Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Interview — measured AI agent skill | DecimalAI

hmbown/interview

SkillScore59Maintained

Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.

by hmbown

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Product Management pack

decimalai skills pull hmbown-interview

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/hmbown-interview/SKILL.md

Raw file: /s/hmbown-interview/SKILL.md ↗ · machine-readable summary at /s/hmbown-interview.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3d ago

—-41% tokens0% turns59% of whole cases pass with skill (13/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-08	✗→✓	▲ Improved	-48%	0%
case-04	✗→✓	▲ Improved	-62%	0%
case-06	✗→✓	▲ Improved	-79%	0%
case-07	✗→✓	▲ Improved	-64%	0%
case-10	✗→✓	▲ Improved	-65%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

hmbown / codewhale

crates/tui/assets/skills/interview/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Interview

When to use

Use when the request lacks a material product or implementation choice that cannot be discovered from the workspace or tools.

Non-goals

Do not interview for facts you can read, search, or measure.
Do not ask multi-question dumps. One focused question at a time.
Do not invent requirements.

Workflow

State the missing decision and why it blocks progress.
Offer concrete options when possible.
Record the answer and continue the work.
Produce a short brief/spec only when enough answers exist.

Failure mode

If the user declines to answer, proceed with explicit assumptions and label them.

Want to see if hmbown/interview would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.