open-access-scout

Use when finding open access journals, checking journal policies, or identifying predatory publishers. Helps researchers locate legitimate open access venues and avoid publication scams.

Quality

61%

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/open-access-scout/SKILL.md

Quality

Content

38%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 and references real bundle files, but it is undermined by verbose generic boilerplate and, more seriously, by code and CLI examples that do not match the actual bundled script (scripts/main.py) and would fail on copy-paste. Fixing the executable examples is the highest-leverage improvement.

Suggestions

Replace the fabricated code/CLI examples with the real bundled interface: scripts/main.py exposes OpenAccessScout.search_open_access(doi, title, authors) and CLI flags --doi/--title/--authors/--list-sources, not scripts/oa_scout.py with --search/--max-apc. Update the Quick Start and Core Capabilities examples accordingly so they are copy-paste executable.

Cut the duplicated generic boilerplate (Output Requirements, Output Contract, Failure Handling, User Checkpoints, Quick Validation, Response Template, When Not to Use, Required Inputs) which restates the same fallback/validation ideas repeatedly; consolidate into one concise Error/Fallback section.

Rewrite the 'When to Use' bullet so it does not echo the description verbatim ('Use this skill when the task needs Use when finding...'), and fold the explicit validation commands into the Workflow steps as actual validate-then-proceed checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic, repeated boilerplate (Output Requirements, Output Contract, Failure Handling, User Checkpoints, Quick Validation, Response Template, When Not to Use, Required Inputs) and the 'When to Use' section awkwardly echoes the description verbatim ('Use this skill when the task needs Use when finding...'), so it is noticeably verbose rather than just slightly trimmable.	2 / 5
Actionability	The capability code examples import a non-existent module (scripts.oa_scout) and call methods that do not exist (find_journals, search, assess_journal, compare_apc), and the CLI uses a non-existent file (oa_scout.py) with flags (--search, --max-apc) that the bundled main.py does not support; only the py_compile/--help audit commands are actually executable.	2 / 5
Workflow Clarity	A 5-step Workflow with a fallback step is present alongside separate validation commands, but the checkpoints are generic and disconnected from the numbered sequence rather than integrated as explicit validate-then-proceed gates, so it sits at the 'steps listed, validation gaps' anchor.	3 / 5
Progressive Disclosure	Content is organized into clear sections with a single one-level-deep, verified-real reference (references/audit-reference.md) signaled in a References section; it does not reach 5 because substantial generic boilerplate remains inlined that could be split out or removed.	4 / 5
	Total	11 / 20 Passed

Description

83%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 strong: it pairs an explicit 'Use when...' trigger clause with concrete capability statements and natural domain keywords. It is held below a perfect score only by minor overlap in its listed actions and slight conflict risk with adjacent research skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('finding open access journals, checking journal policies, ... identifying predatory publishers', 'locate legitimate open access venues and avoid publication scams'), but the actions overlap in phrasing rather than being fully comprehensive and distinct, so it sits below the 5 anchor.	4 / 5
Completeness	Explicitly answers both 'when' ('Use when finding open access journals, checking journal policies, or identifying predatory publishers') and 'what' ('locate legitimate open access venues and avoid publication scams') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases researchers actually say ('open access journals', 'journal policies', 'predatory publishers', 'publication scams') with good coverage, but misses common synonyms/extensions like APC, DOAJ, or article-processing charge, placing it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche in OA/predatory publishing with distinct triggers and minimal conflict risk, but could still overlap with general literature-search or citation-management skills, so it does not reach the 'minimal conflict' of the 5 anchor.	4 / 5
	Total	17 / 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: 1 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/open-access-scout/SKILL.md
Commit: 63c61d3

Reviewed: 11 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.