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
# Repository instructions
Read [AGENTS.md](AGENTS.md) for shared development instructions.
The line at the top of this page pins the label git:20261024.215cdfd, 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.
B 13 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
fail: Size between 200 bytes and 200 KB (92 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
Starting a new one? Use a template for CLAUDE.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
GitHub
lusona/ai-skills · 3 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pl27bvgoetopaxbx
GET https://markdownregistry.com/api/v1/resolve?ref=lusona/ai-skills/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/2dc73f042e6c9cc90b6c85a573ba2652a7bb3b743b29fd10f1aa05bcf729e828
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.
lusona/ai-skills · plugins/lusona/skills/architect/SKILL.md · Resolve consequential technical decisions about boundaries, contracts, and ownership for a product or change. Interview…
lusona/ai-skills · plugins/lusona/skills/experiment/SKILL.md · Test an intervention or compare alternatives through a bounded empirical trial with declared evaluation criteria and…
lusona/ai-skills · plugins/lusona/skills/explore/SKILL.md · Explore ideas, decisions, scenarios, and long-term possibilities through discussion and tradeoffs. Use before choosing…
lusona/ai-skills · plugins/lusona/skills/frame-product/SKILL.md · Develop product vision, audience, problem, outcomes, and boundaries. Use for initial product definition or a change in…
lusona/ai-skills · plugins/lusona/skills/implement/SKILL.md · Implement an authorized bounded change with adaptive planning, explicit TDD, and verification. Also use for explicit…
lusona/ai-skills · plugins/lusona/skills/investigate/SKILL.md · Reproduce a bug or resolve a bounded technical uncertainty using evidence and small experiments. Use whenever a cause…
lusona/ai-skills · plugins/lusona/skills/map-capabilities/SKILL.md · Map capability coverage, dependencies, and delivery order toward a product vision. Use when these need clarification or…
lusona/ai-skills · plugins/lusona/skills/measure/SKILL.md · Establish magnitude, quality, cost, or change with comparable observations that inform a bounded decision. Use for…
