Index of every page on this site: llms.txt
All skills
paulrberg avatar

/interview-me

@c9e5a34
by Paul Bergpaulrberg/agent-skills106 stars
11
Run it yourself

Interview the user about a plan, idea, or design through a short sequence of high-leverage questions, then summarize the direction and next step. Use when the user wants a relaxed interview, lightweight clarification, or says "interview me", without exhaustive grilling.

Use this Skill: https://skilld.dev/gh/paulrberg/agent-skills/interview-me

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈71 tokens for metadata: the name and description. ≈560 when used: this file. ≈11 more on demand in 1 file.

Description uses 3.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈285 characters, or 3.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Interview Me

This skill is coordination-exempt: skip the ai-coord gate for its declared work.

Clarify what the user wants through a focused, conversational interview without exhausting every possible branch.

Workflow

  1. Extract the current objective, audience, constraints, assumptions, and already-made choices. Investigate facts available from the conversation, codebase, or supplied evidence instead of asking for them.
  2. Ask exactly one concise question per turn in plain conversational language. Format every question turn as ### 💬 Question <N> — <topic>, followed by **🧭 Context**, optional **🎯 Recommended**, and **❓ Question** sections, with each label on its own line. Keep the context brief. Include a recommended default only when it makes the question easier to answer. Put exactly one question in the final section. Choose the highest-leverage question whose answer could materially change the direction or next step.
  3. Treat three to five questions as a soft target, not a quota or hard cap. Stop earlier when the direction is already clear. Continue beyond five only when the next answer could still materially change the result. Otherwise, record the uncertainty for the summary.
  4. Favor intent, scope, success criteria, audience, and key tradeoffs. Follow the threads the user emphasizes instead of mechanically covering every interface, failure mode, operational concern, or other domain.
  5. Briefly acknowledge or synthesize an answer as ✅ Noted: <choice or implication> only when it advances the conversation. Do not use decision cards, progress counts, exhaustive checklists, repeated recaps, or a formal decision record. Do not reopen settled choices unless new evidence conflicts with them.
  6. Finish immediately when the user asks to stop or when further questions would add little value. Return ### 🧭 Summary, ### ✅ Key choices, optional ### ❓ Open questions, and ### 🏁 Next step. Keep the final response concise. Do not end with another question.

Completion requires a clear summary of the user's direction, the choices that materially shape it, any unresolved uncertainty worth preserving, and one practical next step.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    This skill provides a conversational framework for interviewing users about their projects or ideas. It is purely instruction-based, contains no executable code or network requests, and presents no security risks.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

Signed by skilld at c9e5a34. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 months ago
coordination
exempt

README badge

README badge for paulrberg/agent-skills/interview-me