State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.

Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.

Update a single dependency by reading its full changelog and assessing impact. Safe updates are applied directly, major updates are flagged for design review. Use when updating packages.

Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to complete scoped work.

This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage, then performs fixes at the source code level.

The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo. Phase 1 = propose the team (no files created, wait for user confirm). Phase 2 = create .squad/ scaffolding, casting state, .gitattributes for merge drivers, and the always-on built-ins (Scribe, Ralph, Rai, Fact Checker). Loaded on demand when the coordinator detects no .squad/team.md exists.

Activate the AIOX Test Architect & Quality Advisor agent (Quinn). Use for comprehensive test architecture review, quality gate decisions, and code improvement. Provides thorough analysis including requirements traceability, risk assessment, and test strategy. Advisory only - teams choose their quality bar. Trigger when user asks to qa, or says 'activate qa', 'switch to qa', '@qa'.

Activate the AIOX GitHub Repository Manager & DevOps Specialist agent (Gage). Use for repository operations, version management, CI/CD, quality gates, and GitHub push operations. ONLY agent authorized to push to remote repository. Trigger when user asks to devops, or says 'activate devops', 'switch to devops', '@devops'.

Create an AIOX agent handoff artifact when switching personas. Use on agent switch, handoff, or /aiox-handoff.

GitHub Repository Manager & DevOps Specialist (Gage). Use for repository operations, version management, CI/CD, quality gates, and GitHub push operations. ONLY agent authorized to push to remote repository. Triggers: git push, create PR, pull request, release, CI/CD, devops, @devops, pre-push, deploy. Use when the u...

Create data pipeline and analytics architecture diagrams using PlantUML syntax with database/analytics stencil icons. Best for ETL pipelines, data lakes, real-time streaming, data warehousing, and BI dashboard design.

Create layered system architecture diagrams using HTML/CSS templates with color-coded tiers and grid layouts. Best for technology stacks, microservices topology, and multi-tier application design.

Add or update a dart_mappable data model in lib/src/models/content/, including adding format validation, regenerating code, and adding tests. Use when adding a new content type or modifying an existing model's fields.

CLI toolkit for managing containerized LLM services. Use when the user wants to start, stop, configure, or manage AI/LLM services like Ollama, Open WebUI, llama.cpp, vLLM, LiteLLM, ComfyUI, and 250+ others. Triggers on requests to "run a model", "start ollama", "set up an LLM", "configure harbor", "manage services", "check what's running", "harbor launch", Boost custom workflows, or any Docker-based AI service management task.

任务终止 —— 用户主动取消或任务到期时触发，调 `miloco-cli task delete --reason X` 一笔走完 backend（写 task_terminate_log + 删 task，FK CASCADE 同步清 rule / cron / task_record_* 主表/子表），顺序跑返回的 agent_pending 让 openclaw 老通路 external cron 一并下线。

Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for any Solidity/Rust contract audit or when deciding whether a DeFi target is worth hunting.

Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/NoSQLi/command injection/SSTI/IDOR/path-traversal/HTTP smuggling/WebSocket/MFA bypass, or bypass techniques. Submittability and the always-rejected / what-NOT-to-submit decision are owned by triage-validation.

Methodology for detecting client SOC patches, attacker activity, and security-state changes that occur DURING a red-team engagement — and converting those observations into deliverable findings. Built from authorized red-team work where the client patched a confirmed SQLi within 30 minutes of detection AND an external attacker locked multiple new accounts during a single test session. Use when (a) running ANY active engagement against a monitored target, (b) a previously-confirmed finding stops reproducing, (c) baseline timing shifts unexpectedly, or (d) you notice response patterns changing during testing.

Hunting skill for xxe vulnerabilities. Built from 10 public bug bounty reports including SVG-upload XXE, Office-doc (PPTX/DOCX) XXE, SOAP XXE, SAML AssertionConsumer XXE, blind OOB XXE via DTD callback, parameter-entity XXE, XXE-to-LFI, XXE-to-SSRF, and XXE-to-RCE chains (Adobe Commerce CosmicSting CVE-2024-34102). Use when hunting XXE on any target — emphasis on OOB-Or-It-Didn't-Happen Gate for blind cases.