Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/21/2026.claude/skills/deep-researchRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registry
Deep Research
Seven-stage deep research pipeline for substantive research questions. Activates when user asks for deep research, 深度研究, research report, evidence-backed inv...
Identity and source
Publisher attribution9438190registry owner unverified by skillvetai
Functional categorySearch, Research & Knowledgeautomatically inferred · 64% rule confidence
Package forminstruction bundle4 recorded files
Canonical sourceClawHub registryclawhub:9438190:deep-research
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 · 8/21/2026.agents/skills/deep-researchRuntime, 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 · 8/21/2026skills/deep-researchRuntime, 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 @9438190/deep-researchclawhub inspect @9438190/deep-research --version 1.0.0Security 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
- 4 / 4 inspected as text
- Checked
- 8/21/2026, 1:59:10 AM
- Scanner
- 0.1.3
- Policy
- 1.0.3
2 inferred permission indicators
- network access — automatically inferred
- filesystem write — automatically inferred
2 dependency and API indicators
- api: cdn.jsdelivr.net
- 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
- 7/13/2026, 3:14:02 AM
- Release binding
- Matches this record
- vt: clean
- skillspector: clean
- 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:ad18fd3168a63a2a0c9eefdc9865e6543e56ca6842a61ebaf08e99f6f6658e7fShow up to 4 recorded paths
references/html-guide.mdreferences/writing-guide.mdskill-card.mdSKILL.md
Source changelog
deep-research 1.0.0 changelog - Introduces a comprehensive 7-stage deep research pipeline for answering substantive research questions, migrating core methodology from DuMate's qianfan-deepresearch skill. - Supports both Chinese and English, automatically matching user language for all reports and interactions. - Uses a structured workflow: clarifies user needs, confirms report outline, breaks down tasks, sequentially executes research, checks for completeness, writes an evidence-backed markdown report, and offers HTML rendering. - Active user involvement at key phases with guided choices and explicit confirmation before progressing. - Ensures coverage of standard domain categories beyond explicit user input and prioritizes source diversity, data accuracy, and critical analysis. - All research outputs are concise, structured, source-cited, and immediately presented in conversation for e…