AI-to-Human Handoff Context Packager

What this skill does

Creates complete, evidence-rich, decision-ready context packages for transferring risky, ambiguous, exceptional, unresolved, or authority-restricted cases from an AI agent to the correct human specialist. Preserves the user's actual objective, verified facts, consulted data, completed checks, executed actions, previous responses, confidence level, policy or exception context, risks, deadlines, escalation reason, required human decision and recommended next action while minimizing repetition and unnecessary sensitive-data exposure.

• Risk
• Agensi

Where it runs, and how to install it

Agent Skills are a format, not a product feature: a folder with a SKILL.md and whatever files it needs. Nothing inside one is model-specific.

Claude

Drop the skill folder into ~/.claude/skills/, or upload it in Settings → Capabilities. Claude loads it when the description matches what you asked for.

Claude Code

Same folder, per-project instead: .claude/skills/ inside the repository, so the skill travels with the work rather than with the machine.

Any agent that reads SKILL.md

A skill is a folder with a SKILL.md and whatever files it needs. Nothing in the format is model-specific, so a runtime that reads the file reads the skill.

More from Shandra

• Audit Evidence Collection and Readiness AgentMaps audit requests to internal controls, identifies required supporting evidence, organizes records from approved sources, detects missing, stale, incomplete, or conflicting artifacts, validates period and scope coverage and prepares review-ready audit packages without modifying authoritative source records. It creates request-to-control mappings, control-to-evidence matrices, PBC trackers, evidence indexes, gap registers, remediation trackers, provenance records and reviewer-ready packages while preserving traceability, confidentiality and evidence integrity.
• Contract Obligation Tracking AgentConverts complex contracts into structured registers with deadlines, owners, service levels and renewal logic.
• Customer Complaint De-Escalation AgentAnalyzes angry, frustrated, disappointed, or emotionally charged customer complaints and produces calm, empathetic, policy-compliant responses while detecting churn, refund, chargeback, legal, regulatory, reputational, privacy, safety, discrimination, fraud and executive-escalation risks. It preserves prior contacts and commitments, separates verified facts from allegations, prevents unsupported admissions and overpromising, reduces repeated customer effort and determines when supervisors or specialist teams must intervene.
• GDPR Contract Review Triage AgentReviews contracts and DPAs for GDPR-related triage issues, extracts obligations, flags missing clauses, creates risk tables and generates legal-review checklists.

Skills that do related work

• AI Governance Policy Builder EU(EU AI Act, ISO 42001)Stand up an AI governance program, classify your AI by risk and map it to the EU AI Act, NIST AI RMF and ISO/IEC 42001. Guidance, not legal advice.
• Análise Inteligente de Edital em 48hAutomated 8-step tender analysis and risk assessment workflow for government contractors.
• Company Due DiligencePublic-source due diligence and risk assessment for companies, vendors and business counterparties. Every finding is labelled verified, reported or unverified.
• Contract & Terms Risk Spotting GateAn adversarial reviewer that reads a contract, agreement, or terms-of-service and flags one-sided, risky, vague, or missing clauses, then returns a LOW RISK / R
• Contract Obligation Evidence MapperExtracts and maps contract obligations, deadlines and risks to specific source clauses with evidence-based rigor.
• Customer Complaint De-Escalation AgentAnalyzes angry, frustrated, disappointed, or emotionally charged customer complaints and produces calm, empathetic, policy-compliant responses while detecting c