grant-funding-scout

NIH funding trend analysis to identify high-priority research areas.

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/grant-funding-scout/SKILL.md

Quality

Content

48%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 content has a clear, checkpointed workflow and a well-signaled reference file, but it is bloated with redundant sections and a Parameters table that does not match the packaged script. Tightening the body and correcting the documented interface would materially raise quality.

Suggestions

Correct the Parameters table to match the actual script flags (--area/-a, --trends/-t, --output/-o) so the documented usage is executable.

Consolidate the redundant Quick Check, Audit-Ready Commands, and Example Usage sections into a single verification block.

Move governance boilerplate (Security Checklist, Lifecycle Status, Evaluation Criteria, Risk Assessment) into a separate audit reference file to reduce SKILL.md bloat.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with several redundant sections — Quick Check, Audit-Ready Commands, and Example Usage all repeat 'python -m py_compile scripts/main.py', and the scope is restated across When to Use, Key Features, Implementation Details, and Input Validation.	2 / 5
Actionability	It gives concrete executable commands (py_compile, --help), but the Parameters table documents flags (--research-area, --years, --format, --top-n) that do not match the actual main.py interface (--area, --trends, --output), leaving key usage guidance incomplete.	3 / 5
Workflow Clarity	A clear 5-step sequence is present with explicit checkpoints: an early scope-validation stop (step 2), a pre-execution py_compile check, and a documented fallback path (step 5 plus the Error Handling section).	4 / 5
Progressive Disclosure	The single reference (references/audit-reference.md) is real and clearly signaled one level deep, but substantial non-core boilerplate (Security Checklist, Lifecycle Status, Evaluation Criteria, Risk Assessment) is inlined that could be split into separate files.	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 is clear and domain-specific but one-sided: it answers 'what' well while omitting any 'when to use it' guidance. Adding a 'Use when...' clause with natural trigger phrases would lift completeness and trigger_term_quality simultaneously.

Suggestions

Append an explicit trigger clause, e.g. 'Use when analyzing NIH funding trends, identifying hot research areas, or positioning grant proposals.'

Add concrete action verbs beyond 'identify' (e.g., 'ranks', 'compares', 'surfaces emerging topics') to improve specificity.

Include natural synonyms users might say ('grant trends', 'funding opportunities', 'NIH RePORTER') for better trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('identify high-priority research areas') but lists no other actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action score 4.	3 / 5
Completeness	It states clearly what the skill does but has no 'Use when...' clause or equivalent trigger, so per the guidelines completeness is capped at 3 rather than reaching the explicit what-and-when score of 4-5.	3 / 5
Trigger Term Quality	Relevant terms like 'NIH funding' and 'funding trend analysis' appear, but common variations and synonyms are missing, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The NIH funding-trend niche is specific and unlikely to trigger the wrong skill, but the absence of explicit trigger phrases keeps it just below the score-5 'distinct triggers' anchor.	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/Evidence Insight/grant-funding-scout/SKILL.md
Commit: 63c61d3

Reviewed: 8 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.