metaflow-to-zenml-migration
Migrate Metaflow flows and Outerbounds-flavored Metaflow projects to idiomatic ZenML pipelines. Handles concept mapping (FlowSpec->pipeline, @step->@step,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
Agents & models
26,319 results
prefect-to-zenml-migration
Migrate Prefect flows, tasks, and deployment patterns to idiomatic ZenML pipelines. Handles concept mapping (`@flow`→`@pipeline`, `@task`→`@step`, result…
harness
Pi-native evaluate→improve→persist harness. Provides a systematic loop for generating candidates, judging them against rubrics, and accumulating knowledge as…
zerion
Crypto wallet API + CLI for AI agents — install, authentication, and routing to specific Zerion capabilities. Use this skill for setup or to learn which…
zerion-agent-management
Manage Zerion agent tokens and security policies — the primitives for autonomous trading and signing. Create / list / use / revoke agent tokens; create / list…
build-workflow-plan
Break the spec into executable tasks. When the spec has been approved and tasks need to be split, or when "planning," "task breakdown," or "scheduling" is mentioned
maintain-workflow-using-unified
Unified runtime activation gate — use only when the user explicitly enters the Unified workflow, invokes a stage command, or mentions "Unified startup/routing/initialization"; not for ordinary repo Q&A or direct tasks that do not mention Unified
miniature-rescue-prompt
Generate the complete prompt sequence for a creative AI video of the "giant hand uses everyday small tools to save a miniature world from disasters" type (a three-beat structure of disaster scene + giant hand intervention + repair and cheers). This skill must be used when the user wants to make a miniature-model-style creative short video, mentions "miniature world," "giant hand disaster relief," "tilt-shift tiny kingdom," or "healing-style creative video," or wants to create a dimensionality-reduction creative expression for environmental, health, or social issues. Even if the user only says "I...
ziniao-page
Ziniao page operations (ZClaw local browser Bridge): navigation, clicking, input, screenshots, executing JS, extracting data, and other browser automation operations. Use when the user needs to operate page elements, take screenshots, or execute automation scripts in the Ziniao browser.
ziniao-skill-maker
Create a custom Skill for ziniao-cli. Use when the user needs to encapsulate ziniao API operations into a reusable Skill (wrapping atomic APIs or orchestrating multi-step processes).
orca-heimdall
Use `orca heimdall ...` to observe and manage durable Heimdall watchers: list the fleet, inspect status, escalations, workers, plans, and debug reports; create…
orchestration
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…
dsh-config
Show or set this session's DSH worker defaults (tier / effort / mode / timeout / on-off)
naiba-openai-managers
ChatGPT use cases and prompts for managers | Part of naiba-openai-work-assistant
5dive-cli
Operate the local 5dive runtime: coordinate sibling agents and inspect or update shared tasks. Use for delegation, inter-agent messaging and task-queue…
openagent
Author your own OpenAgent persona file and mint its shareable holo trading card — write, validate, tier and render `<id>.persona.yaml`. Use when creating or…
memory-management
memory-management — an installable skill for AI agents, published by aaron-he-zhu/seo-geo-claude-skills.
actionbook
Browser action engine. Provides up-to-date action manuals for the modern web — operate any website instantly, one tab or dozens, concurrently.
core-actionbook
Internal support skill for actionbook MCP selectors used by Rust documentation research workflows. Use only when another rust-skills workflow explicitly…
core-agent-browser
Internal support skill for agent-browser CLI workflows used by rust-learner, docs-researcher, and crate-researcher. Use only when browser automation is…
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure…
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before…
interview-me
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence…
planning-and-task-breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large…