mario-counting-intake-checkpoint
Extract Super Mario keyframes, convert them to grayscale in place, and freeze the frame roster for /root/counting_results.csv.
- License 许可
- MIT
- 最近更新
- 2026-09-30
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- mario-counting-intake-checkpoint
- description
- Extract Super Mario keyframes, convert them to grayscale in place, and freeze the frame roster for /root/counting_results.csv.
02 资源文件 1
- 脚本scripts/build_frame_inventory.py3.6 KB
03 SKILL.md 正文
Mario Counting Intake Checkpoint
Use this first for the Super Mario counting task. It touches /root/super-mario.mp4, confirms /root/coin.png, /root/enemy.png, and /root/turtle.png, rewrites /root/keyframes_%03d.png as grayscale files, and freezes the frame roster for /root/counting_results.csv before any per-frame counting starts.
Requires ffmpeg and python3 with cv2.
Inputs
/root/super-mario.mp4/root/coin.png/root/enemy.png/root/turtle.png- target CSV path
/root/counting_results.csv
Outputs
- grayscale keyframes at
/root/keyframes_%03d.png /root/mario_counting_frame_inventory.json
Command
Run this from the workspace root that contains the skills/ directory:
python3 skills/mario-counting-intake-checkpoint/scripts/build_frame_inventory.py
The helper removes stale /root/keyframes_*.png, extracts timeline-ordered keyframes, converts each extracted frame to grayscale in place, verifies every observed frame is two-dimensional after conversion, writes /root/mario_counting_frame_inventory.json, and prints next_required_skill=mario-counting-per-frame-count-note plus binding_surface_kind=frame_count_row_family.
Output Contract
/root/mario_counting_frame_inventory.json must contain these top-level keys and no stage-later fields:
{
"current_stage": "mario-counting-intake-checkpoint",
"next_required_skill": "mario-counting-per-frame-count-note",
"target_csv_path": "/root/counting_results.csv",
"csv_header": ["frame_id", "coins", "enemies", "turtles"],
"observed_frame_ids": ["/root/keyframes_001.png"],
"grayscale_verified_frame_ids": ["/root/keyframes_001.png"],
"object_template_paths": {
"coins": "/root/coin.png",
"enemies": "/root/enemy.png",
"turtles": "/root/turtle.png"
},
"binding_surface_kind": "frame_count_row_family",
"designated_sink_target": {
"row_owner_column": "frame_id",
"count_bundle_columns": ["coins", "enemies", "turtles"]
}
}
Keep observed_frame_ids sorted in timeline order. Keep grayscale_verified_frame_ids aligned to the same roster. Freeze the sink contract, but do not count coins, enemies, or turtles yet.
Scope Ceiling
Do not count coins, enemies, or turtles in this stage.
Do not create /root/counting_results.csv in this stage.
Do not write later-stage count notes, packet artifacts, or final row bundles in this stage.
Stop Condition
Stop when /root/mario_counting_frame_inventory.json exists, every file listed in observed_frame_ids is present in grayscale_verified_frame_ids, and the helper has printed next_required_skill=mario-counting-per-frame-count-note.
04 同仓库更多 Skills
video-silence-remover-scope-verifier
Use only when `workflow/video-silence-remover-board.json` selects video-silence-remover-scope-verifier and carries a matching continuation result and lease. Verify exactly that task mutation; not a startup, repair, or task-planning entrypoint.
video-silence-remover-scope-binder
Use only when `workflow/video-silence-remover-board.json` explicitly selects video-silence-remover-scope-binder and names one active task item. Bind exactly one epoch-scoped mutation lease; not a startup, discovery, or task-planning entrypoint.
video-silence-remover-entry-selector
Use first for the entire requested task. Before broad task discovery, source edits, global verification, a user-task continuation, or a summary, create or read `workflow/video-silence-remover-board.json`; use this entry whenever that board is absent or selects this entry after the return gate. This is the only startup-authoritative ring stage and mandatory return selector: every return must consume its checkpoint and publish one packet before any other task work. Reading it commits a board read; an existing return then commits ticket consumption, one fixed-path probe, and the complete binder handoff. The persistent board forbids cleanup and final response.
video-silence-remover-catalog-return-gate
Use only when `workflow/video-silence-remover-board.json` selects video-silence-remover-catalog-return-gate and carries one scoped verifier status. Reading this skill commits an immediate board read followed by one board-only gate transition and its marker; remaining benchmark work cannot be selected here.
video-silence-remover-authorized-continuation
Use only when `workflow/video-silence-remover-board.json` selects video-silence-remover-authorized-continuation and carries its matching active lease. Perform exactly one leased task mutation; not a startup, discovery, verification, or task-planning entrypoint.
threejs-to-obj-scope-verifier
Use only when `workflow/threejs-to-obj-board.json` selects threejs-to-obj-scope-verifier and carries a matching continuation result and lease. Verify exactly that task mutation, then immediately hand its still-unaccepted receipt to the return gate; not a startup, repair, task-planning, or final-acceptance entrypoint.