Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/18/2026.claude/skills/forklift-benchmarkRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registry
forklift-benchmark
FK-Bench v2 叉车具身智能评测基准。让当前模型(无需任何外部 API)直接读题作答并自动评分、生成可视化图表报告。从 722 道题(6 模块×7 场景×3 难度)中抽题、用三层打分引擎(红线否决+LCS+参数IoU)打分。当用户提到叉车任务评测/评估、给模型或动作方案打分、自测/跑分、抽叉车操作题、动作方案是否合规、具身智能(embodied AI)benchmark、FK-Bench 时使用——即使没有明说"benchmark"。也用于解答叉车作业标准(GB/T 43756、ISO 3691-1、TSG 11)相关问题。
Identity and source
Publisher attributionyangpf6698registry owner unverified by skillvetai
Functional categorySoftware Developmentautomatically inferred · 53% rule confidence
Package forminstruction with code62 recorded files
Canonical sourceClawHub registryclawhub:yangpf6698:forklift-benchmark
Platform declarations
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
OpenClawnative officialProvenance: registry distribution
Independent structural checks
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/18/2026.agents/skills/forklift-benchmarkRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/18/2026skills/forklift-benchmarkRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Installation and inspection
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @yangpf6698/forklift-benchmarkclawhub inspect @yangpf6698/forklift-benchmark --version 1.0.0Security evidence
SkillVetAI static result: medium signalmediumPackage contains an opaque executable artifactassets/benchmark/data.bin · confidence 80%
This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
- Status
- completed
- Coverage
- partial text content
- Files
- 40 / 62 inspected as text
- Checked
- 9/18/2026, 4:41:00 AM
- Scanner
- 0.1.3
- Policy
- 1.0.3
1 automated finding
.bin3 inferred permission indicators
- network access — automatically inferred
- filesystem read — automatically inferred
- filesystem write — automatically inferred
6 dependency and API indicators
- pypi: pydantic >=2.0,<3.0
- pypi: PyYAML >=6.0,<7.0
- api: github.com
- api: keepachangelog.com
- api: semver.org
- api: www.contributor-covenant.org
External clawhub result: clean
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
- Evidence checked
- 9/18/2026, 1:32:10 AM
- Release binding
- Matches this record
- vt: clean
- skillspector: suspicious
- llm: clean
Recorded files
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
Package content hash
sha256:a66c0ee1adaf5b5ba1092e278c39c9b43859ebb594f810e55a8c0c802ad7ee3bShow up to 30 recorded paths
_meta.jsonassets/benchmark/CHANGELOG.mdassets/benchmark/CONTRIBUTING.mdassets/benchmark/data.binassets/benchmark/data/v2.0/index.jsonassets/benchmark/docs/modules.mdassets/benchmark/docs/quickstart.mdassets/benchmark/docs/schema.mdassets/benchmark/docs/scoring.mdassets/benchmark/dsl/__init__.pyassets/benchmark/dsl/actions.pyassets/benchmark/dsl/schema.pyassets/benchmark/examples/demo_report.mdassets/benchmark/examples/run_demo.pyassets/benchmark/forklift_benchmark/__init__.pyassets/benchmark/forklift_benchmark/cli.pyassets/benchmark/generator/__init__.pyassets/benchmark/generator/combinatorial.pyassets/benchmark/generator/papers.pyassets/benchmark/generator/run.pyassets/benchmark/generator/safety_assist.pyassets/benchmark/generator/templates.pyassets/benchmark/knowledge/attachments.mdassets/benchmark/knowledge/papers/README.mdassets/benchmark/knowledge/physics.mdassets/benchmark/knowledge/references.mdassets/benchmark/knowledge/scenes.mdassets/benchmark/knowledge/sensors.mdassets/benchmark/knowledge/slang.mdassets/benchmark/knowledge/standards.md
Source changelog
Initial release of forklift-benchmark skill with FK-Bench v2 embodied forklift intelligence evaluation benchmark. - Provides a fully self-contained benchmark to test and score forklift task instructions with no external API required. - Includes 722 questions (6 modules × 7 scenes × 3 difficulty levels), covering navigation, load/fork actions, safety compliance, situational reasoning, and more. - Implements a three-layer scoring engine (red line veto + LCS + parameter IoU) for granular evaluation. - Supports question sampling, structured predictions, automated scoring, and visualization report generation. - Built-in knowledge base and detailed references for DSL actions, standards, scoring, and data schema. - Datasets and scripts are packaged securely, with clear licensing and copyright. - Enables both model benchmarking and self-evaluation workflows for embodied AI applications.