Real Skill packageSource verifiedClawHub registry

sn-deep-research

用于用户请求深度研究、系统性研究、竞品分析、方案对比、趋势分析或事实核查时。**遇到以下任一情况就主动使用本 skill，不要自行搜几条就回答**：①用户出现触发词：深度研究 / 深度调研 / 深入研究 / 全面研究 / 系统研究 / 调研 / 调查 / 尽调 / 行业研究 / 市场研究 / 竞品分析 / 政策研究 / 技术研究 / 趋势研究 / 事实核查 / 写一份研究报告 / 调研报告 / 深度报告 / research / deep research；②请求需要跨多来源取证、多维度对比、交叉验证才能给出可靠结论；③用户要求产出报告、白皮书、行业分析或尽调文档；④话题涉及最新政策/市场/产品/价格/法规，需要系统核查。明确要求核验来源的单点事实可走 quick；无核验要求的简单常识问答不使用。模糊或宽泛的"研究/了解一下 X"也优先触发。仅不用于：一句话摘要、已给定单一来源的整理、纯文字润色改写。

Identity and source

Publisher attributionSenseNova-Skillsregistry owner unverified by skillvetai
Functional categorySearch, Research & Knowledgeautomatically inferred · 64% rule confidence
Package forminstruction with code30 recorded files
Canonical sourceClawHub registryclawhub:sensenova-skills:sn-deep-research
Open canonical source ↗

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.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/19/2026.claude/skills/sn-deep-research

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/19/2026.agents/skills/sn-deep-research

Runtime, 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 · 8/19/2026skills/sn-deep-research

Runtime, 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 @sensenova-skills/sn-deep-research
clawhub inspect @sensenova-skills/sn-deep-research --version 2026.8.19

Security 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
partial text content
Files
25 / 30 inspected as text
Checked
8/19/2026, 7:10:32 AM
Scanner
0.1.3
Policy
1.0.3
4 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
4 dependency and API indicators
  • api: clawhub.ai
  • api: fonts.googleapis.com
  • api: www.ft.com
  • api: www.semi.org.cn
External clawhub result: suspicious

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
8/19/2026, 4:17:55 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:752ae5f73948666b41f09408089ab3830e6a1472084e8a9cab919e081313c531
Show up to 30 recorded paths
  • agents/perspective.md
  • agents/plan.md
  • agents/report-planner.md
  • agents/report-stitcher.md
  • agents/report-writer.md
  • agents/research.md
  • agents/review.md
  • agents/scout.md
  • agents/supplement-planner.md
  • schemas/evidence.schema.md
  • schemas/outline.schema.md
  • schemas/perspective_feedback.schema.md
  • schemas/plan.schema.md
  • schemas/supplement_plan.schema.md
  • scripts/source_snapshot.py
  • scripts/validate_evidence.py
  • scripts/validate_outline.py
  • scripts/validate_plan.py
  • skill-card.md
  • SKILL.md
  • workbench-runtime/bin/sensenova-ppt-workbench.mjs
  • workbench-runtime/bin/sensenova-research-workbench.mjs
  • workbench-runtime/dist-server/index.mjs
  • workbench-runtime/dist/assets/index-BrQYg30H.js
  • workbench-runtime/dist/assets/index-Bv_HE0iq.css
  • workbench-runtime/dist/assets/MarkdownArtifactViewer-C7xIspsK.js
  • workbench-runtime/dist/favicon.svg
  • workbench-runtime/dist/index.html
  • workbench-runtime/dist/sensetime-mark.png
  • workbench-runtime/package.json

Source changelog

sn-deep-research 2026.8.19 - 全面重写 SKILL.md，进一步细化深度研究的多阶段编排流程与调度机制。 - 明确区分 quick/normal/heavy 三档研究流程，完善档位选择与确认流程。 - 详细规定了多 Agent 协作细则、报告产物目录、各专业角色负责任务与文件接口。 - 强化环境与能力探测机制，任务前强制校验关键功能配置，保障研究完整性。 - 标准化语言锚定与产物语言一致性处理，保证多语种严谨输出。 - 统一与 Research Workbench 的 WebUI 进度联动，用户全流程可视。