fulltext-fetcher

Fetch and save the original HTML of scientific literature webpages when given a URL, DOI, or PubMed PMID (triggered when you need archival-grade page HTML for downstream parsing or review).

Quality

76%

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/Other/fulltext-fetcher/SKILL.md

Quality

Content

65%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 specific content is executable and well-organized, but the body ships a redundant generic templated half that restates the description and duplicates every section header, costing significant token budget. Removing the boilerplate half would sharply improve conciseness and structure.

Suggestions

Delete the generic templated half (the first 'When to Use'/'Key Features'/'Dependencies'/'Example Usage'/'Implementation Details'/'Validation Shortcut' block, lines 7-55); it duplicates the specific fulltext-fetcher half and restates the description as padding.

Consolidate the two parallel sets of section headers into a single canonical structure so there is one authoritative 'When to Use', 'Dependencies', 'Example Usage', and 'Implementation Details' rather than competing duplicates.

Make the validation feedback loop explicit (e.g., 'if .html files are empty, surface the timeout/retry cause and re-run') rather than leaving recovery steps implied, to lift workflow clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	The body contains an entire generic templated half (When to Use, Key Features, Dependencies, Example Usage, Implementation Details, Validation Shortcut) that duplicates the specific half's section headers and pads with boilerplate like 'Scope-focused workflow aligned to' restating the description, fitting the 'noticeably verbose, several padded sections' anchor.	2 / 5
Actionability	The specific half provides copy-paste-ready, fully executable commands for every input type (--url, --doi, --pmid, batch, --allow-all) plus the --out-dir option, matching the 'fully executable, copy-paste ready, covers common cases' anchor.	5 / 5
Workflow Clarity	There is a clear verification checklist (confirm output dir exists, .html files non-empty, avoid path collisions) and a Recommended Workflow sequence, but the two redundant halves dilute the single authoritative flow and the 'only proceed when valid' feedback loop is implied rather than explicit, so it sits just below the top anchor.	4 / 5
Progressive Disclosure	Structure exists with organized sections and real bundle files (scripts/fulltext_fetcher.py, validate_skill.py) referenced correctly, but the body inlines two parallel copies of the same section taxonomy instead of a single overview pointing one level deep, leaving it 'some structure but could be better organized'.	3 / 5
	Total	14 / 20 Passed

Description

88%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.

A high-quality description that cleanly states what the skill does, its three concrete input types, and an explicit use-when trigger. The only minor gap is a few natural synonyms a user might say instead of URL/DOI/PMID.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('Fetch and save the original HTML') and explicitly enumerates three distinct input types ('URL, DOI, or PubMed PMID'), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	It explicitly answers both 'what' (fetch and save original HTML of scientific literature webpages) and 'when' with a concrete trigger clause ('triggered when you need archival-grade page HTML for downstream parsing or review'), matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural trigger coverage ('URL', 'DOI', 'PubMed PMID', 'scientific literature', 'HTML') but misses a few common synonyms users might say (e.g., 'scrape', 'webpage', 'landing page', '.html'), so it sits just below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined (archival-grade HTML capture of scientific literature via URL/DOI/PMID) with distinct triggers unlikely to collide with other skills, fitting the 'clear niche, minimal conflict risk' anchor.	5 / 5
	Total	19 / 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/Other/fulltext-fetcher/SKILL.md
Commit: 63c61d3

Reviewed: 9 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.