Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/22/2026.claude/skills/japanese-conversation-graderRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registry
日语会话测试批改
面向 A1/A2/B1（对应 JLPT‑N5~N3）师生对话场景的日语口语批改 Skill。基于 faster‑whisper 完成音频 ASR 转写，采用 ** 内容完整性 50%、准确性 20%、流利度 30%** 三维加权预评分，秉持鼓励优先原则，降低语法偏差对总分的拖累。内置专有名词白名单，防止人名、地名被 AI 误判扣分；设置 ASR 置信度分级，低置信场景下 AI 分数仅作后台参考，交由教师人工打分。生成老师详细版、学生简洁版两套反馈，支持 CSV 批量导出。本技能平台无关，对接 LMS 需自行开发适配器；AI 仅做预批改，全部错误必须经过教师复核确认，不会自动判错扣分。
Identity and source
Publisher attributionbianmaxingkongregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 55% rule confidence
Package forminstruction bundle2 recorded files
Canonical sourceClawHub registryclawhub:bianmaxingkong:japanese-conversation-scorer
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 · 8/22/2026.agents/skills/japanese-conversation-graderRuntime, 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 · 8/22/2026skills/japanese-conversation-graderRuntime, 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 @bianmaxingkong/japanese-conversation-scorerclawhub inspect @bianmaxingkong/japanese-conversation-scorer --version 1.1.7Security evidence
SkillVetAI static result: no findings detected
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
- full text content
- Files
- 2 / 2 inspected as text
- Checked
- 8/22/2026, 1:51:36 AM
- Scanner
- 0.1.3
- Policy
- 1.0.3
2 inferred permission indicators
- network access — automatically inferred
- filesystem write — automatically inferred
1 dependency and API indicators
- api: clawhub.ai
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
- 8/21/2026, 2:32:49 PM
- 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
sha256:67c521a4c219648a60b2ad4009d36fa31559a01e7476a736cdf9eaa09362feceShow up to 2 recorded paths
skill-card.mdSKILL.md
Source changelog
**Major update: Refactored and modularized skill with stricter platform independence and improved workflow.** - Migrated from canvas-specific grading to a generic, platform-independent Japanese conversation grading system. - Switched ASR engine to faster-whisper with strict model and hardware usage requirements. - Standardized workflow: audio processing, ASR, confidence grading, automated CAF scoring, and mandatory manual review for "low confidence" cases. - Modularized platform adapters; Canvas, Moodle, Feishu, and CSV support now via separate adapter files. - Refined scoring and error correction rules; scoring is content-focused and highly transparent. - Removed 3 platform-specific/documentation files (_meta.json, references/workflow.md, skill-card.md).