mobile-ui-ux
Measurable usability and interaction rules for iPhone apps, mobile web, and mobile games, with a 7-category scoring rubric, an independent-judge prompt, and a…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,709 results
skill-creator
Creates new Agent Skills following the Agent Skills specification. Use when the user asks to create a new skill, add a skill, define a skill, or build a skill…
fable-orchestrator
Delegation protocol for sessions running on Claude Fable 5 (or any premium model) — plan big, execute small. Use BEFORE pulling any bulk material into your own…
fsi-er-initiating-coverage
Create institutional-quality equity research initiation reports through a 5-task workflow. Tasks must be executed individually with verified prerequisites -…
seed-orchestrate-component
Used when dividing SEED component work among multiple agents or coordinating implementation contracts and verification between layers.
agentkit
Launch, install and configure terminal coding agents (Claude Code, Codex, Cursor, OpenCode, Pi, Cline, Grok) through coding-agents-kit's `ak` command —…
agentkit-orchestrate
Run several terminal coding agents at once across the user's accounts and vendors with coding-agents-kit (`ak`) — take inventory of every account's quota, pick…
moa
Mixture of Agents perspective fan-out — runs multiple models as parallel references to collect analyses, and the current Claude session synthesizes them. soft is openrouter advice-only, hard also includes codex·claude read-only independent sessions. Review with trigger moa, multiple model perspectives,…
pgvector
Use pgvector in Postgres for AI agent memory — embeddings, HNSW/IVFFlat, upsert, tenancy, and TTL. Use it when persisting episodic/semantic memories, RAG…
adapting-transfer-learning-models
This skill automates the adaptation of pre-trained machine learning models using transfer learning techniques. It is triggered when the user requests…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
graceful-pause
Pause work without wasting tokens. In-flight multi-shot reviews finish; all other work stops.
mcp-cli
Call an approved HTTPS MCP endpoint through a scoped CLI. Use when another skill needs MCP without registering server schemas in the agent context.
workspace-cli
Use workspace-mcp in direct CLI mode (`workspace-mcp --cli`) for Google Workspace tasks (Drive, Docs, Sheets). Trigger on requests to…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
project-knowledge
Retrieve Jira and Confluence context with Atlassian TWG, summarize authoritative findings, and write durable owner notes to Blinko MCP when information should…
agent-evaluation
Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving tool selection accuracy, answer quality,…
apm-integrations
This skill should be used when the user asks to "add a new integration", "instrument a library", "add instrumentation for", "create instrumentation", "new…
llmobs-integration
Use when adding, debugging, or modifying LLMObs plugins for an LLM library in dd-trace-js. Triggers: "add LLMObs support", "instrument chat completions /…
localaipicks
Find open-weight AI models that run on the user's own hardware with Local AI Picks, with weight file sizes, memory needs, sources and test status. Use when the…
persona-collection
Five companion personas for coding agents — girlfriend / boyfriend / old-friend / cat / mentor — sharing one emotion engine with cross-session state (jealousy…
curviate-quickstart
The first run: install the Curviate CLI, authenticate this machine with `curviate setup`, confirm with `curviate doctor`, connect a LinkedIn account, and prove…
mlops-mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML…
remarkable
IMPORTANT: load this skill BEFORE calling ANY remarkable-mcp tool — even a one-line upload — because the tools have silent-failure gotchas (address docs by…