Investigate a question against primary sources and capture the findings as one cited Markdown note. Use when the user wants a topic researched, a vendor's docs or API facts gathered, a library's or tool's real behavior confirmed, or reading legwork delegated while the main session keeps working.
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
# Research
Reading is cheap to delegate and expensive to get wrong. This skill keeps it cited and keeps
it out of the main conversation. Credit and license: `LICENSE.md` in this folder.
## Who reads
If the agent can start a background subagent, hand the reading to one and keep working. In
Claude Code that is the `researcher` agent, which runs on Sonnet in the background. Otherwise do the reading yourself, following the same brief.
## The brief
1. **Primary sources only**: official docs, source code, specifications, first-party API
responses, release notes. Not a blog post or forum answer *about* them. Follow every
claim back to the source that owns it.
2. **One Markdown file** in the session's scratch directory, named for the question. Each
claim carries its source: a URL and the date it was read. Version-specific facts name
the version.
3. **Say what could not be verified**, in its own section. An unverified claim is labeled,
never smoothed into the prose.
4. **Report back** the file's path and a summary of five lines or fewer, not the file's
contents.
## After the note exists
…
The line at the top of this page pins the label git:20261015.0b3e11b, 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_znz5wuubqvgr3n4v
GET https://markdownregistry.com/api/v1/resolve?ref=ehnruiz/claude-skills/research
GET https://markdownregistry.com/api/v1/blob/2ddb4c3cd8a53828b42190a3ab041cd7ba412c8a7057dc7cfa146106271dafa9
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.
ehnruiz/claude-skills · skills/confluence-jira-links/SKILL.md · Link a Confluence page and the Jira tickets it is about, both ways, without duplicates - each ticket shown on the page…
ehnruiz/claude-skills · skills/diagnosing-bugs/SKILL.md · A disciplined loop for hard bugs, flaky tests and performance regressions - build a red-capable feedback loop first…
ehnruiz/claude-skills · skills/epic-review/SKILL.md · Review a Jira epic (or the Jira Product Discovery idea it implements) against its own In Scope list - which items are…
ehnruiz/claude-skills · skills/explain-the-number/SKILL.md · Like-for-like before a measured number is reported or credited to a change. Use before saying a change moved a score, a…
ehnruiz/claude-skills · skills/grilling/SKILL.md · Grill the user relentlessly about a plan, decision, or idea until every branch of it is settled. Use when the user…
ehnruiz/claude-skills · skills/handoff/SKILL.md · Write a handoff note so a fresh session can continue this one's work. Use when the user says to hand off, wrap up, or…
ehnruiz/claude-skills · skills/leader-1-1-prep/SKILL.md · Build a prep brief for a recurring 1:1 with a skip-level or senior leader. Pulls the last meeting's notes, the tickets…
ehnruiz/claude-skills · skills/llm-integration/SKILL.md · Checklist for code that calls a language model or exposes a system to one. Use when writing or reviewing code that…
ehnruiz/claude-skills · skills/no-ai-attribution/SKILL.md · Keep AI-assistant credit lines out of anything published on the user's behalf. Use before writing a commit message…
ehnruiz/claude-skills · skills/open-in-my-browser/SKILL.md · Open a link the user shares in their own Chrome through the Claude in Chrome extension, where their sign-ins and VPN…
ehnruiz/claude-skills · skills/pick-up/SKILL.md · Continue work from a handoff note an earlier session wrote. Use when the user says to pick up, continue or carry on…
ehnruiz/claude-skills · skills/plain-writing/SKILL.md · Draft text a person will send or post under their own name, in plain language that does not read as machine-written…
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: how code works, or whether a repeated pattern deserves a rule. Use when: asked how, why, or…
boshu2/agentops · plugin/skills/research/SKILL.md · Answer one cited question: how code works, or whether a repeated pattern deserves a rule. Use when: asked how, why, or…
