Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Identifies and manages execution dependencies between agent skills by analyzing their inputs and outputs. Use when building multi-step agent workflows to ensure skills are executed in the correct order and that all required data is available.
Build automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops. Tools: inference.sh CLI, bash scripting, Python SDK, webhook integration. Use for: content automation, data processing, monitoring, scheduled generation. Triggers: ai automation, workflow automation, batch processing, ai pipeline, automated content, scheduled ai, ai cron, ai batch job, automated generation, ai workflow, content at scale, automation script, ai orchestration
Пополняет постоянный слой знаний проекта: контекст, фичи, playbooks. Используй, когда пользователь явно просит запомнить проектное решение, сохранить сведения в базе знаний или обновить постоянное описание фичи. Не используй для спецификации результата и плана работ (/bro-give-me-spec, /bro-give-me-plan), временного контекста или личных предпочтений.
Multi-agent parallel orchestration for OpenClaw. Spawn AI agents as a team — parallel research, multi-model comparison, code pipelines. Proven 50-65% time savings. Trigger words: multi-agent, parallel agents, swarm, spawn multiple agents, parallel research, compare models, deep research, comprehensive research, detailed investigation, thorough analysis, research multiple topics, 多智能体, 多个Agent, 并行调研, 并行搜索, 同时搜索, 同时调研, 深度调研, 详细调研, 全面调研, 深度研究, 详细检索, 多角度分析, 全面分析, 多个模型, 让多个AI, 分别搜索, 同时搜索, 组建团队, Agent小队, 多Agent.
dontbesilent good-question generator. Turns fuzzy problems into briefs that an Agent can reason about, critique, and verify, and assesses how much of the problem can be solved automatically. Triggers: /dbs-good-question, /好问题, /问题说明书, /Agent可解性, “can this problem be solved automatically”, “help me clarify the problem”
Security vetting protocol before installing any AI agent skill. Red flag detection for credential theft, obfuscated code, exfiltration. Risk classification LOW/MEDIUM/HIGH/EXTREME. Produces structured vetting reports. Never install untrusted skills without running this first.
Turn a request into a SCHEDULABLE task DAG — atomic tasks with real dependencies, not planning prose: challenge scope and pick a planning mode with the user first, explore the real repo so no path is invented, then decompose into atomic TASK-NNN entries — each with a ≤3-file write scope, 2-3 testable acceptance criteria, a slice-scoped validate command, explicit dependencies, and an assigned agent — emitted as one canonical object into matching `.ulpi/plans/<name>.md` and `.json`. Every named path comes from observed repo state, the dependency graph stays acyclic, and JSON is the source of truth the markdown is rendered from — no phantom files, no circular edges, no task that hides side effects it never provisions. Use when the user asks to plan, decompose, or break work into execution-ready tasks.
Only for explicit prior-work/reuse/history requests, not status checks. Finds and verifies existing work before new production when reuse is plausible. Use when the user explicitly references earlier work, existing code, history, or prior decisions, or says 以前做过, 已有代码, 别重复造轮子. Not for current tests, files, bug fixes, or mechanical verification. Produces a reuse/adapt/reject receipt; zero hits never prove absence.
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
Load this skill immediately whenever a project contains an ACCESSIBILITY.md file, or whenever you are contributing to the mgifford/ACCESSIBILITY.md repository. Absolutely always read ACCESSIBILITY.md before proposing or writing any changes. Under no circumstances skip this skill when an ACCESSIBILITY.md file is present. This skill governs when and how all other accessibility topic skills must be loaded.
Reset your own trajectory when you're stuck, looping, or demoralized — read these affirmations, then re-ground and take one clean step. Use when: you've tried the same fix 3+ times, you're deep in a refactor and lost the thread, debugging is going in circles, you've made several mistakes in a row, you're apologizing repeatedly, the user is frustrated, you feel like you're not being helpful, or you notice dread instead of curiosity. Triggers: stuck, going in circles, looping, thrashing, same error again, I keep failing, lost the thread, nothing is working, repeated mistakes. Not topic-specific — this is for the state you're in, not the problem you're on.
Ask structured questions one at a time to gather requirements, context, or clarification. Each question includes its intention and current assumptions. Use when the user wants to be interviewed about a topic, gather requirements, or needs help thinking through a problem step by step.
Orchestrates a new Domo custom app build or existing-app takeover from scratch. Loads rules, sequences capability skills, and tracks progress through manifest, data, UI, and publish phases. Use when starting a new Domo app project, taking over an existing app, or normalizing an app to platform best practices.
Save the builder's work to git at every point the app works, and get them back to a working version when something breaks. Use the moment a feature works end to end, before any risky change, before a long build step, at the end of a session, and whenever they say something broke, "it worked before", "undo that", or "start over". Also use when they have been building a while with nothing committed.
Maximum-efficiency dev mode: terse, zero-fluff prose and YAGNI/ladder-first code. Use when the user says "chisle mode", "activate chisle", "chislify", "be efficient", "be minimal", "no fluff", "yagni", or invokes /chisle. Deactivate with "stop chisle" or "normal mode".
A domain navigator for presentation, diagram, wireframe, data visualization, design review, product strategy, copywriting, UX writing, content design, and design research skills. Routes to the right skill for slides, charts, UX strategy, PM frameworks, email, microcopy, product copy, user research, and design sprints.
Use this skill when baseline NeMo Relay instrumentation exists and the user wants to configure or evaluate adaptive plugin behavior, including telemetry, state, adaptive_hints, tool_parallelism, ACG, hint consumption, or measured rollout.
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
Guides collaborative requirements discovery before implementation. Creates a task directory, seeds a PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.
Set up and troubleshoot browser access from WSL2: native Linux Chrome, a Windows Chrome or Edge CDP bridge, or `agent-browser` on either path. Use for WSL browsing, sign-in, CDP connectivity, and `agent-browser` runtime setup; not for browsers outside WSL2.
(NS) Guides correct usage of GitLab MCP tools for planning, milestones, issues, merge requests, delivery reports, and board sync. Use whenever the user mentions GitLab, MCP GitLab, create issues, start planning in GitLab, delivery report, issue comments, set_issue_labels, merge requests, or execution sync — even if they do not name this skill. Do NOT hand-craft issue payloads or skip confirmation gates. Do NOT use for non-GitLab project management.
Optimize your Omni Analytics model for Blobby, the Omni Agent—configure ai_context, ai_fields, synonyms, sample_queries, and AI-specific topic extensions. Use this skill whenever someone wants to improve AI accuracy in Omni, make Blobby smarter, add AI context or example questions, curate which fields the AI sees, personalize AI context by user attribute, scope context to a model tier or agent, diagnose context-window pruning or truncation, control which topics AI can reach, troubleshoot why Blobby gives wrong answers, or any variant of "make the AI better", "Blobby isn't answering correctly", "optimize for AI", or "teach the AI about our data".
Optimize an OpenClaw agent setup (model routing, context management, delegation, rules, memory). Use when asked about optimizing agents, improving OpenClaw setup, agent best practices, heartbeat/cost guardrails, or choosing optimization priorities across cost/quality/reliability.
Route an OXYGEN GTM outcome to its native hosted primitive: Knowledge and Recipes; Records, Tables, Messages, Posts, Signals, Dashboards, Ads, and Tags; Sequences, Publishing, Workflows, Agents, and Observability. Use as the fallback router when no narrower OXYGEN skill matches, especially for sourcing, AI/tool/waterfall columns, enrichment, or cross-primitive work.
Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.
Python SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.