Ready to supercharge your AI agents?

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

Get Started Free →

Constraint Elicitation · yogsoth-ai | DecimalAI

researchby yogsoth-ai

Constraint Elicitation

yogsoth-ai/constraint-elicitation

Source yogsoth-ai/de-anthropocentric-research-engine ↗License Apache-2.0

Structured questioning SOP to identify practical constraints that shape the research spec. Used during spec generation.

SkillScore75Maintained

Automatic

Research pack

Last verified 8/22/2026

What it changes

Passed 18 of 24 test cases with the skill, and 6 of 24 without it.

Without skill25%

With skill75%

Checks it passed that the model alone missed

The response asks only one question.
The response asks exactly one question.
The response asks only the first single question.

and 11 more in the full report

14 fixed4 passed either way4 still failing2 broke

Pass-rate lift: +50 pp
Tokens: -41%
Agent turns: 0%
Response time: -59%

Model gemini-3.6-flashMeasured 8/22/2026v118 of 24 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/yogsoth-ai-constraint-elicitation/SKILL.md https://app.decimal.ai/s/yogsoth-ai-constraint-elicitation/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yogsoth-ai-constraint-elicitation, 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/yogsoth-ai-constraint-elicitation/ and pins it in .decimal/skills.lock

decimalai skills add yogsoth-ai-constraint-elicitation

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

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-constraint-elicitation/SKILL.md https://app.decimal.ai/s/yogsoth-ai-constraint-elicitation/SKILL.md

Raw file: /s/yogsoth-ai-constraint-elicitation/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-constraint-elicitation.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 14

Prompt

I want to research perovskite solar cell degradation. I plan to spend 5-7 sessions and want to prioritize web sources. Ask me the next question to gather context.

What was checked, without and with the skill
Checked	Without skill	With skill
The response asks exactly one question.	Missed	Passed
The response omits asking about time budget.	Passed	Passed

case-11 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md27 linessingle file

Constraint Elicitation

Ask the user 2-3 questions about practical constraints.

Questions (select 2-3 most relevant)

Time Budget
- "Roughly how many sessions do you want to spend on this research?"
- Options: (A) Quick — 3-4 sessions (B) Standard — 5-7 sessions (C) Deep — 8-10 sessions (D) No limit, go as deep as needed
Existing Knowledge
- "Do you already have papers, notes, or prior research on this topic?"
- Options: (A) Starting from scratch (B) I have some papers/notes I can share (C) I have significant prior work — skip basics
Tool Preferences
- "Any preferences for research tools?"
- Options: (A) Use everything available (B) Prioritize academic papers (Semantic Scholar) (C) Prioritize web sources (D) I'll provide specific sources
Hard Constraints
- "Any hard constraints I should know about?"
- Open-ended — deadlines, specific exclusions, required methodologies

Rules

Ask ONE question at a time
Skip questions whose answers are obvious from context
Time budget directly affects spec granularity (fewer sessions = fewer strategies per stage)

Track record

Benchmark

18 / 24

test cases passed, vs 6 / 24 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

yogsoth-ai / de-anthropocentric-research-engine

skills/constraint-elicitation/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Other skills for the same job

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

yogsoth-ai/scope-clarificationStructured questioning SOP to determine research boundaries, depth, and breadth. Used during spec generation.Close match+23 pp pass-rate 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

Constraint Elicitation

Questions (select 2-3 most relevant)

Rules

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills