validate-ul-fund-data SKILL.md skillA
validate-ul-fund-data from open-source-modelling/insurance_skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add open-source-modelling/insurance_skills/validate-ul-fund-data@git:20260907.7934823Pins git:20260907.7934823 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- open-source-modelling/insurance_skills
- Path
validate-ul-fund-data/validate-ul-fund-data/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260907.7934823, committed Sep 7, 2026
- Size
- 3,406 bytes
- Repository stars
- 5
- License
- MIT
Validate quarterly UL fund Excel extracts before analysis. Use whenever a quarterly extract is uploaded, mentioned, or suspected to be malformed, including requests to check, QA, sanity-check, or verify it. Run before analysis even when validation is not explicitly requested.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Validate UL fund data This runs 22 format checks on quarterly fund extracts and produces an audit-friendly report before analysis. ## Why a separate workbook Write a ***standalone report workbook*** `<source>_validation.xlsx` report containing only one sheet, `Validation Q<n> <year>`. Never modify or copy the source workbook. Include the source filename, SHA-256 fingerprint, and byte count so the report remains tied to the file checked. ## Workflow Find the uploaded workbook in `/mnt/user-data/uploads/` by listing the directory, then run: ```bash python3 scripts/validate.py /mnt/user-data/uploads/<file>.xlsx ``` It writes `/mnt/user-data/outputs/<file>_validation.xlsx` and prints a summary. Exit code is `0` if every check passed, `1` if any failed. Present the report with `present_files`, and tell the analyst to save it beside the dataset. In chat, lead with PASS/FAIL and list each failed rule with its sheet, column, reason, and cell references. ## When checks fail Say plainly that a failed extract should not be analysed yet. List the failed rule, sheet, column, reason, and actual cell references such as `FUND_1!B2`. …
Read the whole file at its exact version.
How to install
mdr add open-source-modelling/insurance_skills/validate-ul-fund-data@sha256:7058e8abace14905The line at the top of this page pins the label git:20260907.7934823, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_3jhcrsjpdhmo25ae)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 7, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3406 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
open-source-modelling/insurance_skills · 5 stars · license MIT · pushed 2026-09-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3jhcrsjpdhmo25ae GET https://markdownregistry.com/api/v1/resolve?ref=open-source-modelling/insurance_skills/validate-ul-fund-data GET https://markdownregistry.com/api/v1/blob/7058e8abace149055fcfbb2dacc51cbfb1b4f97e7c56b9c02441b08ec0abe1d9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.