nih-biosketch-builder
Generate NIH Biosketch documents compliant with the 2022 OMB-approved.
32
27%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/nih-biosketch-builder/SKILL.mdQuality
Discovery
40%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 and specific niche (NIH Biosketch generation) which gives it strong distinctiveness, but it is too terse overall. It lacks a 'Use when...' clause, lists only one action (generate), and misses natural trigger terms users might employ when requesting this type of document.
Suggestions
Add a 'Use when...' clause with trigger terms like 'biosketch', 'NIH grant', 'biographical sketch', 'grant application CV', 'eRA Commons'.
List specific concrete actions such as 'format personal statement, list positions and honors, compile contributions to science, populate training and mentoring sections'.
Include common user-facing synonyms and variations like 'biographical sketch', 'NIH CV', 'grant biosketch', 'NSF biosketch' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (NIH Biosketch) and one action (generate), and mentions compliance with 2022 OMB-approved format, but does not list multiple concrete actions like filling sections, formatting contributions, or managing publications. | 2 / 3 |
Completeness | Describes what it does (generate NIH Biosketch documents) but has no 'Use when...' clause or explicit trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also thin, bringing it to 1. | 1 / 3 |
Trigger Term Quality | Includes 'NIH Biosketch' and '2022 OMB-approved' which are relevant domain terms, but misses common user variations like 'CV', 'grant application', 'biographical sketch', 'NSF biosketch', or 'research profile'. | 2 / 3 |
Distinctiveness Conflict Risk | NIH Biosketch is a very specific document type with a clear niche; it is unlikely to conflict with other skills given the specialized domain of NIH grant biosketches. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template) that add no actionable value for NIH biosketch generation. The domain-specific content (NIH format requirements, JSON schema, PubMed import) is useful but buried among repetitive and generic process descriptions. The workflow lacks NIH-specific validation steps and the document suffers from poor organization with redundant sections and circular internal references.
Suggestions
Remove all generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template, Output Requirements) and focus on NIH-biosketch-specific guidance.
Consolidate the three overlapping workflow/usage sections into a single clear workflow with NIH-specific validation checkpoints (e.g., verify page count ≤5, check font compliance, validate section completeness).
Eliminate redundant sections: merge 'Quick Check' into 'Audit-Ready Commands', remove duplicate 'References' section, resolve contradictions between 'Dependencies' and 'Prerequisites'.
Add a concrete validation step after DOCX generation that checks NIH format compliance (page count, required sections present, font/margin specs) with a fix-and-retry loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. Contains multiple redundant sections (e.g., 'Quick Check' and 'Audit-Ready Commands' repeat the same py_compile command, 'References' appears twice, 'Prerequisites' contradicts 'Dependencies'). Includes boilerplate sections like Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, and Response Template that add little actionable value. Self-referential loops like 'See ## Usage above' and 'See ## Workflow above' waste tokens. Much content explains generic workflow patterns Claude already knows. | 1 / 3 |
Actionability | Provides concrete CLI commands and a complete JSON input schema, which is useful. However, the actual script (scripts/main.py) is not provided or shown, so the commands are not truly executable in isolation. The workflow steps are generic ('Confirm the user objective...') rather than specific to NIH biosketch generation. The JSON example and PubMed import commands are concrete and helpful, but much of the guidance is abstract process description rather than executable instruction. | 2 / 3 |
Workflow Clarity | The workflow section is entirely generic ('Confirm the user objective, required inputs...') with no NIH-biosketch-specific steps. There are no validation checkpoints for the generated DOCX (e.g., checking page count ≤5, font compliance, margin compliance). The 'Example run plan' is a separate partial workflow that doesn't integrate with the main 'Workflow' section. No feedback loops for document validation despite this being a document generation task with strict format requirements. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with 200+ lines in a single file. Many sections are redundant or could be consolidated. References to 'references/' directory and 'references/audit-reference.md' exist but no bundle files are provided, making these dead references. The content is poorly organized with sections appearing in illogical order (e.g., 'Usage' appears after 'Implementation Details' which says 'See ## Workflow above' but Workflow appears below it). Self-referential 'See above' links create confusion. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
73f6514
- Reviewed
Table of Contents
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.