CtrlK
BlogDocsLog inGet started
Tessl Logo

pubmed-search

Search and analyze biomedical literature from PubMed using the free E-utilities API. Use when researching medical topics, discovering clinical papers, fetching article metadata by PMID, performing deep paper analysis, or downloading open-access PDFs from PubMed Central. Triggers: pubmed search, search biomedical literature, find medical papers, PMID lookup, pubmed metadata, clinical literature search, biomedical research, life sciences papers, PMC download, ncbi search.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable with a clear, validated workflow and proper use of progressive disclosure for setup detail. Its main weaknesses are systematic repetition of the MCP-first and rate-limit directives across four sections each, and a References entry pointing to a nonexistent requirements.txt file.

Suggestions

State the MCP-first rule once (e.g., in Workflow step 1) and remove the duplicate exhortations from When Not to Use, the Recommended MCP Server intro, Mindset #2, and the "NEVER skip the MCP availability check" anti-pattern, which restate the same directive.

Consolidate rate-limit guidance into Workflow step 4 and drop the duplicated phrasing in Mindset #1 and the tight-loop anti-pattern, or vice versa.

Fix the References section: either add the missing requirements.txt to the bundle or remove the "Dependencies: requirements.txt" entry, since the link does not resolve.

DimensionReasoningScore

Conciseness

The body is operational throughout with no conceptual padding, but the same directives are repeated three to four times each: MCP-first appears in "When Not to Use", "Recommended MCP Server", "Mindset #2", Workflow step 1, and its own anti-pattern, while rate-limit handling appears in Mindset #1, Workflow step 4, and an anti-pattern. This fits the 3 anchor (mostly efficient, some tightening possible); it is not 2 because every section carries actionable content, and not 4 because the repetition is systematic rather than a minor instance.

3 / 5

Actionability

Copy-paste-ready commands cover every subcommand (search, metadata, analyze, download, JSON export) plus a concrete recovery command ("sleep 30 && ./scripts/pubmed_search.py search...") and a complete MCP config JSON. Fully executable and covering the common cases, matching the 5 anchor.

5 / 5

Workflow Clarity

A clearly numbered 5-step sequence (MCP check → setup → search → handle 429 → present candidates) with explicit validation checkpoints: wait-30s-retry-once error recovery for rate limits, PMC availability check before download, and a mandatory user-confirmation gate before triage. Feedback loops and checkpoints are explicit, matching the 5 anchor.

5 / 5

Progressive Disclosure

Good structure with a genuine one-level-deep reference split — setup detail correctly lives in references/setup-and-troubleshooting.md (which exists) and is clearly signaled from both Workflow and References sections. It falls short of 5 because the References section cites "requirements.txt", which does not exist in the bundle, a broken reference; it stays above 3 because the content split itself is appropriate and navigation is easy.

4 / 5

Total

17

/

20

Passed

Description

100%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 a model example: concrete capabilities in third-person voice, an explicit "Use when" clause, and a rich trigger list with synonyms spanning PubMed, PMC, NCBI, and PMID terminology. It scores at the top anchor on every dimension.

DimensionReasoningScore

Specificity

The description names the domain and multiple concrete, distinct capabilities — "fetching article metadata by PMID", "performing deep paper analysis", "downloading open-access PDFs from PubMed Central" — comprehensively covering the skill's subcommands. This matches the 5 anchor (multiple specific concrete actions, comprehensive coverage); it exceeds 4 because coverage has no meaningful gaps.

5 / 5

Completeness

Both what ("Search and analyze biomedical literature from PubMed using the free E-utilities API") and when ("Use when researching medical topics, discovering clinical papers, fetching article metadata by PMID...") are explicitly answered with concrete trigger phrases. Clearly matches the 5 anchor rather than 4, where the when-clause would be less explicit.

5 / 5

Trigger Term Quality

The trigger list covers natural phrases and synonyms across the domain: "pubmed search", "find medical papers", "PMID lookup", "pubmed metadata", "clinical literature search", "PMC download", "ncbi search". Matches the 5 anchor (comprehensive natural terms including synonyms); 4 would require noticeable missing terms, which is not the case.

5 / 5

Distinctiveness Conflict Risk

A clear niche (PubMed/NCBI/PMC) with distinct tool-specific triggers like "PMID lookup", "pubmed metadata", and "PMC download" that no general literature skill would claim. Minimal conflict risk fits the 5 anchor; only "biomedical research" is mildly broad, which is not enough to drop to 4's "minor overlap risk" framing.

5 / 5

Total

20

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

13

/

16

Passed

Repository
pantheon-org/tekhne
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.