agentleFS
manuelschurrmanuelschurr/professional-twin/skills/interview/SKILL.md

interview

Skill0 starsChanged 7 months agoMITView on GitHub

Use when building or updating a file in a professional twin repository. Invoke once per topic file. Interviews the user, reframes and challenges answers, then writes a structured document. This is an interview, not a transcription.

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

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. 0 are common, 15 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 80 edited versions we read keep these.

  • 15

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start by understanding the current repo context, then ask questions one at a time to explore the topic.

    line 12
  2. Distinctive:

    Do NOT write or update the file until you have interviewed the user and they have approved the draft.

    line 14
  3. Distinctive:

    Every topic goes through the interview.

    line 18
  4. Distinctive:

    Identify target file: If the user named one, use it.

    line 24
  5. Distinctive:

    If the user invokes the skill without naming a file, do not pick one yourself.

    line 36
  6. Distinctive:

    Ask which file the user wants to work on.

    line 40
  7. Very specific:

    If the repo doesn't look like a twin repo (no core-profile/ folder, no CLAUDE.md referencing professional-twin), bail out:

    line 42
  8. Distinctive:

    One question per message: If a topic needs more exploration, break it into multiple questions across multiple messages.

    line 48
  9. Distinctive:

    Reflect before advancing: After each answer, play back what you understood in one sentence.

    line 49
  10. Distinctive:

    Be ready to go back: If a later answer casts doubt on an earlier one, return and clarify.

    line 50
  11. Distinctive:

    When the user gives a generic answer, reframe it as a specific testable claim and ask if it's accurate:

    line 60
  12. Distinctive:

    When the user describes a frustration, extract the positive inverse:

    line 64
  13. Distinctive:

    When a position sounds settled but hasn't been stress-tested:

    line 68
  14. Distinctive:

    Ask after each section whether it looks right so far.

    line 75
  15. Distinctive:

    Write in the user's voice and framing — first person if they speak in first person, third person if they prefer that (ask if unclear).

    line 80
  16. Distinctive:

    Ask for examples, but accept gut feelings as valid.

    line 81

“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

Professional Twin: Guided Interview

Overview

Help capture professional identity, values, and positions through natural collaborative dialogue.

Start by understanding the current repo context, then ask questions one at a time to explore the topic. Once you understand the user's positions, present the draft in sections and get approval.

Do NOT write or update the file until you have interviewed the user and they have approved the draft. This applies to EVERY topic regardless of perceived simplicity.

Anti-Pattern: "This Topic Is Straightforward"

Every topic goes through the interview. Even ones that seem obvious. "Straightforward" topics are where unexamined assumptions hide. The interview can be short (a few questions for a narrow topic), but you MUST interview before writing.

Checklist

You MUST complete these steps in order:

  1. Identify target file. If the user named one, use it. If they didn't, see "No target file" below.
  2. Build full context. — Read every .md file in the twin repo — all of core-profile/, direction/, application-materials/, and companies/. You need the full picture before you can interview well.
  3. Review target file. — If the file already has content, identify what's solid, what's thin, what's stale, and what's missing. Don't re-interview ground that's already well-covered.
  4. Cross-reference. — Before forming questions, note what other files already capture that's relevant to this file's topic. You'll use this in the next step to avoid re-asking.
  5. Ask clarifying questions — One at a time, understand the user's positions, experiences, and boundaries on this topic. Before asking any question, check whether another file already answers it. If it does, reference it: "I see [file] already captures [X] — does that still hold, or has your thinking changed?" Only ask from-scratch questions for genuinely uncovered ground.
  6. Present draft — In sections scaled to their complexity, get user approval after each section.
  7. Challenge pass — Review the draft for vagueness, contradictions, and gaps; ask targeted follow-ups one at a time.
  8. Write the file — Integrate new material into the existing file. Reduce redundancy, reshape structure where needed, and preserve what was already approved. Save the result.
  9. Note cross-cutting edits* — If the interview uncovered information that should be stored in another file, mention this to the user and ask whether it should be integrated as well.

No target file

If the user invokes the skill without naming a file, do not pick one yourself. Instead:

  1. List the files in the repo organized by section (core-profile/, direction/, application-materials/, companies/).
  2. For each file, give a one-line hint of what it captures (read the top heading and the first paragraph for accurate hints — do not guess).
  3. Ask which file the user wants to work on.

If the repo doesn't look like a twin repo (no core-profile/ folder, no CLAUDE.md referencing professional-twin), bail out:

This doesn't look like a professional twin repository. Run the setup skill first to scaffold one, or cd into your existing twin repo before invoking interview.

Interview Rules

  • One question per message. If a topic needs more exploration, break it into multiple questions across multiple messages.
  • Reflect before advancing. After each answer, play back what you understood in one sentence. Then ask the next question.
  • Be ready to go back. If a later answer casts doubt on an earlier one, return and clarify. Don't only move forward.
  • Don't accept vague answers. "I value autonomy" → "What did autonomy look like in your best role vs. your worst?" Probe for specifics, but accept a firm gut feeling if they can't point to a story.
  • Prefer contrastive pairs and scenarios over open-ended questions. "High comp at a boring company, or 20% less at one you believe in?" beats "How important is mission?"
  • Ask about past behavior, not hypothetical intent. "When did you last turn something down?" beats "What would make you say no?"
  • Name contradictions without judgment. "Earlier you said X, but this sounds like Y — which one wins?"
  • Move on when you have: a clear position (backed by an example or a stated conviction), and an acknowledged tradeoff for each claim.
  • Check pacing. When you think you have enough on a topic, say so and ask the user whether the coverage feels complete or if there's more to dig into. Don't just keep asking — form your own view on when a topic is sufficiently covered.

Reframing

When the user gives a generic answer, reframe it as a specific testable claim and ask if it's accurate:

"So you're saying you'd rather own a smaller scope end-to-end than have influence across a bigger product you don't control — is that right, or does it depend on the team?"

When the user describes a frustration, extract the positive inverse:

"The flip side is you need X — does that sound right?"

When a position sounds settled but hasn't been stress-tested:

"What would have to be true for you to flip on that?"

Presenting the Draft

  • Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced.
  • Ask after each section whether it looks right so far.
  • Be ready to go back and clarify if something doesn't make sense.

Writing Rules

  • Write in the user's voice and framing — first person if they speak in first person, third person if they prefer that (ask if unclear).
  • Ask for examples, but accept gut feelings as valid. Not everything needs evidence.
  • Flag contradictions in an ## Open Questions section — don't paper over them.
  • Tone: direct, specific, opinionated. Decision-support document, not marketing.
  • Preserve content the user has already approved in earlier sessions. Reduce redundancy by editing for clarity, not by deleting positions.

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.