CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

94%

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

93%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 a model of token-efficient skill authoring: an operational contract (input schema, output schema, defaults, rate limits, error fields), a runnable example, and well-signaled one-level references verified against the actual bundle. The only gap is that the submit→poll→fetch sequence and failure-retry behavior are implied by the action definitions rather than stated as an explicit ordered workflow.

DimensionReasoningScore

Conciseness

The body is entirely operational bullets — "Honor NCBI limits: `>=10s` between requests and `>=60s` between polls for the same RID" — with no explanation of what BLAST is or how the API works conceptually. Every line teaches the model something it could not infer, matching the lean/efficient anchor; there is no padding to trim as in the 4-anchor.

5 / 5

Actionability

It provides a copy-paste-ready command ("echo '{"action":"run",...}' | python scripts/ncbi_blast.py"), the complete stdin JSON contract including all actions ("`action` must be one of `submit`, `status`, `fetch`, or `run`"), every default ("`max_hits` defaults to `5`"), and the exact output/error fields. This is fully executable guidance covering the common cases, matching the 5-anchor rather than the minor-gaps 4-anchor.

5 / 5

Workflow Clarity

The submit→poll(status)→fetch flow is unambiguous and includes real checkpoints: rate-limit guards, RTOE handling, status normalization, and "Failures return `ok=false`, `error.code`, `error.message`" for error recovery. However, the sequence is implied by the action definitions rather than given as an explicit ordered workflow with retry/backoff on failure, which keeps it at "clear sequence with most checkpoints; minor validation gaps" rather than the explicit feedback-loop structure of the 5-anchor. No destructive/batch cap applies since BLAST submissions are non-destructive.

4 / 5

Progressive Disclosure

The body is an overview that delegates cleanly: "Load `references/blast-common-url-api.txt` only for parameter details or uncommon BLAST options" and "Do not load `references/intent-notes.txt` during normal skill execution", and both files plus `scripts/ncbi_blast.py` and its test exist in the bundle. References are one level deep, well signaled with explicit load conditions, and the parameter/API detail genuinely lives in the reference file rather than being inlined — matching the clear-overview anchor exactly.

5 / 5

Total

19

/

20

Passed

Description

92%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 states concrete third-person capabilities, an explicit and specific "Use when" trigger clause, and a clearly delimited niche. The only weakness is that the trigger list omits common natural synonyms such as "sequence similarity search" or "alignment".

DimensionReasoningScore

Specificity

"Submit, poll, and summarize NCBI BLAST Common URL API jobs (Blast.cgi) for nucleotide or protein sequences" lists multiple specific concrete actions (submit, poll, summarize) with domain qualifiers and format details ("raw Text/JSON2", "compact top-hit summaries"), matching the comprehensive-coverage anchor. It uses third person and goes beyond the 4-anchor by covering the raw-fetch behavior too, so it is not a minor-gap case.

5 / 5

Completeness

Both parts are explicit: the "what" is "Submit, poll, and summarize NCBI BLAST Common URL API jobs" and the "when" is the concrete "Use when a user wants RID status, BLAST results, or compact top-hit summaries" clause. This matches the 5-anchor exactly (clear what AND when with concrete trigger phrases), unlike the 4-anchor where the when is present but less specific.

5 / 5

Trigger Term Quality

"Use when a user wants RID status, BLAST results, or compact top-hit summaries" gives good natural keyword coverage ("BLAST results", "top-hit summaries", "RID status"), but common phrasings users would say like "sequence similarity search", "sequence alignment", or "homolog search" are missing. It is above the 3-anchor (relevant keywords present, not just domain jargon) but short of the synonym-and-extension comprehensiveness of the 5-anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is unambiguous ("NCBI BLAST Common URL API jobs (Blast.cgi)") with distinct triggers tied to BLAST-specific artifacts (RID, top-hit summaries), so overlap with generic search or bioinformatics skills is minimal. It clearly satisfies the clear-niche/distinct-trigger anchor rather than merely being "mostly distinct" as in the 4-anchor.

5 / 5

Total

19

/

20

Passed

Validation

100%

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
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.