plain-language description, using live spec fetching, pattern research, and an approval-gated…
eval-guide
Eval enablement accelerator — help customers think through "what does good look like" for their AI agent, then generate a structured eval plan and test cases…
hve-builder-tester
Assess a frozen prompt, instruction, agent, subagent, or skill through black-box behavior testing with explicit fidelity and independent grading. Use for…