fda-guideline-search

Search FDA industry guidelines by therapeutic area or topic.

Quality

53%

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/Evidence Insight/fda-guideline-search/SKILL.md

Quality

Content

53%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 is well-structured with executable guidance and properly signaled one-level-deep references, but it is padded with generic boilerplate and placeholder cross-references that dilute token efficiency. Workflow sequencing is present but lacks concrete validation feedback loops for the networked operation.

Suggestions

Remove the placeholder 'See `## X` above for related details.' lines and the duplicated audit/quick-check command blocks; consolidate to a single concrete command set.

Cut generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) or move them into a shared reference, keeping only FDA-search-specific guidance inline.

Add an explicit validation checkpoint to the workflow, e.g. verify the JSON output schema and handle rate-limit/empty-result errors with a retry step, since the skill performs batched network downloads.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: placeholder cross-references ('See `## Features` above for related details.') and generic boilerplate (Risk Assessment table, Security Checklist, Evaluation Criteria, Response Template) add tokens without skill-specific value.	2 / 5
Actionability	Concrete executable commands (`python -m py_compile`, `python scripts/main.py --help`, `--area oncology`), a full parameters table, and a JSON output example give mostly copy-paste-ready guidance with only minor gaps (e.g. no download-result example).	4 / 5
Workflow Clarity	A sequenced 5-step workflow exists with a stop-early check and a fallback, but there is no concrete validate→fix→retry checkpoint for the network/download operation, leaving validation implicit.	3 / 5
Progressive Disclosure	References are real, one level deep, and clearly labeled (search-strategy.md, area-mappings.json, fda-api-notes.md) with the script in scripts/; it is not a 5 because generic boilerplate is inlined rather than split out.	4 / 5
	Total	13 / 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 terse: it states the core action without explicit trigger guidance or comprehensive action coverage. It is distinguishable yet would benefit from a 'Use when…' clause and richer trigger terms.

Suggestions

Add an explicit 'Use when…' clause naming concrete user triggers, e.g. 'Use when searching FDA guidance documents by therapeutic area, document type, or year.'

Expand the action list beyond a single 'search' verb to cover the skill's actual capabilities (filter by type/year, download and cache PDFs, search within document content).

Include natural synonyms and concrete artifacts users mention, such as 'FDA guidance documents', 'CDER/CBER guidances', and 'PDF'.

Dimension	Reasoning	Score
Specificity	Names the domain (FDA industry guidelines) and one concrete action (search) with two filter dimensions (therapeutic area, topic), but coverage is not comprehensive — it is a single action rather than multiple specific operations.	3 / 5
Completeness	It clearly answers 'what' (search FDA guidelines by area/topic) but lacks any explicit 'Use when…' trigger clause, so completeness is capped at 3 per the rubric guidance.	3 / 5
Trigger Term Quality	Relevant keywords like 'FDA industry guidelines' and 'therapeutic area' are present, but common variations, synonyms, and file extensions a user might naturally say are missing.	3 / 5
Distinctiveness Conflict Risk	The FDA-guideline niche is clear and distinct with minimal conflict risk; it is not a 5 only because the trigger phrasing could be more specific to fully separate it from general search skills.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/fda-guideline-search/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.