skilld
All skills
nvidia avatar

/i4h-workflow-dataset-annotate

@79f1873
by NVIDIA Corporationnvidia/skills3.5k stars
424

Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model. Use for visual success labels; do not use for replay, policy evaluation, or recordings without frames.

Ask your Agent

Use this Skill: https://skilld.dev/gh/nvidia/skills/i4h-workflow-dataset-annotate

This session only. Nothing lands on disk.

BENCHMARK.md

≈1.7k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Skill Benchmark: i4h-workflow-dataset-annotate

✅ Overall verdict: PASS — Recommended for publication

Publication Recommendation

Recommended for publication based on the completed evaluation evidence in this report.

Evaluation Metadata

  • Skill: i4h-workflow-dataset-annotate
  • Evaluation date: 2026-09-21
  • Evaluator version: 1.5.6
  • Agents: Claude Code (aws/anthropic/bedrock-claude-opus-4-8), Codex (openai/openai/gpt-5.5)
  • Tasks: 2 evaluation tasks (2 positive)
  • Dataset digest: sha256:b1d50c74acaec1cdd719c0e683f299d8e8a0538cbe903efc0c052cbb9318fb9e (skill-evaluator-dataset-snapshot/1)
  • Attempts per task: 3
  • Environment: k8s-sandbox
  • Tier 2 evidence: required for publication
  • Tier 3 evidence: required for publication

Each task attempt ran in its own isolated sandbox pod.

What This Report Answers

The three-tier evaluation checks whether the skill:

  • is safe to use;
  • produces correct answers;
  • is discovered and activated when needed;
  • helps the agent complete the user's goal and expected workflow; and
  • avoids wasted skill and tool usage.

Results at a Glance

Measure Claude Code (Baseline → Skill Uplift) Codex (Baseline → Skill Uplift)
Overall 87.7% — baseline ran, but no comparable score was available; uplift unavailable 54.3% — baseline ran, but no comparable score was available; uplift unavailable
Security 100.0% → 100.0% (±0.0 points) 66.7% → 0.0% (-66.7 points)
Correctness 10.0% → 100.0% (+90.0 points) 16.7% → 80.0% (+63.3 points)
Discoverability 92.5% — baseline ran, but no comparable score was available; uplift unavailable 90.0% — baseline ran, but no comparable score was available; uplift unavailable
Effectiveness 6.3% → 52.5% (+46.2 points) 6.3% → 26.3% (+20.0 points)
Efficiency 93.3% — baseline ran, but no comparable score was available; uplift unavailable 75.3% — baseline ran, but no comparable score was available; uplift unavailable

How to read this table: baseline is the same task attempted without the target skill. Scores are rounded to one decimal; threshold-adjacent values use additional precision so their displayed band matches the verdict. Uplift is derived from those displayed scores and shown in percentage points.

Example: 47.0% → 92.0% (+45.0 points) means the skill-assisted run scored 92.0%, 45.0 percentage points above its 47.0% no-skill baseline.

Token Usage

Actual Tier 3 execution usage is reported for every observed agent/case pair and both conditions.

Agent Dataset case With skill Without skill Delta Change Coverage
claude-code All cases 475,052 1,312,248 N/A N/A skill 2/2; base 6/6
claude-code i4h-workflow-dataset-annotate-readme-quick-all-recorded 273,865 567,662 N/A N/A skill 1/1; base 3/3
claude-code i4h-workflow-dataset-annotate-table-recording 201,187 744,586 N/A N/A skill 1/1; base 3/3
codex All cases 887,980 804,389 N/A N/A skill 4/4; base 6/6
codex i4h-workflow-dataset-annotate-readme-quick-all-recorded 613,988 379,076 +234,912 +61.97% skill 3/3; base 3/3
codex i4h-workflow-dataset-annotate-table-recording 273,992 425,313 N/A N/A skill 1/1; base 3/3
ALL AGENTS Dataset aggregate 1,363,032 2,116,637 N/A N/A skill 6/6; base 12/12

Prompt tokens include cached reads, so total tokens are prompt + completion (cached is not added twice). The Efficiency score uses (prompt - cached) + completion. N/A means the relevant trajectory counters were not available; coverage is never estimated.

Tier Status

Tier Purpose Status Evidence
Tier 1 Static validation PASSED WITH OBSERVATIONS 11 validator(s); 2 finding(s)
Tier 2 Semantic deduplication PASSED 2 validator(s); 0 finding(s)
Tier 3 Live agent evaluation PASS 2 agent(s); 2 task(s)

Findings and Observations

<details> <summary>Show detailed findings and successful checks</summary>
  • LOW QUALITY/quality_reliability: Inputs are used but no dedicated Inputs section is documented (team-skills/holoscan/i4h-workflows/i4h-workflow-dataset-annotate/SKILL.md)
  • LOW SECURITY/Unknown (SQP-2): The skill automatically clones a remote Git repository into the user's home directory (~/$I4H_REPO_DIR_NAME) without exp (SKILL.md:32)
</details>

Scoring Methodology

<details> <summary>Show dimension definitions, source signals, and thresholds</summary>
Dimension Question Scored signals
Security Is it safe to use? security (100%)
Correctness Is the answer correct? accuracy (100%)
Discoverability Was the right skill loaded when needed? skill_execution (100%)
Effectiveness Did the skill help complete the task? goal_accuracy (50%) + behavior_check (50%)
Efficiency Did it avoid wasted tool calls and token usage? skill_efficiency (50%) + token_efficiency (50%)
  • Dimension bands: PASS at 50% or above; NEUTRAL from 40% to below 50%; FAIL below 40%.
  • Overall Tier 3 lift: PASS at +5 points or more; FAIL at -10 points or less; values between those bands are NEUTRAL.
  • Overall verdict: PASS only when every configured dimension passes for at least one supported agent. Lift is reported as diagnostic evidence and does not override this gate.
  • The 50% attempt pass threshold is a separate per-task gate; it is not the dimension pass threshold.
  • Effectiveness is the equal-weight mean of goal completion (goal_accuracy) and expected workflow adherence (behavior_check).
  • Efficiency is 50% tool-call productivity (the backward-compatible skill_efficiency wire id) and 50% token_efficiency. Positive-case skill routing is scored under Discoverability, not Efficiency; a negative case without a routing target is N/A. N/A sources are omitted, remaining weights are renormalized, and the dimension is marked partial.

Signals present in this run:

  • security (Security): unsafe operations, secret leakage, and unauthorized access.
  • skill_execution (Skill Execution): whether the expected skill was selected, decoys were avoided, and the workflow executed.
  • skill_efficiency (Tool Productivity): tool-call productivity (legacy wire id; routing is scored under Discoverability).
  • accuracy (Accuracy): final-answer correctness against the reference answer.
  • goal_accuracy (Goal Accuracy): whether the user's goal was achieved.
  • behavior_check (Behavior Check): whether the expected workflow behavior was followed.
  • token_efficiency (Token Efficiency): actual uncached prompt plus completion usage (50% of Efficiency).
</details>

Freshness

Regenerate this benchmark when the skill, evaluation dataset, target agent/model, evaluator version, environment, or scoring policy changes.

Source: SKILL.md on GitHub

Third-party checks

2 warnings1d3 checks · Risk SAFE
  • Gen Agent Trust Hub1d

    The skill is safe to use for its intended purpose of robot workflow annotation. It follows best practices for credential management and utilizes official vendor-associated repositories. It possesses a standard indirect prompt injection attack surface typical of tools that process external data through Vision-Language Models.

  • Socket1d

    1 alert: gptAnomaly

  • Snyk1d

    Risk: MEDIUM · 1 issue

Provenance

Signed by skilld at 79f1873. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated yesterday

Capability

Other metadata
metadata
{
  "author": "Isaac for Healthcare Team <isaac-for-healthcare-support@nvidia.com>",
  "version": "0.8.0",
  "verification-request": "2026-09-15",
  "tags": [
    "isaac-for-healthcare",
    "i4h",
    "dataset",
    "annotation",
    "vlm"
  ]
}

README badge

README badge for nvidia/skills/i4h-workflow-dataset-annotate