ncbi-blast-skill

Submit, poll, and summarize NCBI BLAST Common URL API jobs (Blast.cgi) for nucleotide or protein sequences. Use when a user wants RID status, BLAST results, or compact top-hit summaries; fetch raw Text/JSON2 only on request.

Quality

93%

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

Quality

Content

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a concise, highly actionable overview that correctly defers detail to the bundled script and references, with a runnable example and precise input/output contract. Its only gap is the absence of an explicit retry/validation checkpoint for the polling workflow.

Suggestions

Add an explicit feedback-loop step for polling: e.g., 'If status is WAITING, wait >=60s and re-poll; if FAILED or UNKNOWN, surface the error and stop rather than retrying blindly.'

Surface a brief validation checkpoint after fetch (e.g., check has_hits / query_count_returned before summarizing) so error recovery is visible in the SKILL.md workflow rather than only inside the script.

Dimension	Reasoning	Score
Conciseness	Lean bullet-structured body that assumes Claude's competence, states only non-obvious defaults and rules, and avoids explaining BLAST concepts; not 2 because there is no padding or unnecessary explanation to tighten.	3 / 3
Actionability	Provides the concrete executable command 'python scripts/ncbi_blast.py' plus a complete copy-paste bash example and exact field defaults, matching the copy-paste-ready anchor; not 2 because the guidance is complete rather than pseudocode.	3 / 3
Workflow Clarity	The submit/poll/fetch sequence is present via the action enum with rate-limit guardrails and explicit failure fields, but there is no surfaced validate->fix->retry feedback loop for this batch/remote operation, which caps workflow clarity at 2 per the rubric's feedback-loop note; not 1 because steps are clearly sequenced.	2 / 3
Progressive Disclosure	Body is an overview that delegates concrete work to scripts/ncbi_blast.py and signals two real one-level-deep reference files with explicit load guidance ('Load ... only for parameter details', 'Do not load ... during normal skill execution'); not 2 because navigation is clear and references are shallow.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, third-person, and explicitly pairs capabilities with a natural 'Use when' trigger, covering both what the skill does and when to invoke it. It is concise yet comprehensive with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Submit, poll, and summarize', 'wants RID status, BLAST results, or compact top-hit summaries', 'fetch raw Text/JSON2'), matching the anchor for listing multiple specific concrete actions; not 2 because the action set is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both what ('Submit, poll, and summarize NCBI BLAST Common URL API jobs') and when ('Use when a user wants RID status, BLAST results, or compact top-hit summaries'), with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Includes natural user-facing terms ('RID status', 'BLAST results', 'top-hit summaries', 'nucleotide or protein sequences') that a user would actually say; not 2 because it covers common phrasings rather than only a single keyword.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (NCBI BLAST Common URL API, RID/results workflow) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/life-science-research/skills/ncbi-blast-skill/SKILL.md
Commit: 11c74d6

Reviewed: 17 days 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.