docs: resync reference, user-guide, developer-guide, and messaging pages against code (#17738)

Broad drift audit against origin/main (b52b63396).

Reference pages (most user-visible drift):
- slash-commands: add /busy, /curator, /footer, /indicator, /redraw, /steer
  that were missing; drop non-existent /terminal-setup; fix /q footnote
  (resolves to /queue, not /quit); extend CLI-only list with all 24
  CLI-only commands in the registry
- cli-commands: add dedicated sections for hermes curator / fallback /
  hooks (new subcommands not previously documented); remove stale
  hermes honcho standalone section (the plugin registers dynamically
  via hermes memory); list curator/fallback/hooks in top-level table;
  fix completion to include fish
- toolsets-reference: document the real 52-toolset count; split browser
  vs browser-cdp; add discord / discord_admin / spotify / yuanbao;
  correct hermes-cli tool count from 36 to 38; fix misleading claim
  that hermes-homeassistant adds tools (it's identical to hermes-cli)
- tools-reference: bump tool count 55 -> 68; add 7 Spotify, 5 Yuanbao,
  2 Discord toolsets; move browser_cdp/browser_dialog to their own
  browser-cdp toolset section
- environment-variables: add 40+ user-facing HERMES_* vars that were
  undocumented (--yolo, --accept-hooks, --ignore-*, inference model
  override, agent/stream/checkpoint timeouts, OAuth trace, per-platform
  batch tuning for Telegram/Discord/Matrix/Feishu/WeCom, cron knobs,
  gateway restart/connect timeouts); dedupe the Cron Scheduler section;
  replace stale QQ_SANDBOX with QQ_PORTAL_HOST

User-guide (top level):
- cli.md: compression preserves last 20 turns, not 4 (protect_last_n: 20)
- configuration.md: display.platforms is the canonical per-platform
  override key; tool_progress_overrides is deprecated and auto-migrated
- profiles.md: model.default is the config key, not model.model
- sessions.md: CLI/TUI session IDs use 6-char hex, gateway uses 8
- checkpoints-and-rollback.md: destructive-command list now matches
  _DESTRUCTIVE_PATTERNS (adds rmdir, cp, install, dd)
- docker.md: the container runs as non-root hermes (UID 10000) via
  gosu; fix install command (uv pip); add missing --insecure on the
  dashboard compose example (required for non-loopback bind)
- security.md: systemctl danger pattern also matches 'restart'
- index.md: built-in tool count 47 -> 68
- integrations/index.md: 6 STT providers, 8 memory providers
- integrations/providers.md: drop fictional dashscope/qwen aliases

Features:
- overview.md: 9 image models (not 8), 9 TTS providers (not 5),
  8 memory providers (Supermemory was missing)
- tool-gateway.md: 9 image models
- tools.md: extend common-toolsets list with search / messaging /
  spotify / discord / debugging / safe
- fallback-providers.md: add 6 real providers from PROVIDER_REGISTRY
  (lmstudio, kimi-coding-cn, stepfun, alibaba-coding-plan,
  tencent-tokenhub, azure-foundry)
- plugins.md: Available Hooks table now includes on_session_finalize,
  on_session_reset, subagent_stop
- built-in-plugins.md: add the 7 bundled plugins the page didn't
  mention (spotify, google_meet, three image_gen providers, two
  dashboard examples)
- web-dashboard.md: add --insecure and --tui flags
- cron.md: hermes cron create takes positional schedule/prompt, not
  flags

Messaging:
- telegram.md: TELEGRAM_WEBHOOK_SECRET is now REQUIRED when
  TELEGRAM_WEBHOOK_URL is set (gateway refuses to start without it
  per GHSA-3vpc-7q5r-276h). Biggest user-visible drift in the batch.
- discord.md: HERMES_DISCORD_TEXT_BATCH_SPLIT_DELAY_SECONDS default
  is 2.0, not 0.1
- dingtalk.md: document DINGTALK_REQUIRE_MENTION /
  FREE_RESPONSE_CHATS / MENTION_PATTERNS / HOME_CHANNEL /
  ALLOW_ALL_USERS that the adapter supports
- bluebubbles.md: drop fictional BLUEBUBBLES_SEND_READ_RECEIPTS env
  var; the setting lives in platforms.bluebubbles.extra only
- qqbot.md: drop dead QQ_SANDBOX; add real QQ_PORTAL_HOST and
  QQ_GROUP_ALLOWED_USERS
- wecom-callback.md: replace 'hermes gateway start' (service-only)
  with 'hermes gateway' for first-time setup

Developer-guide:
- architecture.md: refresh tool/toolset counts (61/52), terminal
  backend count (7), line counts for run_agent.py (~13.7k), cli.py
  (~11.5k), main.py (~10.4k), setup.py (~3.5k), gateway/run.py
  (~12.2k), mcp_tool.py (~3.1k); add yuanbao adapter, bump platform
  adapter count 18 -> 20
- agent-loop.md: run_agent.py line count 10.7k -> 13.7k
- tools-runtime.md: add vercel_sandbox backend
- adding-tools.md: remove stale 'Discovery import added to
  model_tools.py' checklist item (registry auto-discovery)
- adding-platform-adapters.md: mark send_typing / get_chat_info as
  concrete base methods; only connect/disconnect/send are abstract
- acp-internals.md: ACP sessions now persist to SessionDB
  (~/.hermes/state.db); acp.run_agent call uses
  use_unstable_protocol=True
- cron-internals.md: gateway runs scheduler in a dedicated background
  thread via _start_cron_ticker, not on a maintenance cycle; locking
  is cross-process via fcntl.flock (Unix) / msvcrt.locking (Windows)
- gateway-internals.md: gateway/run.py ~12k lines
- provider-runtime.md: cron DOES support fallback (run_job reads
  fallback_providers from config)
- session-storage.md: SCHEMA_VERSION = 11 (not 9); add migrations
  10 and 11 (trigram FTS, inline-mode FTS5 re-index); add
  api_call_count column to Sessions DDL; document messages_fts_trigram
  and state_meta in the architecture tree
- context-compression-and-caching.md: remove the obsolete 'context
  pressure warnings' section (warnings were removed for causing
  models to give up early)
- context-engine-plugin.md: compress() signature now includes
  focus_topic param
- extending-the-cli.md: _build_tui_layout_children signature now
  includes model_picker_widget; add to default layout

Also fixed three pre-existing broken links/anchors the build warned
about (docker.md -> api-server.md, yuanbao.md -> cron-jobs.md and
tips#background-tasks, nix-setup.md -> #container-aware-cli).

Regenerated per-skill pages via website/scripts/generate-skill-docs.py
so catalog tables and sidebar are consistent with current SKILL.md
frontmatter.

docusaurus build: clean, no broken links or anchors.

website/docs/user-guide/skills/bundled/mlops/mlops-evaluation-lm-evaluation-harness.md

@@ -1,14 +1,14 @@
 ---
-title: "Evaluating Llms Harness — Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag)"
+title: "Evaluating Llms Harness — lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc"
 sidebar_label: "Evaluating Llms Harness"
-description: "Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag)"
+description: "lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Evaluating Llms Harness
 
-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.
+lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
 
 ## Skill metadata
 
@@ -30,6 +30,10 @@ The following is the complete skill definition that Hermes loads when this skill
 
 # lm-evaluation-harness - LLM Benchmarking
 
+## What's inside
+
+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.
+
 ## Quick start
 
 lm-evaluation-harness evaluates LLMs across 60+ academic benchmarks using standardized prompts and metrics.

website/docs/user-guide/skills/bundled/mlops/mlops-evaluation-weights-and-biases.md

@@ -1,14 +1,14 @@
 ---
-title: "Weights And Biases"
+title: "Weights And Biases — W&B: log ML experiments, sweeps, model registry, dashboards"
 sidebar_label: "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 - coll..."
+description: "W&B: log ML experiments, sweeps, model registry, dashboards"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Weights And Biases
 
-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
+W&B: log ML experiments, sweeps, model registry, dashboards.
 
 ## Skill metadata
 

website/docs/user-guide/skills/bundled/mlops/mlops-huggingface-hub.md

@@ -1,14 +1,14 @@
 ---
-title: "Huggingface Hub"
+title: "Huggingface Hub — HuggingFace hf CLI: search/download/upload models, datasets"
 sidebar_label: "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 Space..."
+description: "HuggingFace hf CLI: search/download/upload models, datasets"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Huggingface Hub
 
-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.
+HuggingFace hf CLI: search/download/upload models, datasets.
 
 ## Skill metadata
 

website/docs/user-guide/skills/bundled/mlops/mlops-inference-obliteratus.md

@@ -1,14 +1,14 @@
 ---
-title: "Obliteratus"
+title: "Obliteratus — OBLITERATUS: abliterate LLM refusals (diff-in-means)"
 sidebar_label: "Obliteratus"
-description: "Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE deco..."
+description: "OBLITERATUS: abliterate LLM refusals (diff-in-means)"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Obliteratus
 
-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.
+OBLITERATUS: abliterate LLM refusals (diff-in-means).
 
 ## Skill metadata
 
@@ -31,10 +31,21 @@ The following is the complete skill definition that Hermes loads when this skill
 
 # OBLITERATUS Skill
 
+## What's inside
+
+9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations.
+
 Remove refusal behaviors (guardrails) from open-weight LLMs without retraining or fine-tuning. Uses mechanistic interpretability techniques — including diff-in-means, SVD, whitened SVD, LEACE concept erasure, SAE decomposition, Bayesian kernel projection, and more — to identify and surgically excise refusal directions from model weights while preserving reasoning capabilities.
 
 **License warning:** OBLITERATUS is AGPL-3.0. NEVER import it as a Python library. Always invoke via CLI (`obliteratus` command) or subprocess. This keeps Hermes Agent's MIT license clean.
 
+## Video Guide
+
+Walkthrough of OBLITERATUS used by a Hermes agent to abliterate Gemma:
+https://www.youtube.com/watch?v=8fG9BrNTeHs ("OBLITERATUS: An AI Agent Removed Gemma 4's Safety Guardrails")
+
+Useful when the user wants a visual overview of the end-to-end workflow before running it themselves.
+
 ## When to Use This Skill
 
 Trigger when the user:

website/docs/user-guide/skills/bundled/mlops/mlops-inference-outlines.md

@@ -1,14 +1,14 @@
 ---
-title: "Outlines"
+title: "Outlines — Outlines: structured JSON/regex/Pydantic LLM generation"
 sidebar_label: "Outlines"
-description: "Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize..."
+description: "Outlines: structured JSON/regex/Pydantic LLM generation"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Outlines
 
-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
+Outlines: structured JSON/regex/Pydantic LLM generation.
 
 ## Skill metadata
 

website/docs/user-guide/skills/bundled/mlops/mlops-inference-vllm.md

@@ -1,14 +1,14 @@
 ---
-title: "Serving Llms Vllm — Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching"
+title: "Serving Llms Vllm — vLLM: high-throughput LLM serving, OpenAI API, quantization"
 sidebar_label: "Serving Llms Vllm"
-description: "Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching"
+description: "vLLM: high-throughput LLM serving, OpenAI API, quantization"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Serving Llms Vllm
 
-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.
+vLLM: high-throughput LLM serving, OpenAI API, quantization.
 
 ## Skill metadata
 
@@ -30,6 +30,10 @@ The following is the complete skill definition that Hermes loads when this skill
 
 # vLLM - High-Performance LLM Serving
 
+## When to use
+
+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.
+
 ## Quick start
 
 vLLM achieves 24x higher throughput than standard transformers through PagedAttention (block-based KV cache) and continuous batching (mixing prefill/decode requests).

website/docs/user-guide/skills/bundled/mlops/mlops-models-audiocraft.md

@@ -1,14 +1,14 @@
 ---
-title: "Audiocraft Audio Generation"
+title: "Audiocraft Audio Generation — AudioCraft: MusicGen text-to-music, AudioGen text-to-sound"
 sidebar_label: "Audiocraft Audio Generation"
-description: "PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen)"
+description: "AudioCraft: MusicGen text-to-music, AudioGen text-to-sound"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Audiocraft Audio Generation
 
-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.
+AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
 
 ## Skill metadata
 
@@ -146,6 +146,7 @@ torchaudio.save("sound.wav", wav[0].cpu(), sample_rate=16000)
 
 ### Architecture overview
 
+<!-- ascii-guard-ignore -->
 ```
 AudioCraft Architecture:
 ┌──────────────────────────────────────────────────────────────┐
@@ -165,6 +166,7 @@ AudioCraft Architecture:
 │        Converts tokens back to audio waveform                 │
 └──────────────────────────────────────────────────────────────┘
 ```
+<!-- ascii-guard-ignore-end -->
 
 ### Model variants
 

website/docs/user-guide/skills/bundled/mlops/mlops-models-segment-anything.md

@@ -1,14 +1,14 @@
 ---
-title: "Segment Anything Model — Foundation model for image segmentation with zero-shot transfer"
+title: "Segment Anything Model — SAM: zero-shot image segmentation via points, boxes, masks"
 sidebar_label: "Segment Anything Model"
-description: "Foundation model for image segmentation with zero-shot transfer"
+description: "SAM: zero-shot image segmentation via points, boxes, masks"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Segment Anything Model
 
-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.
+SAM: zero-shot image segmentation via points, boxes, masks.
 
 ## Skill metadata
 
@@ -151,6 +151,7 @@ masks = processor.image_processor.post_process_masks(
 
 ### Model architecture
 
+<!-- ascii-guard-ignore -->
 <!-- ascii-guard-ignore -->
 ```
 SAM Architecture:
@@ -163,6 +164,7 @@ SAM Architecture:
    (computed once)       (per prompt)             predictions
 ```
 <!-- ascii-guard-ignore-end -->
+<!-- ascii-guard-ignore-end -->
 
 ### Model variants
 

website/docs/user-guide/skills/bundled/mlops/mlops-research-dspy.md

@@ -1,14 +1,14 @@
 ---
-title: "Dspy"
+title: "Dspy — DSPy: declarative LM programs, auto-optimize prompts, RAG"
 sidebar_label: "Dspy"
-description: "Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's frame..."
+description: "DSPy: declarative LM programs, auto-optimize prompts, RAG"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Dspy
 
-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
+DSPy: declarative LM programs, auto-optimize prompts, RAG.
 
 ## Skill metadata
 

website/docs/user-guide/skills/bundled/mlops/mlops-training-axolotl.md

@@ -1,14 +1,14 @@
 ---
-title: "Axolotl"
+title: "Axolotl — Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO)"
 sidebar_label: "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)"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Axolotl
 
-Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
+Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).
 
 ## Skill metadata
 
@@ -30,6 +30,10 @@ The following is the complete skill definition that Hermes loads when this skill
 
 # Axolotl Skill
 
+## What's inside
+
+Expert guidance for fine-tuning LLMs with Axolotl — YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support.
+
 Comprehensive assistance with axolotl development, generated from official documentation.
 
 ## When to Use This Skill

website/docs/user-guide/skills/bundled/mlops/mlops-training-trl-fine-tuning.md

@@ -1,14 +1,14 @@
 ---
-title: "Fine Tuning With Trl"
+title: "Fine Tuning With Trl — TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF"
 sidebar_label: "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..."
+description: "TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Fine Tuning With Trl
 
-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.
+TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.
 
 ## Skill metadata
 

website/docs/user-guide/skills/bundled/mlops/mlops-training-unsloth.md

@@ -1,14 +1,14 @@
 ---
-title: "Unsloth"
+title: "Unsloth — Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM"
 sidebar_label: "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"
 ---
 
 {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */}
 
 # Unsloth
 
-Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
+Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.
 
 ## Skill metadata