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
## Skills
- Skills in `ai/skillshare/skills` are custom or vendor-installed. A custom skill has `metadata.origin: custom` in its `SKILL.md` frontmatter. Vendor skills do not have this tag.
- When you create a custom skill, add this tag to its frontmatter:
```yaml
metadata:
origin: custom
```
- Do not add the tag to a vendor skill, and do not edit a vendor skill locally. Its upstream updates replace local changes.
- To list the custom skills, run `grep -lx ' origin: custom' ai/skillshare/skills/*/SKILL.md`.
The line at the top of this page pins the label git:20261107.665a973, 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.
GET https://markdownregistry.com/api/v1/artifacts/art_kgwvyhg5oocyy2av
GET https://markdownregistry.com/api/v1/resolve?ref=fredwu/dotfiles/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/2fb8466de784b3bca9ec407bfabc2fc393d7c6a1250a5ceee9f67f9a8cbd23ce
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.
fredwu/dotfiles · ai/skillshare/skills/claude-review-loop/SKILL.md · Review and remediate code through bounded Claude rounds, preferring T3's orchestrator with ACP fallback. Use only when…
fredwu/dotfiles · ai/skillshare/skills/claude-review/SKILL.md · Run one read-only Claude review through T3's orchestrator when available, with ACP fallback. Use only when explicitly…
fredwu/dotfiles · ai/skillshare/skills/code-review-loop/SKILL.md · Review, remediate, and verify code through bounded rounds. Use for review-and-fix requests; use code-review for one…
fredwu/dotfiles · ai/skillshare/skills/code-review/SKILL.md · Review a code target once without edits for concrete, in-scope defects. Use code-review-loop for review and remediation.
fredwu/dotfiles · ai/skillshare/skills/codex-review-loop/SKILL.md · Review and remediate code through bounded Codex rounds, preferring T3's orchestrator with ACP fallback. Use only when…
fredwu/dotfiles · ai/skillshare/skills/codex-review/SKILL.md · Run one read-only Codex review through T3's orchestrator when available, with ACP fallback. Use only when explicitly…
fredwu/dotfiles · ai/skillshare/skills/compare-plans/SKILL.md · Compare the current completed analysis plan with one or more supplied or identifiable peer plans and return prioritized…
fredwu/dotfiles · ai/skillshare/skills/compare-worktree/SKILL.md · Compare the current worktree with one explicit peer and recommend material improvements read-only. Use only on explicit…
fredwu/dotfiles · ai/skillshare/skills/connect-recommend/SKILL.md · Use this skill when the user asks about Stripe Connect configuration, charge patterns, Dashboard access, or how to get…