agentleFS
kellykampenkellykampen/agent-skills/skills/workflow/interview/SKILL.md

interview

Skill2 starsChanged 11 days agoMITView on GitHub

Interview the user in depth (via the AskUserQuestion tool) to turn a rough idea, plan file, or feature request into a concrete spec — then capture the result one of three ways. Use when the user runs /interview, or asks you to "interview me about this plan/feature", "grill me on the details", "flesh this out into a spec", or "turn this into Linear issues". Not for casual clarifying questions — this is a deep, iterative interview.

94 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use fetch-library-docs, contributor and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Rehan-Ul-HaqSkill

    fetch-library-docs

    Fetches official documentation for external libraries and frameworks (React, Next.js, Prisma, FastAPI, Express, Tailwind, MongoDB, etc.) with 60-90% token savings via content-type filtering. Use this skill when implementing features using library APIs, debugging library-specific errors, troubleshooting configuration issues, installing or setting up frameworks, integrating third-party packages, upgrading between library versions, or looking up correct API patterns and best practices. Triggers automatically during coding work - fetch docs before writing library code to get correct patterns, not after guessing wrong.

    Also in 4 projects that use this

  • NimbleBrainIncSkill

    contributor

    Get started contributing to NimbleBrain open source — find an integration to build, set up your environment, propose an idea, or check on your work. Use when onboarding as a contributor. Triggers include "I'm a new contributor", "what should I build", "show me open issues", "file an issue".

    Also in 3 projects that use this

  • mjunaidcaSkill

    browsing-with-playwright

    Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction. NOT when only fetching static content (use curl/wget instead).

    Also in 4 projects that use this

  • qa-amanSkill

    teach-me

    Teach a topic, video, article, codebase change, spec, or transcript until the user demonstrably understands it, using staged instruction, a running checklist doc, and quizzes. Use whenever the user says "teach me", "explain this in detail", "help me understand X", "/teach-me", "walk me through this", "I want to learn X", "understand this deeply", or pastes a YouTube URL, article, paper, PR, or spec and asks to understand it rather than summarize it. Also use when the user wants study notes or raw material from a source they are learning. Do NOT use for a quick factual lookup, a summary request, or when the user just wants the answer.

    Also in 8 projects that use this

  • trebaudSkill

    find-unknowns

    Workflow for surfacing a task's unknowns before, during, and after implementation — blind spot pass, brainstorm/prototype, interview, references, implementation plan, deviation notes, quiz. Use when starting work in an unfamiliar domain or codebase, when a task feels underspecified, when the user says "find my unknowns", "blindspot pass", "what am I missing", "help me scope this", or when a long task came back wrong.

    Also in 3 projects that use this

  • donatassimkusSkill

    offer

    Offer design, pricing strategy, and business model architecture. Invoke when asked about making an offer better, pricing a product or service, naming an offer, raising prices, generating fast cash, increasing lifetime value, finding the right customer, qualifying buyers, or designing a business model where customers pay for their own acquisition. Use when someone says their offer isn't converting, they need to charge more, they want to add bonuses or guarantees, or they need a money model for their business.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 80 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask about anything that matters: technical implementation, UI/UX, data model, edge cases, failure modes, scope, concerns, tradeoffs, …

    line 18
  2. Distinctive:

    Make the questions non-obvious: Don't ask what you could infer from the code or the request.

    line 19
  3. Very specific:

    When interviewing about a feature or refactor (a description, a comment, a ticket), write the finished spec to ./plans/<spec-name>.md …

    line 29
  4. Very specific:

    When the user wants issues created, after the interview use the linear-* skills to create:

    line 32

“Common” is measured: kept by at least 6 in 10 of the 80 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Interview

Interview the user thoroughly, then persist the result. The goal is to close the gap between what they have in their head and what's actually written down — surfacing decisions, tradeoffs, and edge cases they haven't thought about yet.

How to interview

  • Use the AskUserQuestion tool for every question — never a wall of prose questions. Batch up to 4 at a time, with smart multiple-choice options plus room for free-text.
  • Ask about anything that matters: technical implementation, UI/UX, data model, edge cases, failure modes, scope, concerns, tradeoffs, non-goals.
  • Make the questions non-obvious. Don't ask what you could infer from the code or the request. Ask the things that would actually change the design.
  • If you're in a git repo, read the relevant codebase first and ask questions grounded in it (existing patterns, conventions, where this fits).
  • Keep going — interview continually, round after round, until the picture is genuinely complete. Don't stop early.

Modes — pick based on what the user asked for

1. Plan file (default)

/interview <plan-file> — read the given plan/spec file, interview to fill its gaps, then write the finished spec back to that same file.

2. Feature → plans/

When interviewing about a feature or refactor (a description, a comment, a ticket), write the finished spec to ./plans/<spec-name>.md (create the plans/ dir if needed). Ground the questions in the current codebase.

3. Feature → Linear

When the user wants issues created, after the interview use the linear-* skills to create:

  • A Linear project capturing the what / why / how / key features.
  • Issues under the repo's team (usually named similarly to the repo), each ≤ 3 points of effort — break anything larger down.
  • Links between issues for blockers / dependencies.
  • Project-level dependency links — before finishing, check the team's other projects and link the ones this new project depends on. Every new project should get ≥1 project dependency unless it's genuinely foundational (rare). These are project↔project relations (not issue relations): the Linear MCP and linear-cli rel don't create them — use projectRelationCreate via linear-cli api mutate, type: "dependency", with the prerequisite anchored end and the dependent anchored start ({ projectId: <prereq>, anchorType: "end", relatedProjectId: <new project>, relatedAnchorType: "start" }). The reverse anchor order won't render in the Dependencies column.

Finish

State clearly where you wrote the spec (file path or Linear project/issue links) and give a short summary of the key decisions the interview locked in.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.