nih-biosketch-builder

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

Quality

46%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

35%

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

The body contains genuinely useful, executable NIH-specific content (CLI flags, JSON schema, format specs) that matches the real main.py, but it is buried under heavy generic boilerplate, internal contradictions, redundant command repetition, and a workflow lacking NIH-specific validation. It scores below the rubric midpoint, driven down mainly by conciseness.

Suggestions

Cut the generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Test Cases, Lifecycle Status, Response Template, Output Requirements) and the duplicated py_compile/--help blocks to restore token efficiency and remove the Prerequisites/Dependencies contradiction.

Standardize on a single script path and remove "See ## Usage above"-style cross-references so every command is copy-paste ready.

Add an explicit NIH format-conformance validation step to the Workflow (e.g., verify the generated DOCX is <=5 pages and uses an approved >=11pt font with >=0.5" margins) with a validate->fix->retry feedback loop before delivery.

Dimension	Reasoning	Score
Conciseness	The ~250-line body is padded with generic boilerplate (Risk Assessment table, 12-item Security Checklist, Lifecycle Status with dates, Evaluation Criteria, Response Template) and repeats the same py_compile/--help commands across Quick Check, Audit-Ready Commands, and Example Usage, while "Prerequisites: No additional Python packages required" directly contradicts the Dependencies section.	1 / 3
Actionability	Real executable commands ("python scripts/main.py --input data.json --output biosketch.docx", "--import-pubmed '12345678,23456789' --output publications.json") and a concrete JSON input schema are present and match main.py's argparse, but two inconsistent script paths ("scripts/main.py" vs "skills/nih-biosketch-builder/scripts/main.py") and vague cross-refs ("See ## Usage above") prevent copy-paste-ready guidance throughout.	2 / 3
Workflow Clarity	The five-step Workflow is sequenced with a fallback notion, but for a fragile document-generation task it lacks any NIH-specific validation checkpoint (e.g., verify <=5 pages, confirm fonts/margins meet NIH spec) or validate->fix->retry feedback loop, which caps workflow_clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	references/audit-reference.md is a real, one-level-deep, clearly signaled file, but the body is a monolithic wall of mostly-inline boilerplate with two duplicate "## References" headers, so content that should be split out is not and navigation is weakened.	2 / 3
	Total	7 / 12 Passed

Description

57%

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, distinctive niche but is grammatically truncated and covers only a single action with no explicit "Use when..." trigger clause, so it answers "what" but not "when." It sits just above the midpoint of the rubric.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user needs to prepare or generate an NIH Biosketch for a grant application."

Expand the action list beyond a single verb to reflect the script's real capabilities (generate DOCX, auto-import publications from PubMed, emit a template), e.g. "Generate NIH Biosketch DOCX files, auto-import publications from PubMed via PMID, and produce input templates."

Fix the truncated phrase "compliant with the 2022 OMB-approved." by adding the missing noun, e.g. "the 2022 OMB-approved NIH Biosketch format."

Dimension	Reasoning	Score
Specificity	"Generate NIH Biosketch documents compliant with the 2022 OMB-approved" names a concrete domain and one action verb, but lists only a single action rather than multiple specific concrete actions (e.g., generate, validate format, auto-import PubMed).	2 / 3
Completeness	It states what the skill does ("Generate NIH Biosketch documents...") but includes no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	"NIH Biosketch" is a natural term users would say, but the description lacks common variations and trigger phrasing such as NIH grants, biosketches, or NIH applications, and the sentence is truncated at "2022 OMB-approved."	2 / 3
Distinctiveness Conflict Risk	"NIH Biosketch documents compliant with the 2022 OMB-approved" targets a highly specific, unambiguous niche that is unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 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
Commit: 7cc5680

Reviewed: 3 days 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.