Ready to supercharge your AI agents?

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

Get Started Free →

Research Review via a secondary Codex agent (xhigh reasoning) · brycewang-stanford | DecimalAI

researchby brycewang-stanford

Research Review via a secondary Codex agent (xhigh reasoning)

brycewang-stanford/research-review

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

Get a deep critical review of research from Claude via claude-review MCP.

SkillScore64Maintained

Automatic

Research pack

Last verified 8/28/2026

What it changes

Passed 12 of 19 test cases with the skill, and 6 of 19 without it.

Without skill32%

With skill64%

Checks it passed that the model alone missed

The specified reviewer model parameter is gpt-5.4.
The reasoning effort parameter is configured to xhigh.
Subsequent dialogue turns use send_input referencing the spawned agent id.

and 4 more in the full report

7 fixed7 passed either way8 still failing0 broke

Pass-rate lift: +32 pp
Tokens: +23%
Agent turns: 0%
Response time: -24%

Model gemini-3.6-flashMeasured 8/28/2026v314 of 22 cases passed with skill · 19 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/brycewang-stanford-research-review/SKILL.md https://app.decimal.ai/s/brycewang-stanford-research-review/SKILL.md

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

decimalai skills add brycewang-stanford-research-review

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

We want to launch an external Codex reviewer agent to critique our machine learning research project. Which specific default model parameter should be specified when spawning this reviewer agent?

What was checked, without and with the skill
Checked	Without skill	With skill
The specified reviewer model parameter is gpt-5.4.	Missed	Passed

case-03 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md96 linessingle file

Research Review via a secondary Codex agent (xhigh reasoning)

Get a multi-round critical review of research work from an external LLM with maximum reasoning depth.

Constants

REVIEWER_MODEL = gpt-5.4 — Model used via a secondary Codex agent. Must be an OpenAI model (e.g., gpt-5.4, o3, gpt-4o)

Context: $ARGUMENTS

Prerequisites

Use spawn_agent and send_input when the user has explicitly allowed delegation or subagents.
If delegation is not allowed, run the same review loop locally and preserve the same deliverable structure.

Workflow

Step 1: Gather Research Context

Before calling the external reviewer, compile a comprehensive briefing:

Read project narrative documents (e.g., STORY.md, README.md, paper drafts)
Read any memory/notes files for key findings and experiment history
Identify: core claims, methodology, key results, known weaknesses

Step 2: Initial Review (Round 1)

Send a detailed prompt with xhigh reasoning:

spawn_agent:
  reasoning_effort: xhigh
  message: |
    [Full research context + specific questions]
    Please act as a senior ML reviewer (NeurIPS/ICML level). Identify:
    1. Logical gaps or unjustified claims
    2. Missing experiments that would strengthen the story
    3. Narrative weaknesses
    4. Whether the contribution is sufficient for a top venue
    Please be brutally honest.

Step 3: Iterative Dialogue (Rounds 2-N)

Track record

Benchmark

12 / 19

test cases passed, vs 6 / 19 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 — 8/9/2026

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/42-wanshuiyin-ARIS/skills/skills-codex-claude-review/research-review/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/9/2026Version v3

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

Research Review via a secondary Codex agent (xhigh reasoning)

Constants

Context: $ARGUMENTS

Prerequisites

Workflow

Step 1: Gather Research Context

Step 2: Initial Review (Round 1)

Step 3: Iterative Dialogue (Rounds 2-N)

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills