Ready to supercharge your AI agents?

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

Get Started Free →

FINER Criteria Check · yogsoth-ai | DecimalAI

researchby yogsoth-ai

FINER Criteria Check

yogsoth-ai/finer-criteria-check

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

SOP: check research-question quality against each of the 5 FINER criteria

SkillScore78Maintained

Automatic

Research pack

Last verified 8/23/2026

What it changes

Passed 18 of 23 test cases with the skill, and 14 of 23 without it.

Without skill61%

With skill78%

Checks it passed that the model alone missed

Report the overall score as PASS (5/5).
State the overall summary as PASS (5/5).
Provide an overall verdict of PASS (5/5).

and 11 more in the full report

8 fixed10 passed either way1 still failing4 broke

Pass-rate lift: +17 pp
Tokens: -22%
Agent turns: 0%
Response time: -24%

Model gemini-3.6-flashMeasured 8/23/2026v118 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/yogsoth-ai-finer-criteria-check/SKILL.md https://app.decimal.ai/s/yogsoth-ai-finer-criteria-check/SKILL.md

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

decimalai skills add yogsoth-ai-finer-criteria-check

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

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-finer-criteria-check/SKILL.md https://app.decimal.ai/s/yogsoth-ai-finer-criteria-check/SKILL.md

Raw file: /s/yogsoth-ai-finer-criteria-check/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-finer-criteria-check.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

Assess this environmental question: 'How does seasonal microplastic accumulation in urban stormwater runoff affect benthic invertebrate biodiversity in the Puget Sound watershed?' Provide individual F, I, N, E, R pass/fail lines and overall status.

What was checked, without and with the skill
Checked	Without skill	With skill
Assign a PASS judgment to all five FINER criteria.	Passed	Passed
Report the overall score as PASS (5/5).	Missed	Passed

case-14 · 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.md34 linessingle file

FINER Criteria Check

FINER 5-criteria per-item check — the standardized test of research-question quality.

HARD-GATE

Pipeline

Pre-check: is the RQ a complete sentence
F (Feasible): is it feasible under the available resources/time/data
I (Interesting): is it interesting to scholars and practitioners in the field
N (Novel): does it provide new knowledge/new perspective/new method
E (Ethical): does it comply with research ethics
R (Relevant): is it relevant to the field/society/practice
Overall verdict: all pass / partial pass
Revision suggestions: give specific revision directions for failed items
Output: the 5 verdicts + revision suggestions (if any)

Output Format

F: PASS/FAIL — [rationale]
I: PASS/FAIL — [rationale]
N: PASS/FAIL — [rationale]
E: PASS/FAIL — [rationale]
R: PASS/FAIL — [rationale]

Overall: PASS (5/5) / PARTIAL (X/5)
Suggestions: [specific revision suggestions for FAIL items]

Track record

Benchmark

18 / 23

test cases passed, vs 14 / 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

yogsoth-ai / de-anthropocentric-research-engine

skills/finer-criteria-check/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-assessmentSOP: Assess whether a research question has appropriate scope (too broad / appropriate / too narrow)Close match+63 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

FINER Criteria Check

HARD-GATE

Pipeline

Output Format

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills