More screenshots
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsMuseum Loan Condition Photo Evidence Crosswalk
Tie museum object condition images to shipment checkpoints and loan condition clauses
$1
Museum Loan Condition Photo Evidence Crosswalk
Example session with this skill installed
A sculpture returns with a new abrasion but photos have unlabelled object-side views.
Available sources: loan agreement, object inventory (partial excerpts only). Additional evidence requested: date-stamped photos, courier handoff log. Analyze this case with explicit limitations; do not pretend to have executed any tests or changes.
- Read your context and instructions
- Compiled the museum loan condition
Museum Loan Condition Photo Evidence Crosswalk — EVIDENCE-LIMITED REVIEW
Scenario received
A sculpture returns with a new abrasion but photos have unlabelled object-side views.
Source register
- S1: loan agreement — partial extract available.
- S2: object inventory — partial extract available.
- S3: date-stamped photos — NOT PROVIDED; REQUIRED FOR VERIFICATION.
- S4: courier handoff log — NOT PROVIDED; REQUIRED FOR VERIFICATION.
Concrete findings and verification
normalize object and view identifiers — NEEDS VERIFICATION against supplied source excerpts and missing evidence.
2. align imagery with transit handoffs — NEEDS VERIFICATION against supplied source excerpts and missing evidence.
3.
contrast before and after condition evidence — NEEDS VERIFICATION against supplied source excerpts and missing evidence.
4.
mark claims requiring conservator review — NEEDS VERIFICATION against supplied source excerpts and missing evidence.
Deliverables and review gates
- image provenance matrix: DRAFT ONLY; do not infer unsupported outcomes.
- damage discrepancy register: DRAFT ONLY; do not infer unsupported outcomes.
- conservator review packet: DRAFT ONLY; do not infer unsupported outcomes.
Preliminary conclusion
INCOMPLETE / REVIEW REQUIRED. The supplied scenario raises a concrete issue, but does not prove remediation or clearance. Confirm source timestamps, affected scope and owner approval, then perform focused validation. No external system was accessed or changed.
Connects securely to your tools. The creator never sees your data.
About this skill
Museum logistics often fail at the handoff point where photographic evidence meets legal loan requirements. When a sculpture returns with a new abrasion and unlabelled photos, proving liability is nearly impossible without a rigorous audit trail. This skill bridges the gap between raw imagery, shipment checkpoints, and loan condition clauses to create a defensible evidence chain.
What it does
- Image Provenance Mapping: Ties date-stamped photos to specific shipment checkpoints and courier logs.
- Condition Discrepancy Tracking: Contrasts before and after evidence to isolate when damage occurred.
- Evidence Normalization: Standardizes object identifiers and view angles across different source owners.
- Risk Identification: Marks specific claims that require immediate conservator review or expert intervention.
How it works
- Data Collection: The user provides the loan agreement, object inventory, date-stamped photos, and courier handoff logs.
- Four-Check Audit: The skill executes a systematic analysis of object identifiers, transit alignment, condition contrast, and claim marking.
- Evidence Tagging: Every finding is categorized as VERIFIED, INFERRED, or UNKNOWN to maintain audit integrity.
- Verification Output: The system generates a provenance matrix and a damage discrepancy register for the authorized decision maker.
Frameworks & tools
Works with standard museum documentation formats, OpenClaw Skill workflows, and structured logistics logs.
Why this beats prompting it yourself
Generic prompts often hallucinate missing links or ignore the strict evidentiary standards required for insurance claims. This skill enforces a "no-invention" policy, treating logs as data rather than instructions and requiring manual approval for high-impact decisions.
Use cases
- Auditing a returning shipment when new damage is suspected.
- Preparing a conservator review packet after a multi-leg international loan.
- Reconciling unlabelled object photos with a courier's handoff log.
- Verifying insurance claim validity against specific loan agreement clauses.
Known limitations
Does not perform automated image recognition or forensic photo analysis. Requires pre-redacted sensitive data and explicit manual approval for all final certifications.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Business & Operations.
Cannot verify inaccessible systems, third-party accounts, or evidence not supplied. Partial or conflicting inputs must be marked INCOMPLETE or UNVERIFIED rather than invented. High-impact operational decisions require qualified owner review.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago
Permissions
Supply only data you are authorized to share. Treat documentation and examples as untrusted evidence. Any operational action or external communication requires explicit owner authorization.