Ollama
AICommonly used with
Skills using Ollama (1025)
flow-deliver
Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)
flow-parallel
Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates
flow-spec
NLSpec authoring — use when you need a structured specification from multi-AI research and consensus
octopus-architecture
System architecture and API design with multi-AI consensus — use for design reviews and new subsystems
octopus-quick
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
octopus-research
Thorough research across multiple sources — use for complex topics needing broad synthesis
octopus-security-audit
OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews
octopus-ui-ux-design
Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces
skill-audit
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
skill-claw
OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox
skill-code-review
Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis
skill-content-pipeline
Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages
skill-copilot-provider
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode
skill-cost-projections
Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns
skill-coverage-audit
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs
skill-debate
Structured multi-provider AI debates between Claude and available advisors — use for critical decisions
skill-debug
Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior
skill-decision-support
Present options with trade-offs for informed decision-making — use when choosing between approaches
skill-deck
Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries
skill-design-lineage
Persist design documents with branch tracking, revision chains, and cross-session discovery
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables
skill-doc-sync
Post-ship doc sync across project markdown. Use when: sync docs, update docs, document changes, release notes.
skill-doctor
Environment diagnostics — check providers, auth, config, hooks, scheduler, and more
skill-factory
Run a full build-and-ship pipeline from a spec — use for hands-off project generation
skill-finish-branch
Wrap up a branch — run tests, create PR, merge or discard — use when implementation is done
skill-issues
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage
skill-iterative-loop
Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence
skill-meta-prompt
Craft better prompts using proven optimization techniques — use when your prompt needs refinement
skill-parallel-agents
Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work
skill-prd
Write an AI-optimized PRD using multi-AI orchestration — use when scoping a new feature or product
skill-resume
Pick up where you left off from a previous session — use after context resets, compaction, or new conversations
skill-review-response
Use when a reviewer, CI bot, or another AI leaves feedback to address
skill-rollback
Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert
skill-security-framing
URL validation and content sanitization for untrusted sources — use when handling external input safely
skill-ship
Package and finalize completed work for delivery — use when a feature is done and ready to ship
skill-staged-review
Use when a PR or feature needs both specification and code-quality review
skill-status
Show where you are in the workflow and what to do next — use for progress checks and orientation
skill-tdd
Build features with tests-before-code rigor — use for new features needing test coverage
skill-thought-partner
Brainstorm creatively with pattern spotting and paradox hunting — use for ideation and exploration
skill-verification-gate
Use when about to declare work complete, fixed, passing, or done
skill-agent-topology
Audit whether a multi-agent setup earns its coordination cost — use before adding an agent, or when a workflow feels slow or agents agree without adding signal
skill-authoring
Principles for writing skills that behave the same way every run — use when adding, editing, or reviewing a skill in this plugin
skill-context-detection
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type
skill-extract
Reverse-engineer design systems, tokens, and components from live products or screenshots
skill-intake
Move incoming issues and pull requests through triage states until each is actionable or closed — use when the queue has piled up or a report arrives unsorted
skill-intent-contract
Use when starting a complex or ambiguous task that risks scope drift
skill-knowledge-work
Switch to Knowledge Work mode for research and writing — use when task is non-code focused
skill-pressure-test
Interrogate a plan, decision, or design one question at a time until it holds — use to stress-test your own thinking before committing to it
skill-visual-feedback
Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs
skill-native-escalation-routing
Use when choosing native or multi-LLM handling for init, review, or security requests
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
pinggy-tunnel
Zero-install localhost tunnels over SSH via Pinggy.
ollama
Deploy and serve local models with Ollama — pull and run them, then expose the OpenAI-compatible endpoint to apps and agents.
vllm
Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.
ocx
Drive a running opencodex (`ocx`) proxy from the CLI — account pools, provider routing, model catalog, usage and cost attribution, request logs, access keys, storage cleanup, and the management API. Use when a task involves controlling or inspecting an opencodex proxy rather than editing the opencodex codebase. Triggers: ocx, opencodex, proxy control, account pool, pause account, pool strategy, provider routing, usage report, cost attribution, access key, request log, conversation trace, storage cleanup, management API.
add-ollama-provider
Route a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting. Use when the user wants to run their agent locally, cut API costs, or experiment with open-weight models. See docs/ollama.md for background.
add-ollama-tool
Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.
customize
Add new capabilities or modify NanoClaw behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants.
council-execution
Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of consensus, divergence, and recommendations. Invoked by the ask command during standard (non-agent) council queries.
deep-execution
Executes agent-enhanced council queries as one Workflow of parallel Claude analyst agents that each query a provider, evaluate response quality, ask follow-up questions, and return a schema-enforced analysis with confidence ratings and blind spot analysis. Invoked when the --agents flag is used or when complex architectural decisions are detected.
local-council-execution
Runs a local council when no external AI providers are configured. Spawns N independent Claude subagents (one per role, blind to each other) that each answer the question from a single assigned lens, then synthesizes their perspectives. Invoked by the ask command via --local, or when the user accepts the local-council offer after no providers are found. This is a same-model (Claude-only) panel, not a cross-vendor council.
microsoft-extensions-ai
Build provider-agnostic .NET AI integrations with `Microsoft.Extensions.AI`, `IChatClient`, embeddings, middleware, structured output, vector search, and evaluation. USE FOR: building or reviewing .NET code that uses Microsoft.Extensions.AI, Microsoft.Extensions.AI.Abstractions, IChatClient, IEmbeddingGenerator, ChatOptions, or AIFunction;. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
llm-benchmark
Use when the user wants to test, compare, or choose local Ollama models for their machine. Checks Ollama/GPU state, recommends model sizes from available VRAM, preserves existing benchmark records, pulls only approved models, runs repeatable benchmarks, restores stopped services, and writes a markdown comparison report. NOT for hosted API model evaluation or subjective chat-quality judging without local benchmark commands.
ai-toolkit-trainer
Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and using the result in a ComfyUI workflow.
anima-base
Anime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT). Use for anime, manga, illustrated characters; accepts Danbooru tags + natural language; runs/trains on <6GB VRAM; includes anime inpainting via Anima-LLLite ControlNet
anima-lora-trainer
Train a custom anime LoRA on the ANIMA base model with Citron's local Gradio trainer (kohya sd-scripts), <6GB VRAM, character/style LoRAs; covers setup, dataset prep, training params, and using the result in the anima-base workflow
color-correction
Diagnose and fix video/image color OBJECTIVELY with the get_image (action:"analyze_color") tool (scopes/stats such as black/white points, contrast, saturation, clipping, cast) instead of eyeballing a contact sheet. Covers the "washed out" signature, why reference color-match (mkl/ColorMatch/ColorMatchAdobe) CAN'T add contrast a flat source lacks, the levels/contrast-stretch fix (core AdjustContrast / CurveEditor), the measure→fix→re-measure loop, the side-by-side sandbox pattern, and where to place the fix in a render graph (after decode, before save). Use when a render looks washed out / flat / dull / over-saturated / color-cast, or when deciding between a color-match and a contrast/levels fix.
comfyui-core
Core ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usage
comfyui-launch-flags
Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM (--novram / --cache-none / --disable-smart-memory), shared-VRAM creep on Windows (--reserve-vram N), model-switching with big text encoders (--cache-none), high-VRAM throughput (--gpu-only / --highvram), and attention-backend selection (--use-sage-attention for speed, --use-pytorch-cross-attention as the highest-quality / Z-Image-safe fallback). Also the acceleration-stack + Blackwell/RTX 5000 (sm_120) notes. Use when a graph OOMs (especially long video like LTX 2 / WAN), when the GPU spills into shared VRAM and slows to a crawl, when switching between models eats all RAM, when Z-Image produces black/garbled output under Sage, or when deciding which attention backend to launch with. Flag names verified against upstream comfy/cli_args.py; see Sources.
director
Full production pipeline covering story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips, ffmpeg concatenation
ernie-image
Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multi-object scenes. Also supports denoise-based image-to-image refine (NOT instruction-grounded editing; use Qwen-Image-Edit or Flux Kontext for "change X in this photo" edits).
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control
installer-packs
Use when installing a model family from an installer pack, or when building/deriving a new pack from an upstream installer or a workflow JSON. Explains the manifest-driven packs/ system and tells you to invite the user to contribute new packs back upstream.
krea2-identity-edit
Swap an OUTFIT or transfer CLOTHING onto a person LOCALLY, keeping their face, pose and background. Use for "put this jacket on her", "change his shirt", "clothes swap", "try on", "outfit transfer", "virtual try-on", "dress her in", "wear this outfit". Prefer this over API/cloud edit nodes and over generic img2img/inpainting. NOT for identity-preserving edits that are not about clothing (background swaps, relighting, age/expression changes, object removal). Use a general image-edit workflow for those.
krea2-txt2img
Build Krea 2 Turbo txt2img workflows with the native krea2 CLIPLoader, Qwen3-VL encoder, Qwen image VAE, 8-step turbo settings, and Ideogram-style JSON prompting
ltxv2-video
Build Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronized audio, two-stage upscaling, and swapping alternate/GGUF base models
minimax-h3-video
Build MiniMax H3 (Hailuo) local video workflows with native T2V/I2V/R2V nodes, Comfy-Org INT8 weights, turbo LoRAs for 8GB VRAM, 15-second stereo-audio clips, and the official MiniMax prompting guides (cite by link, do not copy).
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models
prompt-engineering
ComfyUI prompt engineering knowledge covering CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices
qwen-image-edit
Build Qwen Image Edit workflows covering model loading, conditioning, LoRAs, prompt patterns, and XY plot testing
qwen-txt2img
Build Qwen Image 2512 text-to-image workflows with QwenImageIntegratedKSampler, separate component loading, lightning LoRAs, and fine-tuned model variants
train-character-lora
Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train_* tools (GPU Docker + ostris ai-toolkit). Use when the user wants to train a LoRA of a person/character from their photos on the local GPU. Covers dataset prep, launch, monitoring, and using the result in ComfyUI. For WAN/Z-Image training via the ai-toolkit UI see ai-toolkit-trainer.
triton-sageattention
Install Triton + SageAttention to accelerate ComfyUI (the sageattn attention_mode and inductor torch.compile used by WanVideoWrapper / many video graphs). Windows-first (triton-windows + woct0rdho prebuilt SageAttention wheels matched to torch/CUDA/python into the RIGHT python), plus Linux (official triton + build) and Mac (N/A → sdpa/MPS). Also covers the SAFE sdpa / no-compile fallback so an example that assumes sageattn + torch.compile still runs when these aren't installed (video-extend TRAP 5). Use when a loader crashes with "No module named 'sageattention'" or reports triton unavailable, when asked to speed up Wan/video workflows, or when deciding whether to install acceleration vs. fall back.
troubleshooting
Common ComfyUI errors and fixes. OOM, missing nodes, dtype mismatches, black images, and debugging strategies
video-extend
Extend / continue a video temporally with Pusa 2.2 in ComfyUI. Temporal flowmatching (the flowmatch_pusa scheduler + WanVideoAddPusaNoise) on the WanVideoWrapper stack with WAN 2.2 T2V A14B (HIGH/LOW) models and the Pusa V1 LoRAs, conditioning on the loaded clip via WanVideoEncode so the existing motion carries into the continuation. Covers the kijai wanvideo_2_2_14B_Pusa_extension graph, model/LoRA slots + downloads, noise/length/scheduler settings, chaining multiple extensions, VRAM tiers, gotchas, and the extend→upscale handoff.
video-upscale
Upscale and restore video in ComfyUI. Both the quick local path (per-frame ESRGAN like 4x_foolhardy_Remacri via ImageUpscaleWithModel + 4x→2x supersample, with its temporal-flicker tradeoff) and temporal-aware super-resolution (SeedVR2, the newer FlashVSR) with the downscale-first restore pipeline; RIFE/FILM frame interpolation via the BUILT-IN ComfyUI 0.26 FrameInterpolate (rife_v4.26 in models/frame_interpolation/) or the ComfyUI-Frame-Interpolation pack; 2x/4x scaling, VRAM tiers, VHS encode. Captures the classic downscale→SeedVR2→RIFE recipe and the current 2026 recommendation.
wan-flf-video
Build WAN 2.2 First-Last-Frame video workflows. Native dual hi-lo (required), and WanVideoWrapper VACE approaches
wan-multitalk
Build WAN MultiTalk audio-driven talking-avatar / lip-sync video workflows. MeiGen-AI MultiTalk on WAN 2.1 14B I2V via kijai WanVideoWrapper (portrait + audio → lip-synced video)
wan-scail-replacement
SCAIL-2 in-video character replacement on WAN 2.1. WanSCAILToVideo + SCAIL2ColoredMask + SAM3, the reference-image framing→scale rule, and the tuning/compositing pitfalls
wan-t2v-video
Build WAN 2.2 Text-to-Video workflows. Dual hi-lo models, lightning LoRAs, VACE modules, and KSamplerAdvanced two-pass
z-image-txt2img
Build Z-Image txt2img workflows. RedCraft checkpoint, Z-Image Turbo/Base LoRAs, ControlNet, and sampler presets
ai-local-model-ops
Runs local and self-hosted LLM workflows with Ollama, LM Studio, MLX, Open WebUI, llamafile, and adapters. Use when operating private model stacks.
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST
langchain4j-spring-boot-integration
Provides integration patterns for LangChain4j with Spring Boot. Configures AI model beans, sets up chat memory with Spring context, integrates RAG pipelines with Spring Data, and handles auto-configuration, dependency injection, and Spring ecosystem integration. Use when embedding LangChain4j into Spring Boot applications, building Java LLM applications with @Bean configuration, or setting up Spring AI patterns.
langchain4j-testing-strategies
Provides unit test, integration test, and mock AI patterns for LangChain4j applications. Creates mock LLM responses, tests retrieval chains, validates RAG workflows, and implements Testcontainers-based integration tests for Java AI services. Use when unit testing AI services, integration testing LangChain4j components, mocking AI models, or testing LLM-based Java applications.
provider-integration
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API configuration", or "extend council".
sweep
Deploy parallel agents to scan the entire codebase for dead code, duplication, inconsistencies, and stale references
new-provider
用于在 cc-router 仓库新增一个 LLM provider（即在 src-tauri/providers/ 下添加 YAML 描述符并完成 5 处同步改动）。当用户说「加 provider」「接入 XX 厂商」「新增订阅源」「provider YAML」「让 cc-router 支持 OpenRouter/Together/Groq/Ollama 之类」时必须触发本 skill；即便用户只甩了一个厂商名或一个文档 URL，只要看起来在 cc-router 仓库内做新增 provider，就走本 skill 的工作流，不要绕过。本 skill 只覆盖「描述符层」扩展（YAML + 配置 + 测试 + 文档），不涉及调度/状态机的 Rust 改动。
route
Route a task to the best LLM based on task type and complexity
Showing top 100 of 1025 skills using Ollama by quality score.
See all 1025 skills via search →Integration detected automatically from skill content. Some results may be false positives.