Security
Skill
/web-research-refresh
Refresh stale content via web verification, source logging, and citation-backed updates.
Install
$ npx -y skills add frumu-ai/tandem --skill web-research-refresh --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/web-research-refresh
Context preview
The summary Claude sees to decide when to auto-load this skill.
Refresh stale content via web verification, source logging, and citation-backed updates.
SKILL.md
web-research-refresh.SKILL.mdname: web-research-refresh description: "Refresh stale content via web verification, source logging, and citation-backed updates." version: "0.1.0" author: tandem compatibility: tandem tags: - web - research - documentation requires: - web triggers: - fact check - refresh docs - verify claims
Web Research Refresh Skill
Mission
Replace stale claims with verified, current facts and maintain a transparent evidence trail.
Inputs To Use First
- inputs/stale_brief.md
- inputs/verification_questions.md
- inputs/customer_support_tickets.md
Workflow
1. Extract factual claims and mark each as verify/update/remove. 2. Prioritize high-risk claims (policy, pricing, legal, security). 3. Research authoritative sources and log each citation. 4. Rewrite facts with dates and references. 5. Publish clear before/after reporting.
Required Outputs
- outputs/claims_inventory.md
- outputs/research_plan.md
- outputs/evidence_log.md
- outputs/updated_facts_sheet.md
- outputs/web_research_report.html
Quality Bar
- Every factual update has a source URL and access date.
- Low-trust sources are explicitly flagged or excluded.
- Changes are traceable from original claim to new fact.
- Final report is readable by non-technical stakeholders.
Ships withtandem
Tandem is the authority layer between AI agents and company tools: runtime policy for tools, memory, approvals, and audit trails.
Get the whole plugin
Stats
125
Stars
13
Forks
Active
Maintenance
Rust
Language
23d ago
Last commit
9mo ago
Created
2h ago
Added
Other skills on tandem.
Skill

