.claude/skills/web-researchRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Use when the user wants web research: gathering cited, multi-angle evidence on a specific question. Triggers on: "research X for me", "do web research on", "...
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/web-researchRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/web-researchRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/web-researchRuntime, 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 @anderskev/web-researchclawhub inspect @anderskev/web-research --version 3.0.3This 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.
sha256:55eba45b76783170eebd2bfea1c535dd7ff2df4e367b8caf6f35d4622e22e440references/citation-schema.mdreferences/companion-contract.mdreferences/failure-modes.mdreferences/report-template.mdreferences/subagent-brief.mdskill-card.mdSKILL.md**Major workflow, input, and doc restructuring to support multi-angle web research with formal deliverables.** - New workflow: strict plan→review→subagent dispatch→cited synthesis with gating and verification at each step. - Outputs are always on disk (plan, individual findings, report)—never inline prose. - Inputs strictly limited: accept only distilled research questions; explicit control of output dir, refresh, and auto_proceed. - Strong separation from codebase, file, or judge-type searches; refuses paywalled scraping. - New “references/” docs specify contracts, common failure modes, and templates. - Previous README and misc. doc/scripts removed for clarity and to enforce new interface.