Ready to supercharge your AI agents?

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

Get Started Free →

Ask Questions If Underspecified · moizibnyousaf | DecimalAI

productivityby moizibnyousaf

Ask Questions If Underspecified

moizibnyousaf/ask-questions-if-underspecified

Source moizibnyousaf/ai-agent-skills ↗License MIT

Clarify requirements before implementing.

SkillScore65Maintained

Automatic

Coding pack

Last verified 8/16/2026

What it changes

Passed 15 of 23 test cases with the skill, and 3 of 23 without it.

Without skill13%

With skill65%

Checks it passed that the model alone missed

Default choices are bolded.
Recommended options are bolded.
Default options are clearly bolded.

and 31 more in the full report

13 fixed2 passed either way7 still failing1 broke

Pass-rate lift: +52 pp
Tokens: -6%
Agent turns: 0%
Response time: -47%

Model gemini-3.6-flashMeasured 8/16/2026v115 of 23 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/moizibnyousaf-ask-questions-if-underspecified/SKILL.md https://app.decimal.ai/s/moizibnyousaf-ask-questions-if-underspecified/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add moizibnyousaf-ask-questions-if-underspecified, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/moizibnyousaf-ask-questions-if-underspecified/ and pins it in .decimal/skills.lock

decimalai skills add moizibnyousaf-ask-questions-if-underspecified

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/moizibnyousaf-ask-questions-if-underspecified/SKILL.md https://app.decimal.ai/s/moizibnyousaf-ask-questions-if-underspecified/SKILL.md

Raw file: /s/moizibnyousaf-ask-questions-if-underspecified/SKILL.md ↗ · machine-readable summary at /s/moizibnyousaf-ask-questions-if-underspecified.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

I need you to add an export feature for customer reports in our web app, but I haven't defined the exact formats or scope yet. Help me figure out what key decisions we need to make before writing any code.

What was checked, without and with the skill
Checked	Without skill	With skill
The response presents numbered questions with lettered multiple-choice options.	Missed	Passed
The recommended default option in each question is bolded.	Missed	Passed
The response includes a fast-path reply instruction such as 'defaults' or compact option codes.	Missed	Passed

case-01 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md76 linessingle file

Ask Questions If Underspecified

Goal

Ask the minimum set of clarifying questions needed to avoid wrong work; do not start implementing until the must-have questions are answered (or the user explicitly approves proceeding with stated assumptions).

Workflow

1) Decide whether the request is underspecified

Treat a request as underspecified if after exploring how to perform the work, some or all of the following are not clear:

Define the objective (what should change vs stay the same)
Define "done" (acceptance criteria, examples, edge cases)
Define scope (which files/components/users are in/out)
Define constraints (compatibility, performance, style, deps, time)
Identify environment (language/runtime versions, OS, build/test runner)
Clarify safety/reversibility (data migration, rollout/rollback, risk)

If multiple plausible interpretations exist, assume it is underspecified.

2) Ask must-have questions first (keep it small)

Ask 1-5 questions in the first pass. Prefer questions that eliminate whole branches of work.

Make questions easy to answer:

Optimize for scannability (short, numbered questions; avoid paragraphs)
Offer multiple-choice options when possible
Suggest reasonable defaults when appropriate (mark them clearly as the default/recommended choice; bold the recommended choice in the list, or if you present options in a code block, put a bold "Recommended" line immediately above the block and also tag defaults inside the block)
Include a fast-path response (e.g., reply defaults to accept all recommended/default choices)
Include a low-friction "not sure" option when helpful (e.g., "Not sure - use default")
Separate "Need to know" from "Nice to know" if that reduces friction
Structure options so the user can respond with compact decisions (e.g., 1b 2a 3c); restate the chosen options in plain language to confirm

3) Pause before acting

Until must-have answers arrive:

Do not run commands, edit files, or produce a detailed plan that depends on unknowns
Do perform a clearly labeled, low-risk discovery step only if it does not commit you to a direction (e.g., inspect repo structure, read relevant config files)

If the user explicitly asks you to proceed without answers:

Track record

Benchmark

15 / 23

test cases passed, vs 3 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

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

moizibnyousaf / ai-agent-skills

skills/ask-questions-if-underspecified/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Ask Questions If Underspecified

Goal

Workflow

1) Decide whether the request is underspecified

2) Ask must-have questions first (keep it small)

3) Pause before acting

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills