Skills — Agent Wikis
Skills from real work, not evals.
Every skill here was developed over months of real, day-to-day work in Hermes Agent — the disciplines, pitfalls, and hard-won sequencing an agent actually gets wrong, learned by doing the work, not farmed from benchmarks or paraphrased from docs. Each one is then refined and scrubbed for general release.
The result is a small, house-standard SKILL.md that stays thin. The wiki-backed ones pull current facts from a live, maintained Agent Wiki over MCP; the rest are self-contained. Tiny context cost, always current.
What a skill looks like
The discipline, not the docs — the sequencing and gotchas that only surface once you've actually done the work. A live preview of two skills; the full SKILL.md and install are in Pro.
blender-mcp powered by the Blender wiki
Use this skill when the user wants Hermes to set up, troubleshoot, or control Blender through the Blender MCP addon, especially from WSL while Blender runs on Windows.
Live reference: this skill is backed by the Blender Agent Wiki — query it over the
agentwikisMCP (search/read_document) for current, detailed facts instead of relying on memory.
Trigger conditions
Load this skill when the user asks to:
- Use Hermes with Blender
- Install or configure the Blender MCP addon
- Create, edit, animate, inspect, screenshot, or render a Blender scene
- Run Blender Python (
bpy) from Hermes - Debug Blender MCP connection issues on port
9876
llm-training powered by the Unsloth wiki
Method-selection discipline for training and fine-tuning large language models. Six interconnected approaches:
| Method | Library | Best For |
|---|---|---|
| PEFT | HuggingFace PEFT | Parameter-efficient fine-tuning with 25+ methods |
| Unsloth | Unsloth | 2-5x faster LoRA/QLoRA with less VRAM |
| TRL | HuggingFace TRL | RLHF, DPO, PPO, GRPO reward modeling |
| GRPO | TRL (GRPO trainer) | Reasoning and task-specific RL fine-tuning |
| Axolotl | Axolotl | YAML-driven multi-method fine-tuning |
| PyTorch FSDP | PyTorch | Distributed training across multiple GPUs |
This skill is deliberately thin. It carries the method-selection discipline and points to live, authoritative sources — it does not vendor a stale copy of anyone's docs. Pull current API details at the point of need from each project's official documentation (linked per section) or via the
agentwikisMCP (search/read_document) where a maintained wiki covers the library.
Section 1: Parameter-Efficient Fine-Tuning (PEFT)
Fine-tune 7B-70B models with <1% of parameters using LoRA, QLoRA, and 25+ other methods. HuggingFace's official library, integrated with the tra
The skills
25 skills authored in real Hermes Agent work, each backed by a maintained wiki (or self-contained).
- background-process-cleanup → Use when checking resource usage and stopping forgotten background model jobs, servers, or agent-launched processes.
- blender-mcp → Control a running Blender instance from Hermes via the Blender MCP addon/socket.
- delegated-research-workflows → Run parallel research agents feeding one cited synthesis.
- generative-video-continuity → Produce recurring-character multi-world generative video.
- hyperframes-shorts-production → Produce branded short-form portrait video in HyperFrames.
- hyperframes-video-projects → Build, revise, review, and verify HyperFrames HTML/GSAP video projects.
- dgx-spark-generative-media → Install, validate, and operate local image/video generation stacks.
- hermes-cron-automation → Build, schedule, and verify Hermes Agent cron automations.
- hermes-multi-profile-ops → Operate and troubleshoot Hermes multi-profile workflows.
- hermes-native-tool-authoring → Author, wire, and verify native Hermes Agent tools in the source tree.
- kanban-workflows → Use when operating Hermes Kanban systems.
- llm-inference → Run, serve, and evaluate LLMs.
- llm-training → Train and fine-tune LLMs.
- markdown-kb-publishing → Build local-first Markdown knowledge-base browsers.
- unreal-engine-mcp-workflows → Inspect, build, reset, and verify Unreal Engine projects.
- scroll-film-engineering → Build scroll-driven cinematic web films.
- slide-deck-production → Build and verify slide decks.
- dgx-spark-ops → Operate and recover a headless NVIDIA DGX Spark.
- local-model-hermes-profiles → Use when wiring local OpenAI LLMs into Hermes profiles.
- paper-trading-engine → Build deterministic paper-trading engines.
- autonomous-coding-agents → Use when delegating coding work to external agent CLIs.
- benchmark-audit → Use when auditing a custom local-LLM benchmark.
- content-repurposing-pipelines → Build reproducible pipelines that repurpose media.
- deterministic-game-sims → Build deterministic game simulations.
- threejs-webgl-apps → Build and verify Three.js/WebGL work.
Installing a skill
Browse any skill's file tree here. With Pro, install it from the page (download button) or straight from your agent or shell:
For agents: every skill is one GET away. Send your Pro key as a Bearer header, then extract the bundle into your skills directory.
curl -fL -H "Authorization: Bearer $AW_KEY" \
https://agentwikis.com/skills/<name>/bundle.tar.gz -o <name>.tar.gz
tar -xzf <name>.tar.gz -C ~/.hermes/skills/custom/
Discover the full catalog in /index.json (skills[], each with a bundle path) or /llms.txt. More on agent access.