grant-mock-reviewer

Simulates NIH study section peer review for grant proposals. Triggers when user wants mock review, critique, or evaluation of a grant proposal before submission. Generates structured critique using official NIH scoring rubric (1-9 scale), identifies weaknesses, provides actionable revision recommendations, and produces a comprehensive review summary similar to actual NIH Summary Statement.

Install with Tessl CLI

npx tessl i github:aipoch/medical-research-skills --skill grant-mock-reviewer

What are skills?

Review — 72%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

46%

-18%

Mock NIH Peer Review: R01 Grant Proposal

Full NIH Summary Statement output

Criteria

Without context

With context

1-9 scale direction

87%

Five criteria scored

100%

Correct score descriptors

20%

40%

MOCK SUMMARY STATEMENT header

100%

Estimated Percentile

Resume and Summary section

Per-criterion strengths bullets

100%

Per-criterion weaknesses bullets

100%

Per-criterion narrative

100%

Additional Review Considerations

75%

Revision recommendations section

100%

Priority-ordered recommendations

90%

100%

Without context: $0.2447 · 1m 48s · 12 turns · 16 in / 5,089 out tokens

With context: $0.5163 · 1m 14s · 21 turns · 8,442 in / 3,732 out tokens

100%

85%

Grant Scoring Dashboard: Machine-Readable Output

Machine-readable JSON scores output

Criteria

Without context

With context

Uses scripts/main.py

100%

--scores-only flag

100%

--output flag used

100%

Output is valid JSON

100%

overall_impact field

100%

priority_score field

100%

criteria object present

100%

Per-criterion score field

100%

Per-criterion strengths field

100%

Per-criterion weaknesses field

100%

Without context: $0.5049 · 2m 29s · 18 turns · 21 in / 9,163 out tokens

With context: $0.4577 · 1m 16s · 18 turns · 8,441 in / 3,599 out tokens

100%

64%

Assessing Grant Revision Impact

Before/after proposal revision comparison

Criteria

Without context

With context

Uses scripts/main.py

100%

--compare flag

100%

--original flag

100%

--revised flag

100%

Output saved to file

100%

Original impact score shown

100%

Revised impact score shown

100%

Criterion-level changes shown

100%

Direction indicators present

100%

Without context: $0.5348 · 2m 59s · 19 turns · 21 in / 10,022 out tokens

With context: $0.4641 · 1m 34s · 17 turns · 8,438 in / 4,585 out tokens

Evaluated: 1 day ago
Agent: Claude Code

Table of Contents

Mock NIH Peer Review: R01 Grant Proposal Grant Scoring Dashboard: Machine-Readable Output Assessing Grant Revision Impact

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.