reference-search

Multi-database literature search and search-strategy design that outputs structured, reproducible result lists; use when you need reference retrieval, systematic searching, review topic selection, or to construct a traceable search strategy.

Quality

68%

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/reference-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 content is actionable with concrete commands, config, and example output, and it points cleanly to one-level-deep bundle files. Its main weakness is a duplicated generic boilerplate block that hurts token efficiency, plus missing validation checkpoints in the batch search workflow.

Suggestions

Remove the generic template block at lines 11-54 (the duplicated 'When to Use / Key Features / Dependencies / Example Usage / Implementation Details' sections) since the numbered sections 1-5 already cover the same ground more concretely.

Add an explicit validation/feedback checkpoint to the search workflow (e.g., verify result counts against expectations and retry/adjust the query if empty or off-scope) so the batch search/export process can score above 3 on workflow clarity.

Remove or create the referenced tests/test_pubmed_search.py file so all referenced bundle paths resolve to real files.

Dimension	Reasoning	Score
Conciseness	The body duplicates an entire generic template block ('When to Use', 'Key Features', 'Dependencies', 'Example Usage', 'Implementation Details' at lines 11-54) that restates the numbered sections 1-5 below it, adding boilerplate padding like 'use this skill when a evidence insight task needs a packaged method instead of ad-hoc freeform output'.	2 / 5
Actionability	Provides concrete executable commands ('python scripts/pubmed_search.py'), a copy-paste CONFIG block with real keys, and a realistic JSON output example; minor gap is that EMAIL must be supplied by the user so it is not runnable verbatim.	4 / 5
Workflow Clarity	A clear four-step search workflow is present (Define → Design → Execute → Record), but there are no explicit validation/feedback checkpoints, and the rubric caps batch search/export workflows without validation at 3.	3 / 5
Progressive Disclosure	References are one level deep and clearly signaled (references/guide.md, references/evaluation-checklist.md, assets templates, scripts/pubmed_search.py), with good section structure; minor gaps are the duplicated section blocks and a dangling reference to tests/test_pubmed_search.py which is not present in the bundle.	4 / 5
	Total	13 / 20 Passed

Description

82%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, clearly answering both 'what' and 'when' with concrete, natural trigger phrases and a distinct niche. The only notable issue is the second-person 'use when you need' phrasing, which costs it a specificity point under the rubric.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('literature search', 'search-strategy design', 'outputs structured, reproducible result lists'), which is a solid 4, but the second-person phrasing 'use when you need' triggers the -1 specificity penalty per the judging guidelines.	3 / 5
Completeness	Explicitly states both what it does ('Multi-database literature search and search-strategy design that outputs structured, reproducible result lists') and when to use it with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('reference retrieval', 'systematic searching', 'review topic selection', 'traceable search strategy') users would say, though common synonyms like 'PubMed' or 'lit review' are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (reproducible literature search / search-strategy construction) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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/reference-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.