zlei6/OpenMontage
1
0
Fork 0
mirror of https://github.com/calesthio/OpenMontage.git synced 2026-08-10 17:31:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add mandatory Layer 3 skill gate before any asset generation

Browse Source 
New Step 4b requires the agent to read agent_skills from every tool
before writing generation prompts. Discovered during UAT: agent
generated video clips, images, and TTS without reading provider-specific
prompting guidance, violating AGENT_GUIDE governance.
This commit is contained in:
calesthio
2026-04-04 13:20:19 -07:00
parent 97097e61a1
commit 93de8effbe
1 changed files with 26 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
skills/meta/video-reference-analyst.md
View File

@@ -263,6 +263,32 @@ costs, recommend one with a brief reason, and let them decide.
**Recommendation:** Always recommend one option with a brief reason why. Don't leave
the user paralyzed with equal choices.
### Step 4b: Layer 3 Skill Gate (MANDATORY)
**Before ANY asset generation** (sample or full production), the agent MUST:
1. Check the `agent_skills` field on every tool that will be used
2. Read each referenced skill in `.agents/skills/`
3. Apply the provider-specific prompting guidance to all generation prompts
This is NOT optional. The AGENT_GUIDE says: *"Layer 3 is not optional.
Every generation tool has an agent_skills field. Read them before writing
prompts."*
Example checklist before generating:
```
Tool agent_skills Read?
──────────── ──────────────────── ─────
video_selector ai-video-gen [ ]
flux_image flux-best-practices [ ]
elevenlabs_tts elevenlabs, text-to-speech [ ]
video_compose remotion-best-practices [ ]
```
Do NOT proceed to Step 5 until all relevant Layer 3 skills are read.
The difference between a generic prompt and a skill-informed prompt is
the difference between "usable" and "cinematic."
### Step 5: Sample-First Production (MANDATORY)
After the user picks a variant, ALWAYS say: