docs(skills): compress 74 built-in skill descriptions to <=60 chars

Target: every skill's description fits in a one-line gateway menu and
leads with trigger keywords an agent would match on. Drops filler like
'Use this skill to', 'A skill for', 'This skill provides'.

Before: max description length was 791 chars (architecture-diagram),
74 of 81 built-in skills were >60 chars.

After: max 60, mean 54, all 81 built-in skills <=60.

Rewritten with double-quoted YAML scalars to preserve Chinese/arrow
glyphs (baoyu-comic, yuanbao, youtube-content).

skills/mlops/evaluation/lm-evaluation-harness/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: evaluating-llms-harness
-description: Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
+description: "lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.)."
 version: 1.0.0
 author: Orchestra Research
 license: MIT

skills/mlops/evaluation/weights-and-biases/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: weights-and-biases
-description: Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
+description: "W&B: log ML experiments, sweeps, model registry, dashboards."
 version: 1.0.0
 author: Orchestra Research
 license: MIT

skills/mlops/huggingface-hub/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: huggingface-hub
-description: Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.
+description: "HuggingFace hf CLI: search/download/upload models, datasets."
 version: 1.0.0
 author: Hugging Face
 license: MIT

skills/mlops/inference/obliteratus/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: obliteratus
-description: Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.
+description: "OBLITERATUS: abliterate LLM refusals (diff-in-means)."
 version: 2.0.0
 author: Hermes Agent
 license: MIT

skills/mlops/inference/outlines/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: outlines
-description: Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
+description: "Outlines: structured JSON/regex/Pydantic LLM generation."
 version: 1.0.0
 author: Orchestra Research
 license: MIT

skills/mlops/inference/vllm/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: serving-llms-vllm
-description: Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
+description: "vLLM: high-throughput LLM serving, OpenAI API, quantization."
 version: 1.0.0
 author: Orchestra Research
 license: MIT

skills/mlops/models/audiocraft/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: audiocraft-audio-generation
-description: PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
+description: "AudioCraft: MusicGen text-to-music, AudioGen text-to-sound."
 version: 1.0.0
 author: Orchestra Research
 license: MIT

skills/mlops/models/segment-anything/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: segment-anything-model
-description: Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
+description: "SAM: zero-shot image segmentation via points, boxes, masks."
 version: 1.0.0
 author: Orchestra Research
 license: MIT

skills/mlops/research/dspy/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: dspy
-description: Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
+description: "DSPy: declarative LM programs, auto-optimize prompts, RAG."
 version: 1.0.0
 author: Orchestra Research
 license: MIT

skills/mlops/training/axolotl/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: axolotl
-description: Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
+description: "Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO)."
 version: 1.0.0
 author: Orchestra Research
 license: MIT

skills/mlops/training/trl-fine-tuning/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: fine-tuning-with-trl
-description: Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
+description: "TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF."
 version: 1.0.0
 author: Orchestra Research
 license: MIT

skills/mlops/training/unsloth/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: unsloth
-description: Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
+description: "Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM."
 version: 1.0.0
 author: Orchestra Research
 license: MIT