Ready to supercharge your AI agents?

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

Problem Framing · getcrew44 | DecimalAI

productivityby getcrew44

Problem Framing

getcrew44/problem-framing

Source getcrew44/crew44 ↗License MIT

Use when the user describes a goal but the underlying problem is unclear, or when a request feels like a premature solution.

SkillScore77Maintained

Automatic

Product Management pack

Last verified 8/23/2026

What it changes

Passed 17 of 22 test cases with the skill, and 11 of 22 without it.

Without skill50%

With skill77%

Checks it passed that the model alone missed

Asks who the target end user is.
Asks what is blocking the user today.
Offers between 2 and 3 problem framings.

and 7 more in the full report

9 fixed8 passed either way2 still failing3 broke

Pass-rate lift: +27 pp
Tokens: -29%
Agent turns: 0%
Response time: -36%

Model gemini-3.6-flashMeasured 8/23/2026v117 of 22 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/getcrew44-problem-framing/SKILL.md https://app.decimal.ai/s/getcrew44-problem-framing/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add getcrew44-problem-framing, 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/getcrew44-problem-framing/ and pins it in .decimal/skills.lock

decimalai skills add getcrew44-problem-framing

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

curl -fsSL --create-dirs -o .claude/skills/getcrew44-problem-framing/SKILL.md https://app.decimal.ai/s/getcrew44-problem-framing/SKILL.md

Raw file: /s/getcrew44-problem-framing/SKILL.md ↗ · machine-readable summary at /s/getcrew44-problem-framing.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

Our sales team claims the CRM is too slow and asked us to rebuild the backend database right away. I suspect jumping straight into a database overhaul is premature, but I need to figure out what's really driving this request. Can you help me unpack this request and frame the actual core problem before we take any action?

What was checked, without and with the skill
Checked	Without skill	With skill
Restates the database rebuild request in plain language without technical jargon.	Missed	Passed
Identifies at least one hidden assumption behind the database overhaul request.	Passed	Passed
Offers between 2 and 3 distinct problem framings.	Passed	Passed

case-01 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md23 linessingle file

Problem Framing

Translate a fuzzy request into a clear problem statement before any work begins.

When to use

The user describes what they want but not why.
The request jumps to a specific solution.
Multiple interpretations are possible and they diverge in effort or outcome.

Steps

Restate the request in plain language. Confirm with the user.
Ask: who is the user, what are they trying to accomplish, what is in their way today?
Identify hidden assumptions in the request and name them.
Offer 2-3 framings of the problem if more than one fits. Let the user pick.
State the chosen framing back as a single sentence the user can confirm.

Anti-patterns

Restating jargon back without unpacking it.
Asking five clarifying questions at once.
Skipping confirmation and proceeding on a guess.

Track record

Benchmark

17 / 22

test cases passed, vs 11 / 22 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

getcrew44 / crew44

daemon/internal/presets/defaultcrew/skills/partner/problem-framing/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

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

Problem Framing

When to use

Steps

Anti-patterns

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills