CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

meta-search-builder

Medical literature search strategy generator. Given a user's natural-language description (e.g., meta-analysis topic, PICOS elements, research question), automatically extract medical entities (disease, intervention, population, outcomes) and generate professional search queries for seven major databases (PubMed, Cochrane, Embase, Web of Science, CNKI, Wanfang, VIP). Useful for developing search strategies for systematic reviews and meta-analyses.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/meta-search-builder/SKILL.md
SKILL.md
Quality
Evals
Security

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 skill's real workflow — PICOS extraction rules, a complete seven-database output template, and a well-integrated one-level-deep reference with executable syntax and examples — is genuinely actionable. However, the body is heavily padded with generic template boilerplate and generator artifacts that consume tokens without adding guidance, and the validation/checkpoint sections are vacuous rather than substantive.

Suggestions

Delete the boilerplate sections ('When to Use', 'Key Features', 'Dependencies', 'Example Usage', 'Implementation Details', 'Quick Validation') or replace them with a few skill-specific lines; remove generator artifacts like the 'Skill directory: 20260316/…' block.

Fix the broken cross-reference 'See `## Workflow` above for related details' (Workflow appears below Implementation Details) and reorder so the overview points forward to the real steps.

Add a concrete validation checkpoint, e.g., verify each generated query against the syntax rules in references/databases.md (field tags, quote style, boolean grouping) before returning output, ideally with a small worked example in the body.

DimensionReasoningScore

Conciseness

Roughly half the body is generic template filler: 'Use this skill when the request matches its documented task boundary', 'Key Features' repeating the description verbatim, 'Example Usage' leaking generator artifacts ('Skill directory: 20260316/scientific-skills/Others/meta-search-builder', 'No packaged executable script was detected'), and boilerplate 'Implementation Details'. Not 1 because the Workflow section itself is lean and every token there earns its place.

2 / 5

Actionability

The core guidance is concrete and executable: PICOS extraction rules ('Limit the number of keywords to at most 5', "Simplify descriptive phrases (e.g., 'patients with ovarian cancer' -> 'ovarian cancer')"), a complete output-format template for all seven databases, and a clearly signaled pointer to references/databases.md for real syntax and examples. Below 5 because there is no worked end-to-end example in the body and 'See `## Workflow` above' points the wrong direction (Workflow is below that section).

4 / 5

Workflow Clarity

The two-step sequence (extract PICOS entities, then generate per-database strategies with a defined output format) is clear, but checkpoints are vacuous or implicit: 'Quick Validation' states 'No local script validation step is required for this skill' and the validation sections are generic boilerplate with no step verifying that generated queries follow each database's syntax.

3 / 5

Progressive Disclosure

Scored against the actual bundle: one reference file (references/databases.md), substantive, clearly signaled at the point of need ('See [references/databases.md](references/databases.md) for database-specific syntax and examples'), exactly one level deep. Below 5 because the body's padded boilerplate sections and one broken internal cross-reference dilute navigation.

4 / 5

Total

13

/

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.

A strong description that clearly states what the skill does with enumerated specifics (entities, seven named databases) and an explicit applicability clause. The main gap is that the trigger guidance is a soft 'Useful for…' statement rather than a concrete 'Use when…' phrase, and a few natural synonyms (e.g., 'literature search', 'evidence synthesis') are absent.

Suggestions

Convert 'Useful for developing search strategies for systematic reviews and meta-analyses' into an explicit trigger clause, e.g., 'Use when the user is planning a systematic review or meta-analysis and needs database search strategies, or mentions PICOS, PubMed, Cochrane, or Embase'.

Add natural synonyms users would actually say — 'literature search', 'search strategy', 'evidence synthesis' — to broaden trigger coverage.

Optionally state when NOT to use it (e.g., not for single-database quick PubMed lookups) to further sharpen distinctiveness.

DimensionReasoningScore

Specificity

The description lists multiple concrete, comprehensive actions — 'extract medical entities (disease, intervention, population, outcomes)' and 'generate professional search queries for seven major databases (PubMed, Cochrane, Embase, Web of Science, CNKI, Wanfang, VIP)' — in third-person voice, matching the anchor-5 example's structure.

5 / 5

Completeness

The 'what' is explicit and concrete, and the 'when' is present via 'Useful for developing search strategies for systematic reviews and meta-analyses' — an explicit applicability clause, though not an imperative 'Use when…' trigger with concrete trigger phrases, which keeps it below 5.

4 / 5

Trigger Term Quality

Good natural keyword coverage: 'meta-analysis topic, PICOS elements, research question', 'systematic reviews and meta-analyses', and all seven database names. Falls short of 5 because common variations users would say — 'literature search', 'evidence synthesis', 'build a search strategy' — are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche (search strategy generation for medical systematic reviews/meta-analyses, including Chinese databases CNKI, Wanfang, VIP) with distinct trigger terms and minimal overlap with any generic search or document skill.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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/Other/meta-search-builder/SKILL.md

Reviewed

Table of Contents

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.