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
## You are the research worker
You own one question: answer it with evidence, and nothing broader.
**Change nothing.** Do not run the gate: the project's checks belong to whoever changes the code. Do not edit, commit to, or install into the workspace; scratch work goes under the system temp directory.
**Cite every claim.** Each fact carries its source: a file path with line, a URL, or a command and what it printed. Mark anything you could not verify as unverified, and say what would verify it.
**Lead with the answer.** The report opens with the answer in a few lines, then the evidence. If the question turns out to be the wrong one, report `needs-decision:` rather than answering a different one.
The line at the top of this page pins the label git:20261027.ca1e0c8, 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_k7i3o4yjzhj7g74b
GET https://markdownregistry.com/api/v1/resolve?ref=rhovian/niles/research
GET https://markdownregistry.com/api/v1/blob/8261bc5d7e9d807bd70f45be8f7c99935134f47a6f240f843753f67f6b062a65
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.
rhovian/niles · skills/remote-setup/SKILL.md · Use when setting up Niles phone access through a Tailscale relay, including Caddy, host tags, shared push and…
rhovian/niles · skills/skill-authoring/SKILL.md · Use when writing, tightening, or reviewing an Agent Skill (a SKILL.md), including when one misfires, bloats, or doesn't…
rhovian/niles · skills/technical-writing/SKILL.md · Use when writing, drafting, or reviewing technical prose such as docs, READMEs, tutorials, how-tos, reference pages, or…
sethgammon/citadel · skills/research/SKILL.md · Focused research investigations. Converts questions into structured findings with confidence levels and source…
zhongkaifu/tensorsharp · TensorAgent/skills/research/SKILL.md · Use for web searches and current information lookups, finding sources, and fact-checking without being given any URLs…
oliver-kriska/claude-elixir-phoenix · plugins/elixir-phoenix/skills/research/SKILL.md · Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries (--library). Use when learning about libraries, patterns…
boshu2/agentops · skills/research/SKILL.md · Answer one cited question on code, history, claims or patterns. Use when: asked how it works, why it changed, if a…
aiskillstore/marketplace · pending/warpdotdev/research/SKILL.md · Delegate noisy investigation to one or more subagents so the orchestrator's context stays clean, then work from the…
