output-validation

Local self-check of instructions and mask outputs (format/range/consistency) without using GT.

Security Scan

The skill's instructions and requested actions match its stated purpose (local validation of interval/mask outputs); it is an instruction-only validator that reads local video, JSON, and NPZ files and performs consistency checks.

Purpose & Capability

Name and description describe local output validation; SKILL.md contains focused checks (key format, coverage, NPZ/CSR structure, value validity) that directly implement that purpose. Nothing in the instructions attempts to access unrelated services or secrets.

Instruction Scope

Instructions operate on user-supplied local files (VIDEO_PATH, INSTRUCTIONS_PATH, MASKS_PATH) and perform file- and content-level assertions. They do not ask the agent to read unrelated system files, environment variables, or send data externally. The scope stays within validating generated outputs.

Install Mechanism

This is instruction-only (no install spec), which is low-risk. The reference snippet uses Python libraries (numpy, cv2) but the skill does not declare runtime dependencies or required binaries; users should ensure Python + numpy + OpenCV are available in their environment.

Credentials

No environment variables, credentials, or config paths are requested. The skill's data access is limited to the file paths the user supplies, which is proportionate to its validation purpose.

Persistence & Privilege

The skill is not always-on and does not request persistent or elevated privileges. It does not modify other skills or system-wide settings.

Assessment

This skill is an instruction-only local validator for interval/mask outputs and appears coherent with that purpose. Before installing/using: (1) ensure you run it in an environment with Python, numpy, and OpenCV (cv2) available, since the snippet assumes those libraries; (2) provide only trusted local VIDEO_PATH / INSTRUCTIONS_PATH / MASKS_PATH files (the checks read those files but do not contact external services); (3) be prepared for the snippet to raise assertions on invalid data — consider running it in an isolated environment or CI step; and (4) if you need automated installation, request or add an explicit install spec declaring required packages to avoid surprises.

When to use

• After generating your outputs (interval instructions, masks, etc.), before submission/hand-off.

Checks

• Key format: every key is "{start}->{end}", integers only, start<=end.
• Coverage: max frame index ≤ video total-1; consistent with your sampling policy.
• Frame count: NPZ f_{i}_* count equals sampled frame count; no gaps or missing components.
• CSR integrity: each frame has data/indices/indptr; len(indptr)==H+1; indptr[-1]==indices.size; indices within [0,W).
• Value validity: JSON values are non-empty string lists; labels in the allowed set.

Reference snippet

import json, numpy as np, cv2
VIDEO_PATH = "<path/to/video>"
INSTRUCTIONS_PATH = "<path/to/interval_instructions.json>"
MASKS_PATH = "<path/to/masks.npz>"
cap=cv2.VideoCapture(VIDEO_PATH)
n=int(cap.get(cv2.CAP_PROP_FRAME_COUNT)); H=int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)); W=int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
j=json.load(open(INSTRUCTIONS_PATH))
npz=np.load(MASKS_PATH)
for k,v in j.items():
    s,e=k.split("->"); assert s.isdigit() and e.isdigit()
    s=int(s); e=int(e); assert 0<=s<=e<n
    for lbl in v: assert isinstance(lbl,str)
frames=0
while f"f_{frames}_data" in npz: frames+=1
assert frames>0
assert npz["shape"][0]==H and npz["shape"][1]==W
indptr=npz["f_0_indptr"]; indices=npz["f_0_indices"]
assert indptr.shape[0]==H+1 and indptr[-1]==indices.size
assert indices.size==0 or (indices.min()>=0 and indices.max()<W)

Self-check list

• JSON keys/values pass format checks.
• Max frame index within video range and near sampled max.
• NPZ frame count matches sampling; keys consecutive.
• CSR structure and shape validated.