multi-agent-deep-research
v1.0.0Coordinate deep, source-verifiable research projects in OpenClaw using AgentSkills-compatible folders, local artifact tracking, and explicit evidence ledgers...
⭐ 0· 84·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the SKILL.md and included reference files: everything is oriented to creating local, file-backed research projects, ledgers, templates, and delegation patterns. There are no unexpected dependencies, binaries, or credentials requested.
Instruction Scope
Runtime instructions are explicit about creating project directories and writing local ledgers in the workspace. They only reference local paths and project files provided in the package. Delegation/subagent use is explicitly conditional on user request and platform support; instructions do not tell the agent to read unrelated system files or transmit data to unknown endpoints.
Install Mechanism
This is an instruction-only skill (no install spec, no code files to execute). Nothing is downloaded or written into system locations by an installer; the workflow writes artifacts into the user's workspace only, per the guidance.
Credentials
No environment variables, credentials, or config paths are required. The declared requirements are minimal and proportionate to a workspace-based research workflow.
Persistence & Privilege
always is false and the skill does not request persistent elevated privileges or modify other skills' configurations. It only instructs writing project files within the active workspace, which is consistent with its purpose.
Assessment
This skill is internally coherent and appears to do what it claims: create and manage local, file-backed research projects. Before installing, consider: (1) it will create and edit files in whatever workspace you run it from — run it in a directory you trust or a disposable workspace if you want to test; (2) the SKILL.md assumes the agent may collect external sources (web/API access) if your OpenClaw setup provides that capability — verify which core skills or connectors (browser, web fetch, APIs) are enabled so you know whether the agent will reach the network; (3) no credentials or installs are required, but review the included templates and references so you are comfortable with the file layout and naming; (4) the package source/homepage is unknown, so if provenance matters to you, validate the owner or inspect the SKILL.md and reference files yourself before use. Overall: safe and proportionate for local, auditable research workflows, but exercise normal caution about workspace permissions and network-capable agent connectors.Like a lobster shell, security has layers — review code before you run it.
latestvk97aww5nq87p4a0ect3f9e069583b25m
License
MIT-0
Free to use, modify, and redistribute. No attribution required.