.claude/skills/evidence-based-labelingRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
用MCP证据构建并执行可复核标签体系
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/evidence-based-labelingRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/evidence-based-labelingRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/evidence-based-labelingRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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 @yuanzhian-patsnap/evidence-based-labelingclawhub inspect @yuanzhian-patsnap/evidence-based-labeling --version 1.0.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
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.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:63ef61ad1b280ee02534cce7a3267136d8fcf72353fc541cffe7669ebbfe5ebfagents/openai.yamlassets/decision-rules-template.yamlassets/label-confirmation-card-template.mdassets/task-config-template.yamlassets/taxonomy-template.csvREADME.mdreferences/default-decision-rules.mdreferences/domain-milk-protein-examples.csvreferences/domain-milk-protein-rules.mdreferences/domain-milk-protein-taxonomy.csvreferences/domain-milk-protein.yamlreferences/input-output-contract.mdreferences/quality-and-review.mdreferences/taxonomy-design.mdreferences/workflow-modes.mdreferences/zhihuiya-mcp-orchestration.mdscripts/create_labeling_workbook.mjsscripts/inspect_labeling_input.mjsscripts/validate_labeling_output.mjsscripts/validate_task_config.pyscripts/validate_taxonomy.pyskill-card.mdSKILL.md- Initial release of the evidence-based-labeling skill focused on building, optimizing, and applying a structured labeling system for patents, scientific literature, technical documents, and more. - Introduces end-to-end, evidence-driven labeling workflows supporting open, semi-open, and closed taxonomy modes with clear rules and user-driven checkpoints. - Integrates PatSnap MCP for concept discovery, evidence gathering, and sample enhancement, with clear separation between model judgment, external evidence, and business decisions. - Provides tooling for validation of labeling inputs, taxonomy structure, task configuration, and output quality, with auxiliary scripts included. - Emphasizes clear output statuses, role-based review queues, and quality tracking, with strong safeguards for data integrity, configuration, and MCP usage.