tools-update-cron: sync 2026-08-09 — 37 skill(s) updated

stock-search/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: stock-search
 description: '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".'
-version: 1.0.0
+version: 2.3.0
 author: Hermes Agent
 metadata:
   hermes:
@@ -56,21 +56,47 @@ research -s stock-search-research chat -q "<question> --target <category>" -Q --
 - `--max-turns 50` — safety net (3-loop cap is the real limit)
 - `--yolo` — required for headless one-shot dispatch
 
-**Target categories** (passed in the question string as `--target <category>`):
-- `start_frames` — first/last frame images for I2V
-- `character_refs` — character reference images
-- `audio` — TTS clips, ambient sounds, music
-- `misc_images` — unsorted images, inspiration
-- `all` — let the methodology classify by file type
+**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>`:
 
-If no `--target` is specified, the methodology defaults to `misc_images`.
+| `--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 — start_frames, character_refs, audio, or misc_images?"
+"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
 
@@ -105,6 +131,9 @@ new 3-loop budget.
    `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