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 agentsFood Allergen Label Artwork Formula Revision Check
Compare released label allergen claims with the exact food formula and packaging revision
$1
Food Allergen Label Artwork Formula Revision Check
Example session with this skill installed
A sauce pack prints dairy-free artwork after a new ingredient formula introduces milk powder.
Available sources: approved recipe revision, ingredient allergen table (partial excerpts only). Additional evidence requested: print artwork proof, packaging batch ledger. Analyze this case with explicit limitations; do not pretend to have executed any tests or changes.
- Read your context and instructions
- Compiled the food allergen label
Food Allergen Label Artwork Formula Revision Check — EVIDENCE-LIMITED REVIEW
Scenario received
A sauce pack prints dairy-free artwork after a new ingredient formula introduces milk powder.
Source register
- S1: approved recipe revision — partial extract available.
- S2: ingredient allergen table — partial extract available.
- S3: print artwork proof — NOT PROVIDED; REQUIRED FOR VERIFICATION.
- S4: packaging batch ledger — NOT PROVIDED; REQUIRED FOR VERIFICATION.
Concrete findings and verification
- join artwork to released formula — NEEDS VERIFICATION against supplied source excerpts and missing evidence.
compare declared allergens and may-contain statements — NEEDS VERIFICATION against supplied source excerpts and missing evidence.
3.
trace print lot to manufacturing date — NEEDS VERIFICATION against supplied source excerpts and missing evidence.
4.
route unresolved labels to food-safety hold — NEEDS VERIFICATION against supplied source excerpts and missing evidence.
Deliverables and review gates
- formula-artwork mismatch map: DRAFT ONLY; do not infer unsupported outcomes.
- affected batch register: DRAFT ONLY; do not infer unsupported outcomes.
- label release gate: 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
Manual allergen label verification is prone to human oversight, especially when ingredient formulas change mid-production. This skill enforces a rigorous, evidence-first audit to ensure food packaging claims align perfectly with the current recipe revision and manufacturing batch. It eliminates guesswork by requiring specific identifiers for every record, from the ingredient allergen table to the print artwork proof.
What it does
- Formula-artwork mapping links specific recipe revisions to active packaging proofs to identify discrepancies.
- Allergen declaration auditing compares declared allergens and "may-contain" statements against the ingredient table.
- Batch ledger tracing connects print lot numbers to specific manufacturing dates to scope affected inventory.
- Risk routing identifies unresolved label mismatches and flags them for immediate food-safety holds.
How it works
- Input verification where you provide the approved recipe, allergen table, artwork proof, and batch ledger.
- Evidence analysis where the skill executes four mandatory checks across artwork, formulas, and manufacturing dates.
- Verdict generation providing a status of SUPPORTED, BLOCKED, or UNVERIFIED based on the data provided.
- Output production including a mismatch map and an affected batch register for quality control.
Frameworks & tools
This skill is designed for quality assurance and food safety workflows. It processes structured records such as batch ledgers, ingredient specifications, and artwork version logs.
Why this beats prompting it yourself
Generic prompts often hallucinate missing links or ignore versioning gaps. This skill enforces a hard gate architecture that distinguishes between verified, inferred, and unknown data, preventing dangerous assumptions in food safety.
Use cases
- Verify a sauce pack printing dairy-free artwork after a formula update adds milk powder.
- Audit packaging batches after an ingredient supplier changes their cross-contamination profile.
- Perform a release gate check before a new product launch to ensure label compliance.
Known limitations
Requires specific document revisions and identifiers to function; missing inputs are treated as gaps rather than successes. Does not perform physical inspections or lab testing.
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 23 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.