The /research skill I use for all coding - by Josh Pigford

[](https://everydayisayear.ai/) # [](https://everydayisayear.ai/) SubscribeSign in  Discover more from Every Day is a Year Josh Pigford takes a weekly look at the AI tools, updates, and trends that actually matter — from a founder who builds with this stuff every day. No hype, just what's worth your time. Subscribe By subscribing, you agree Substack's [Terms of Use](https://substack.com/tos), and acknowledge its [Information Collection Notice](https://substack.com/ccpa#personal-data-collected) and [Privacy Policy](https://substack.com/privacy). Already have an account? Sign in # The /research skill I use for all coding ### How I make sure every session has accurate and up-to-date context [](https://substack.com/@shpigford) [Josh Pigford](https://substack.com/@shpigford) Apr 02, 2026 5 3 Share [](https://substackcdn.com/image/fetch/$s_!LF9p!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F52099120-2119-451a-ac9d-4fcc5b2a3df9_1376x768.jpeg) I’m a heavy Claude Code user and while I love Plan mode, I find it’s actually not all that thorough in its planning. While it certainly has an obscene amount of data in its training corpus, it doesn’t have _everything_ and is obviously missing anything recent. So I’ve found that making sure a given task has the latest docs and latest web search results tends to solve problems much more efficiently. For docs, it detects if you’ve got the [Context7](https://context7.com/) MCP installed. There’s a lot of debate on the efficacy of Context7. The argument being that web searching/scraping works just fine. But I find that a substantial number of developer sites are extremely javascript heavy or behind auth (which is certifiably insane). So Context7 fills in the gap much more efficiently. At any rate, here’s the `/research` skill I tack on to just about any new feature or bug I’m working through. This is geared towards Claude, but you should be able to adapt to whatever harness you use relatively easily. Thanks for reading Every Day is a Year! Subscribe for free to receive new posts and support my work. Subscribe ``` --- name: research description: "Deep research before planning. Launches parallel agents to search docs, web, and codebase, then synthesizes findings into actionable context." --- $ARGUMENTS Research this thoroughly before any planning or implementation begins. ## How to research ### Step 1: Clarify before you research (MANDATORY — never skip) Before reading a single file or launching any agent, use AskUserQuestion. Read the input and identify every place where you have 2+ plausible interpretations — scope, intent, constraints, approach, priority. Ask about those specifically. **How to ask:** Present choices tailored to the actual input, not generic categories. The options should come directly from the ambiguities in what was asked. If you see three plausible ways to interpret what the user wants, list those three things and ask which is closest. Don't ask what you can already infer. Do ask anything that would materially change what you research or recommend. Good trigger conditions for asking: - The input describes a symptom but not a root cause — ask what they think the cause is, with options - The input proposes a solution — ask if the solution is required or just a starting hypothesis - The scope is fuzzy — ask whether they want a targeted fix or a broader rethink, with examples of each - Multiple approaches exist with real tradeoffs — ask which tradeoffs matter most to them - The change could affect related systems — ask whether those are in scope - Any constraint (time, backwards-compat, file/dependency, team conventions) is unstated — ask K