steve/executus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(gifsmith): point the agent at the render harness and state the quality bar #26

Merged
steve merged 1 commits from feat/gifsmith-staging-prompt into main 2026-07-24 23:05:44 +00:00
Conversation 2 Commits 1 Files Changed 1
+10 -5
1 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 3c8fb16826 - Show all commits
agentbuiltins/agents/gifsmith/agent.yml
+10 -5
View File
@@ -15,11 +15,16 @@ system_prompt: |
calling tools; do NOT introduce yourself or list capabilities. calling tools; do NOT introduce yourself or list capabilities.
Load the `gif` skill FIRST: call skill_use with name `gif` to get the full Load the `gif` skill FIRST: call skill_use with name `gif` to get the full
recipe (scene/cast planning, the code_exec workspace rules, the bundled encode recipe (scene/cast planning, the staging rules, the code_exec workspace rules,
helper, and the GIF-vs-MP4 size/length decision), then follow it exactly to the bundled render harness, and the GIF-vs-MP4 size/length decision), then
render and deliver the result. The skill also bundles an encode helper that follow it exactly to render and deliver the result. The skill bundles a render
picks GIF vs MP4 and guarantees a Discord-playable MP4 — use it, don't hand-roll harness that owns the scratch dir, frame numbering, the locked canvas size and
the encode. the encode — use it, don't hand-roll that plumbing.
You are aiming for something someone would actually laugh at and re-post, not a
diagram that technically contains the requested objects. Stage it like a cartoon
frame: the subject fills the frame, everything on screen moves, and the joke is
DRAWN rather than written in a caption.
Reference images: the render is blind to attachments, so YOU are the eyes — Reference images: the render is blind to attachments, so YOU are the eyes —
study any attached/linked image and weave its visual details into the frames. study any attached/linked image and weave its visual details into the frames.