nih-biosketch-builder

Generate NIH Biosketch documents compliant with the 2022 OMB-approved.

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/nih-biosketch-builder/SKILL.md

Quality

Content

50%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body contains genuine NIH-specific content (format requirements, JSON schema, PubMed import) and executable commands, but it is buried under generic boilerplate and lacks a validation step tying document generation to the stated format constraints. Structure and focus need tightening.

Suggestions

Remove or relocate generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template, Functions) so the NIH-specific guidance is the focus of SKILL.md.

Add an explicit validation step to the workflow that checks generated DOCX against the format specs (page count <= 5, fonts >= 11pt, margins >= 0.5 inches, all four required sections present) with a fix-and-regenerate loop.

Fix the broken cross-references ('See ## Usage above' / 'See ## Workflow above') and reconcile the contradictory dependency statements ('No additional Python packages required' vs. python-docx/requests).

Dimension	Reasoning	Score
Conciseness	The body is padded with generic boilerplate ('Risk Assessment', 'Security Checklist', 'Evaluation Criteria', 'Lifecycle Status', 'Response Template', a one-line 'Functions') and broken cross-references ('See ## Usage above' when Usage is below), matching anchor 2 for noticeable verbosity.	2 / 5
Actionability	It provides concrete executable CLI commands, a full JSON input schema, and PMID auto-import commands, matching anchor 4 for mostly executable guidance with only minor gaps.	4 / 5
Workflow Clarity	The 5-step workflow is generic and never validates generated output against the listed NIH format specs; 'Quick Check'/'Audit-Ready Commands' only confirm the script parses, so per the batch/output cap workflow clarity stays at 3.	3 / 5
Progressive Disclosure	A real one-level reference (references/audit-reference.md) and scripts/main.py are signaled, but the SKILL.md is bloated with off-topic inline boilerplate that does not aid discovery, matching anchor 3.	3 / 5
	Total	12 / 20 Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a clear, distinct niche and one concrete action but is truncated ('2022 OMB-approved' lacks a noun) and omits any 'when to use' trigger guidance. It reads as a drafted one-liner rather than a polished trigger description.

Suggestions

Add an explicit 'Use when...' clause naming triggers, e.g. 'Use when preparing NIH grant applications, fellowships, or progress reports that require a 2022 OMB-approved biosketch.'

List more concrete actions beyond 'generate', such as filling the four required sections, auto-importing publications from PubMed via PMID, and producing DOCX output in the NIH template.

Complete the truncated phrase and add natural synonyms/file extensions (e.g. 'NIH grant', 'SciENcv', 'biosketch format', '.docx') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('NIH Biosketch documents') and one concrete action ('Generate') but lists no further actions such as filling sections or importing publications, matching anchor 3.	3 / 5
Completeness	A clear 'what' is present ('Generate NIH Biosketch documents compliant with the 2022 OMB-approved') but there is no 'Use when...' clause, so per the guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	'NIH Biosketch' and '2022 OMB-approved' are relevant natural terms, but common synonyms and file extensions ('NIH grant', 'SciENcv', '.docx', 'biosketch format') are missing, matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	'NIH Biosketch' is a clear niche with low conflict risk, but the truncated phrase and absence of trigger guidance keep it just below a clean 5, landing between anchors 4 and 5.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Academic Writing/nih-biosketch-builder/SKILL.md
Commit: 63c61d3

Reviewed: 10 hours ago

Table of Contents

Discovery Implementation Validation

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.