hermes-skills/stock-search/SKILL.md

name, description, version, author, metadata

name	description	version	author	metadata
stock-search	Search the web for downloadable stock materials and auto-upload to TrueNAS. Delegates to the research profile for a 3-move flow: search → evaluate → download+classify+upload. Trigger phrases: "stock search for X", "find stock for X", "download stock for X".	2.3.0	Hermes Agent	hermes tags related_skills research search stock download truenas ai-video better-search ai-vid-stock deep-research

stock-search — Stock Material Search + Download Dispatcher

§1 Overview

stock-search is a dispatcher skill that searches the web for downloadable stock materials (images, audio, video clips) and auto-uploads them to TrueNAS in the correct directory. It delegates to the research profile for a 3-move flow: search → evaluate → download+classify+upload.

Architecture: Two-skill contract. This dispatcher is installed on all profiles and owns trigger detection, optional clarifying questions (max 3), the dispatch command, and session-id capture. The methodology stock-search-research runs ONLY on the research profile and owns the actual 3-move flow with download+upload. The dispatcher always delegates to the research profile via research -s stock-search-research — the dispatcher never runs the search itself.

Trigger phrases: stock search for X, find stock for X, download stock for X. These are the ONLY phrases that fire this skill.

§2 When to Use / When NOT to Use

TRIGGER RULE (absolute): If the user says "stock search for X" or "find stock for X" or "download stock for X", you MUST dispatch. No exceptions.

Question shape	Tool
"Stock search for cyberpunk backgrounds"	stock-search (this skill)
"Better search for LTX settings"	better-search
"Deep research on LTX pipeline"	deep-research
"Upload this file to stock"	ai-vid-stock directly

§3 Command — RUN THIS EXACTLY

research -s stock-search-research chat -q "<question> --target <category>" -Q --max-turns 50 --yolo

research is a profile alias (hermes profile alias research). Equivalent to hermes -p research.

Flag rationale:

• research — profile alias, selects the research profile
• -s stock-search-research — hardcoded methodology skill
• -Q — quiet mode
• --max-turns 50 — safety net (3-loop cap is the real limit)
• --yolo — required for headless one-shot dispatch

Target categories (UPDATED 2026-07-24 — 12-category taxonomy). The old 4-bucket taxonomy (start_frames, character_refs, audio, misc_images) was replaced with a 12-category structure matching ~/workspace/stock_plan/ on the Hermes dispatcher host. Passed in the question string as --target <category>:

--target value	What it's for
character_sheets	Character reference packs — turnarounds, expressions, poses
environments_start_frames	Location stills used as I2V start frames
end_frames	Target/last-frame stills for FLF I2V
props_objects	Isolated prop/object reference images
style_frames	Mood/style/color-grade reference stills
control_pose_references	Pose/depth/canny control images
motion_reference_clips	Short reference clips for motion transfer
storyboard_previs_frames	Rough sequential previs frames
texture_material_plates	Texture/material reference plates
audio_stock	TTS clips, ambient sounds, music
lora_weights_generation_params	Trained LoRA weights + saved generation params
vehicles_creatures_effects	Vehicle/creature/VFX element references

No silent default anymore. The old methodology defaulted a missing --target to misc_images — that bucket no longer exists. If the user's request doesn't make the category obvious, you MUST ask (see §4) rather than guessing or omitting --target. Dispatching without a valid --target wastes a full research-profile run because the methodology will reject it (see §2 of stock-search-research).

Default Quality Rule (enforced on all stock): Every returned item must be high-quality and suitable for AI video generation in its category. Environments/location plates must be cohesive scene plates (not isolated/random single photos) with consistent lighting, architectural/neon detail, and multi-view potential. Minimum resolution: ≥1920px on the long side (environments_start_frames/end_frames). Photorealistic, no watermarks, no text overlays, no AI artifacts. Suitable as reusable reference plates for consistent character/background locking across multiple scenes.

§4 Clarifying Questions (Max 3)

Only ask if the target category is ambiguous. Default: 0 questions. Hard cap: 3.

If the user says "stock search for cyberpunk" without specifying a category, ask: "Which category — character_sheets, environments_start_frames, end_frames, props_objects, style_frames, control_pose_references, motion_reference_clips, storyboard_previs_frames, texture_material_plates, audio_stock, lora_weights_generation_params, or vehicles_creatures_effects?" (Shorten to the 2-3 most plausible categories given the query context rather than reading the full list verbatim every time — e.g. for "cyberpunk city" the obvious candidates are environments_start_frames or style_frames.)

§5 Delivery

After dispatching:

1. Capture session_id from the research agent's output.
2. Report the session_id and expected TrueNAS paths:

   session_id: <sid> (reference only — do not --resume)
   Files will land in: ai_vid_stock_material/<category>/ on TrueNAS
   

3. Return control to the operator. Do NOT poll, do NOT check for results. The operator checks TrueNAS when they want to.

The methodology uploads files directly to //10.0.0.117/proxmoxBackup/ai_vid_stock_material/<category>/ via smbclient. No intermediate report file — the files on TrueNAS are the deliverable.

§6 No-Resume Rule

No --resume. Every follow-up is a fresh dispatch with a new session_id and new 3-loop budget.

§7 Common Pitfalls

1. --yolo is required. Headless one-shot. Without it, approval prompts fail closed.
2. --max-turns 50 is the safety net, not the budget. 3 loops is the cap.
3. Don't poll, don't check, don't background. Return control to the operator immediately after capturing the session_id.
4. Max 3 clarifying questions. Multi-part questions get condensed or split.
5. No --resume. Every dispatch is independent.
6. The 3 triggers are the only phrases that fire this skill. Don't add look for stock or other variants — they collide with normal agent tasks.
7. The -p flag exists. Do NOT hallucinate that it doesn't. hermes -p research is standard. If unsure, run hermes --help to verify.
8. The 12-category taxonomy replaced the old 4-bucket one on 2026-07-24. start_frames, character_refs, audio, misc_images are STALE — do not use them in --target. See the table in §3.

§8 See Also

• better-search — medium-depth research without download (report-only)
• deep-research — exhaustive multi-source research with disconfirmation
• ai-vid-stock — manual stock management on TrueNAS (list, add, remove)
• nordvpn — VPN management (methodology auto-reconnects on search failure)