ljxpython/web-research
apps/runtime-service/runtime_service/agents/research_agent/skills/web-research/SKILL.md
Structured web research workflow with planning, delegated subtopic investigation, and file-based synthesis.
$ install --global
skillsauthnpx skillsauth add ljxpython/aitestlab web-researchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 6, 2026, 8:23 PM9.2s1 file scanned
SKILL.md
- name:
- web-research
- description:
- Structured web research workflow with planning, delegated subtopic investigation, and file-based synthesis.
Web Research
Trigger
Use this skill when the user asks for web research, latest information lookup, option comparison, or a report with citations.
Required Workflow
- Create a research folder and write
research_plan.mdfirst. - Split the topic into 2-5 non-overlapping subtopics.
- Delegate one focused task per subtopic via
task. - Require each delegated task to write findings into
findings_<subtopic>.md. - Read all findings files before writing the final answer.
- Synthesize direct conclusions, include source URLs, and call out evidence gaps.
Guardrails
- Keep each subtopic narrow and non-overlapping.
- Avoid over-researching simple questions.
- Do not finalize without reading all generated findings files.
- Prefer concise and evidence-based output.
Related Skills
ljxpython/deepagent-research-delegation
development
VerifiedTrustedCommunity
Use this skill when external references or broader codebase discovery is required; delegate to a research subagent and synthesize findings.
81SKILL.mdUpdated Apr 6, 2026
ljxpython/deepagent-common-workflow
documentation
VerifiedTrustedCommunity
Use this skill for engineering tasks that require planning with write_todos, controlled file edits, and final verification.
81SKILL.mdUpdated Apr 6, 2026
ljxpython/test-strategy
testing
VerifiedTrustedCommunity
在需求分析之后激活。负责把关键测试点转换成简洁、可执行的测试策略与优先级安排。
81SKILL.mdUpdated Apr 6, 2026
ljxpython/test-data-generator
testing
VerifiedTrustedCommunity
当测试用例设计完成后需要具体测试数据，或用户明确要求生成测试数据、构造数据集时激活。负责根据字段约束、业务规则和测试目标，生成覆盖正常值、边界值、异常值的完整测试数据集，支持多种数据类型和格式。
81SKILL.mdUpdated Apr 6, 2026