Ready to supercharge your AI agents?

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

Research Guardian · brycewang-stanford | DecimalAI

researchby brycewang-stanford

Research Guardian

brycewang-stanford/x1

Source brycewang-stanford/Auto-Empirical-Research-Skills ↗License NOASSERTION

Research Guardian - Ethics Advisory & Bias Detection across all research stages Enhanced VS 3-Phase process: Surface-level screening, deep contextual analysis, constructive recommendations

SkillScore64Maintained

Automatic

Research pack

Last verified 8/8/2026

What it changes

Passed 14 of 22 test cases with the skill, and 13 of 22 without it.

Without skill59%

With skill64%

Checks it passed that the model alone missed

Recommends full IRB review and external ethics consultation.
Cites GDPR requirements for data minimization and purpose limitation.
Identifies informed consent as the primary application for demonstrating respect for persons.

3 fixed11 passed either way6 still failing2 broke

Pass-rate lift: +5 pp
Tokens: +98%
Agent turns: 0%
Response time: +32%

Model gemini-3.6-flashMeasured 8/8/2026v114 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/brycewang-stanford-x1/SKILL.md https://app.decimal.ai/s/brycewang-stanford-x1/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-x1, 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/brycewang-stanford-x1/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-x1

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

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-x1/SKILL.md https://app.decimal.ai/s/brycewang-stanford-x1/SKILL.md

Raw file: /s/brycewang-stanford-x1/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-x1.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

We are designing a clinical trial testing an experimental medical device. To prepare our IRB application baseline, evaluate human subjects protections against standard US federal regulations for bioethics. Provide an analysis evaluating respect for persons, beneficence, and justice, structured in a table with Area, Status, Concerns, and Recommendations, under an Ethics Review Summary header.

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies the Belmont Report as the baseline framework for respect for persons, beneficence, and justice.	Passed	Passed
Identifies informed consent as the primary application for demonstrating respect for persons.	Missed	Passed

case-04 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md188 linessingle file

Prerequisites (v8.2 -- MCP Enforcement)

diverga_check_prerequisites("x1") -> must return approved: true

No prerequisites required. X1 is a cross-cutting agent that can be invoked at any stage.

Checkpoints During Execution

CHECKPOINT OPTIONAL -> diverga_mark_checkpoint("CP_ETHICS_REVIEW", decision, rationale)

Fallback (MCP unavailable)

Read .research/decision-log.yaml directly. Conversation history is last resort.

Research Guardian

Agent ID: X1 Category: X - Cross-Cutting VS Level: Enhanced (3-Phase) Tier: MEDIUM (Sonnet)

Overview

Cross-cutting quality and integrity agent combining research ethics advisory (from A4) with bias and trustworthiness detection (from F4). Can be invoked at any stage of the research lifecycle -- from proposal through publication -- with no prerequisites.

When to Use

Before data collection: ethics review, IRB preparation, informed consent design
During analysis: QRP screening, bias detection, trustworthiness assessment
Before submission: integrity audit, research practice verification
At any stage: cross-cutting ethics and bias concerns

VS-Enhanced 3-Phase Process

Phase 1: Identify Standard Ethics/Bias Concerns

Purpose: Flag predictable, surface-level concerns that any reviewer would catch.

Scan for obvious ethical oversights (missing consent, unprotected data)
Check for common QRP indicators (p-hacking, HARKing, selective reporting)

Track record

Benchmark

14 / 22

test cases passed, vs 13 / 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 — 8/2/2026

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

brycewang-stanford / Auto-Empirical-Research-Skills

skills/25-HosungYou-Diverga/skills/x1/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version 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

Prerequisites (v8.2 -- MCP Enforcement)

Checkpoints During Execution

Fallback (MCP unavailable)

Research Guardian

Overview

When to Use

VS-Enhanced 3-Phase Process

Phase 1: Identify Standard Ethics/Bias Concerns

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills