一键导入
raw-fpv-visual-labeler
Label visible cleanup-relevant movable objects from grouped RAW-FPV frames without creating executable cleanup handles.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Label visible cleanup-relevant movable objects from grouped RAW-FPV frames without creating executable cleanup handles.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Select and run Roboclaws validation, product, eval-suite, and live-agent eval rows from a plan, diff, or explicit capability request.
Complete open-ended household robot goals through public household MCP tools.
Drive the ADR-0003 MolmoSpaces real-world cleanup MCP contract.
Align scene Gaussian/splat, USD/mesh, and robot map assets into an honest digital-twin evidence workflow. Use when a new Gaussian scene arrives, when B1/Map12-style assets need to be connected, when map anchors are being projected into a 3D scene, or when an agent must decide whether an alignment is candidate, verified, runtime-proven, or planner-backed.
Create blog, README, social, or demo-review visual showcases from completed Roboclaws run artifacts, especially chaptered GIFs/contact sheets for household cleanup runs. Use when asked to turn report output, robot_views, traces, or run_result.json into polished visual result evidence without rerunning the robot task.
Use this skill whenever the user asks whether a Roboclaws live-agent report run is faster, wants to compare Agent SDK/Codex/Claude cleanup reports, asks about model-call work, residual latency, speedup validity, or report performance under provider/network variance. The skill extracts sanitized JSON metrics first and answers only from generated metric/comparison artifacts, not from report.html scraping or raw prompts.
| name | raw-fpv-visual-labeler |
| description | Label visible cleanup-relevant movable objects from grouped RAW-FPV frames without creating executable cleanup handles. |
Use this skill only for perception-only RAW-FPV labeling probes. It consumes
public robot FPV frame evidence and emits structured visual labels for review
and offline scoring. It does not call cleanup tools, does not create
observed_* handles, and does not authorize navigation, pick, place, or done.
Use 3-6 neighboring RAW-FPV frames from the same waypoint, sweep segment, or source observation neighborhood when available. Each frame may include only:
Never include private labels, generated hidden target ids, acceptable destination truth, executable observed-object handles, detector candidates, or camera-label producer candidates.
Return strict JSON:
{
"schema": "raw_fpv_visual_labeler_response_v1",
"labels": [
{
"evidence_frame_id": "run/raw_fpv_001",
"category": "mug",
"category_family": "dish",
"coarse_region": "middle_right",
"confidence": 0.82,
"is_cleanup_relevant": true,
"bbox": [0.62, 0.5, 0.12, 0.15],
"surface_hint": "table",
"reason_not_actionable": ""
}
]
}
Required per label:
evidence_frame_idcategorycategory_familycoarse_regionconfidenceis_cleanup_relevantOptional per label:
bboxsurface_hintreason_not_actionableAllowed category families are food, dish, book, linen, toy, and
electronics. Fixtures and surfaces such as tables, beds, counters, shelves,
sinks, cabinets, and floors may be mentioned only as surface_hint or as
is_cleanup_relevant=false; they are not object hits.
These labels are perception evidence. The cleanup agent must not consume them
as executable handles in camera-raw-fpv. A later assisted RAW-FPV or
camera-grounded-labels producer decision would need its own contract change.