More screenshots
Works with the AI Agents you already use
🧾 Proof-to-Channel Evidence Packet
Map supported product claims to current channel rules, required artifacts, human-authored fields, and a fail-closed submission-readiness gate.
$5
🧾 Proof-to-Channel Evidence Packet
Example session with this skill installed
One product, a verified marketplace rule snapshot, two product claims, current documentation and screenshot evidence, required demo and install paths, pricing disclosure, link target, and explicitly marked human-authored fields.
- Read your context and instructions
- Compiled the proof-to-channel evidence packet
READY with two reciprocally supported claims, one supplied screenshot, complete demo, install, pricing, link and attribution fields, no do-not-say claims, and a receipt declaring result.json, report.md, and manifest.json.
Connects securely to your tools. The creator never sees your data.
About this skill
Proof-to-Channel Evidence Packet turns owner-supplied product proof, claim links, current channel rules, screenshots, demo and install paths, pricing disclosure, attribution, and human-authored identity fields into a deterministic release packet. The offline Python helper rejects malformed values, credential-like URL query keys, stale or future evidence, nonreciprocal claim links, missing artifacts, and unsafe output paths. It writes a claim matrix, do-not-say claims, human-review requirements, an artifact brief, stable findings, and SHA-256 receipts for three declared files. READY means the supplied packet is reviewable for the named channel. It does not retrieve private profiles, write founder experience, submit a listing, publish, or predict acceptance.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
• No external paid install or sale exists for this exact product.
• Caller-supplied rules and source labels are not independently authenticated.
• READY does not predict acceptance, reach, demand, or revenue.
• The helper evaluates normalized supplied evidence and does not independently retrieve or authenticate source records.
• Malformed inputs and unsafe output paths fail closed without a successful persistence receipt.
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 3 months ago
Permissions
File Scopes
The deterministic standard-library helper makes no network request and refuses unsafe or existing output paths.