Ready to supercharge your AI agents?

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

Get Started Free →

Design Space Exploration · yogsoth-ai | DecimalAI

researchby yogsoth-ai

Design Space Exploration

yogsoth-ai/design-space-exploration

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

Parametric variation + constraint satisfaction combinatorial search

SkillScore95Maintained

Automatic

Research pack

Last verified 8/22/2026

What it changes

Passed 20 of 21 test cases with the skill, and 11 of 21 without it.

Without skill55%

With skill95%

Checks it passed that the model alone missed

The target budget for web-search must be 20
The target budget for web-research must be 8
The target budget for paper-research must be 5

and 7 more in the full report

10 fixed11 passed either way0 still failing1 broke

Pass-rate lift: +41 pp
Tokens: -3%
Agent turns: 0%
Response time: -41%

Model gemini-3.6-flashMeasured 8/22/2026v121 of 22 cases passed with skill · 21 comparable

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-design-space-exploration/SKILL.md https://app.decimal.ai/s/yogsoth-ai-design-space-exploration/SKILL.md

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

decimalai skills add yogsoth-ai-design-space-exploration

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

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-design-space-exploration/SKILL.md https://app.decimal.ai/s/yogsoth-ai-design-space-exploration/SKILL.md

Raw file: /s/yogsoth-ai-design-space-exploration/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-design-space-exploration.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

What is the target resource count specified for web-research in the state ledger?

What was checked, without and with the skill
Checked	Without skill	With skill
The target budget for web-research must be 8	Missed	Passed

case-19 · 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.md57 linessingle file

Design Space Exploration

Parametric variation + constraint satisfaction combinatorial search. Systematically explore the combinatorial design space by varying parameters under constraints to find novel viable configurations.

State Ledger

Resource	Target	%
web-search	20	0%
web-research	8	0%
paper-overview	20	0%
paper-search	12	0%
paper-research	5	0%

HARD-GATE

Cannot exit strategy until ≥80% of each budget line is consumed OR yield targets are met with justification for remaining budget.

Available Tactics

Tactic	Role
combination-mapping	Enumerate parameter dimensions and generate viable combinations
emergence-detection	Detect emergent properties in novel configurations

Available SOPs

SOP	Role
input-space-construction	Build parameter spaces for design dimensions
generic-space-extraction	Extract shared constraints across configurations
emergent-property-identification	Identify non-additive properties in novel configurations
combinatorial-synthesis	Synthesize design space exploration outputs

Execution Guidance

Define Parameters: Identify independent design dimensions
Set Constraints: Define hard constraints (must satisfy) and soft constraints (prefer)
Enumerate: Use combination-mapping to systematically generate configurations
Filter: Apply constraint satisfaction to eliminate infeasible combinations

Track record

Benchmark

20 / 21

test cases passed, vs 11 / 21 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/design-space-exploration/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.

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

Design Space Exploration

State Ledger

HARD-GATE

Available Tactics

Available SOPs

Execution Guidance

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills