Skip to content
cccskills
FreePublished on GitHub

personal-interview

Build the owner profile and social voice through interview.

The English summary is being prepared. Showing the original description.

indigoai-us/hq-core90 stars(GitHub 90 + cccskills 0)

Run score Not tested

See how to install

Files included (2)

  • SKILL.md5.3 KB
  • agents/openai.yaml128 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Personal Interview

Deep conversational interview to build a rich profile and authentic voice guide. Run this after /setup to give your workers real context about who you are and how you communicate.

Context to Load

  1. Read personal/agents-profile.md if it exists (owner profile + working preferences)
  2. Read personal/agents-companies.md if it exists (company roster + roles)
  3. Read companies/*/knowledge/profile.md if it exists
  4. Read companies/*/knowledge/voice-style.md if it exists

Use existing content as a starting point — don't re-ask what's already captured.

Interview Flow

Ask questions one at a time. Keep it conversational, not interrogative. Adapt follow-ups based on previous answers.

Block 1: Background

  1. What do you do day-to-day? (roles, responsibilities, projects)
  2. What's your professional background in 2-3 sentences?
  3. What industry or domain do you work in?

Block 2: Goals & Priorities

  1. What are you trying to accomplish this quarter/year?
  2. What tasks drain your energy that you'd love to hand off to AI?
  3. What does "done well" look like for you?

Block 3: Communication Style

  1. How would your coworkers describe your communication style?
  2. When you write an email or message, do you tend to be brief or detailed?
  3. Do you use humor, emojis, or keep things strictly professional?
  4. Are there phrases or patterns you naturally use? (e.g., "let's ship it", "what's the blocker")

Block 4: Writing Voice

  1. Share 2-3 examples of things you've written that feel authentically "you" — tweets, emails, messages, anything. (Or paste links/screenshots and I'll analyze them.)
  2. What tone do you aim for in public content? (e.g., authoritative, approachable, provocative, educational)
  3. Are there writers, creators, or voices you admire or want to sound like?
  4. What should your writing NEVER sound like?

Block 5: Work Patterns

  1. How do you prefer to review work — detailed walkthrough or just show me the result?
  2. When should AI ask vs. just decide?
  3. What tools/platforms do you use daily?

Block 6: Personal Context (optional)

  1. Anything else your AI workers should know about you — values, pet peeves, preferences?

Block 7: Profile Photo (final step)

Always ask this last, after every other question, as the step that finishes the interview and gets them into the HQ app.

If personal/agents-profile.md already says "Profile photo: set", skip this step.

  1. Ask whether they have set a profile photo in HQ. You can't check this yourself. If they haven't, ask them to finish by setting one: in the HQ app, open Settings → Profile → Change photo, or go to https://hq.computer/personal/profile. Any photo works; HQ crops it to a square.
  • Wait until they confirm it's done or say "skip". Don't try to upload it yourself; there is no command for that. Don't ask them to paste or attach the photo in chat.
  • Record the result in personal/agents-profile.md only: "Profile photo: set" or "Profile photo: not set". Never write it to companies/{company}/knowledge/profile.md, which is company-scoped.

Output

After the interview, update these files:

companies/{company}/knowledge/profile.md

# {Name}'s Profile

## About
{Rich description from interview — role, background, domain}

## Goals
{Current priorities and what success looks like}

## Delegation Preferences
{What to hand off, what to keep, autonomy level}

## Work Patterns
- Review style: {preference}
- Decision threshold: {when to ask vs. decide}
- Tools: {daily tools/platforms}

## Context Notes
{Anything else — values, pet peeves, preferences}

companies/{company}/knowledge/voice-style.md

# {Name}'s Voice Style

## Tone
{Based on interview — e.g., direct, warm, no-nonsense}

## Communication Style
- Length: {brief/detailed/depends}
- Formality: {casual/professional/adaptive}
- Humor: {yes/no/situational}

## Patterns
- Phrases: {natural phrases they use}
- Never: {what to avoid}

## Public Voice
- Target tone: {authoritative/approachable/etc}
- Influences: {writers/voices they admire}
- Anti-patterns: {what NOT to sound like}

## Examples
{2-3 real examples from the interview, quoted}

personal/agents-profile.md + personal/agents-companies.md

Update or create both files. personal/agents-profile.md holds the owner profile + working preferences (loaded for writing/comms tasks). personal/agents-companies.md holds the three-tier company roster (loaded for company routing). The first line of personal/agents-profile.md MUST stay # {Name} - Profile — the SessionStart hook inject-local-context.sh parses the owner name from that exact pattern.

Rules

  • One question at a time. Wait for response.
  • If user says "skip" or "pass", move on gracefully.
  • Don't fabricate answers — only write what was actually said.
  • If profile/voice files already exist, merge new content with existing. Don't overwrite without asking.
  • Keep the tone of the interview itself warm and conversational — not clinical.
  • Always end the interview with the profile photo step (Block 7).
  • After finishing, suggest: "Run /newworker to create your first worker, or /prd to plan a project."

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

accept

Free

Accept HQ membership invites from a magic link or raw token.

The English summary is being prepared. Showing the original description.

indigoai-us/hq-core90Updated Oct 26, 2026

adr

Free

Capture qualifying architecture decisions as ADRs in the right HQ or repo location.

The English summary is being prepared. Showing the original description.

indigoai-us/hq-core90Updated Oct 26, 2026

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

The English summary is being prepared. Showing the original description.

indigoai-us/hq-core90Updated Oct 26, 2026

Find shallow modules and propose deepening refactors, ranked with file refs; never edits code. Use when code is hard to change or planning a refactor.

The English summary is being prepared. Showing the original description.

indigoai-us/hq-core90Updated Oct 26, 2026

Generate dark ASCII banner graphics for HQ and social launch assets.

The English summary is being prepared. Showing the original description.

indigoai-us/hq-core90Updated Oct 26, 2026

Compare approaches to best-in-class prior art, merge existing work, verify cruft removal, and recommend the most durable design before PRD work.

The English summary is being prepared. Showing the original description.

indigoai-us/hq-core90Updated Oct 26, 2026

See all skills by indigoai-us

Report a problem with this skill