quickgo-database

Query the QuickGO and Evidence & Conclusion Ontology (ECO) REST API. Use this when you need to map genes to biological processes, molecular functions, or cellular components, find genes associated with a specific pathway/GO term, or explore the Gene Ontology hierarchy. Do not use for querying drug targets (use OpenTargets) or mechanistic signaling pathway diagrams (use KEGG).

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/quickgo_database/SKILL.md

Quality

Content

70%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 highly actionable with executable commands and a clean reference structure, but it loses points on conciseness (conceptual intro padding) and workflow clarity (no explicit validation/feedback checkpoints between the chained steps).

Suggestions

Trim the introductory paragraph about QuickGO/GOA being a 'centralised resource' — Claude already knows what Gene Ontology is; lead with the action.

Add explicit validation checkpoints between chained steps (e.g., after resolving a UniProtKB ID, confirm the identifier was found before running the annotation search; after saving output, verify the file is non-empty before parsing).

Optionally add a brief 'verify the result' note (e.g., check the saved JSON has results) to the workflows so error recovery is explicit.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with copy-paste commands, but the intro and the 'It provides a centralised resource...' paragraph restate general concepts about GO/QuickGO that Claude already knows, which could be tightened.	2 / 3
Actionability	Workflows give fully executable `uv run scripts/quickgo_tool.py ...` commands with concrete flags and example IDs, copy-paste ready and consistent with the bundled script.	3 / 3
Workflow Clarity	Multi-step workflows are numbered and sequenced, but there are no validation/verification checkpoints (e.g., confirming the resolved ID before using it, checking output exists/parse error before the next step); per the rubric this caps workflow clarity at 2 for these chained operations.	2 / 3
Progressive Disclosure	The body is a concise overview with four well-signaled, one-level-deep references (e.g., 'See [references/annotations.md](references/annotations.md)') that resolve to real, organized bundle files; navigation is easy and content is appropriately split.	3 / 3
	Total	10 / 12 Passed

Description

82%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.

A strong description: it names concrete capabilities, gives explicit positive and negative triggers, and disambiguates from adjacent skills. Trigger-term naturalness is the only mild weakness, relying on domain vocabulary over everyday phrasings.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'map genes to biological processes, molecular functions, or cellular components, find genes associated with a specific pathway/GO term, or explore the Gene Ontology hierarchy' — matching the 'Lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers 'what' (Query the QuickGO and ECO REST API...) and 'when' ('Use this when you need to map genes...'), with an explicit negative boundary ('Do not use for...'), matching the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	Natural terms like 'genes', 'pathway', and 'GO term' appear, but core user-facing phrases ('Gene Ontology', 'functional annotation', 'gene function') are present only as jargon/specifics; common phrasings a user would actually say are partial, not comprehensive.	2 / 3
Distinctiveness Conflict Risk	The 'Do not use for querying drug targets (use OpenTargets) or mechanistic signaling pathway diagrams (use KEGG)' carve-out gives a clear niche and explicit disambiguation against sibling skills, unlikely to trigger incorrectly.	3 / 3
	Total	11 / 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: google-deepmind/science-skills
Path: skills/quickgo_database/SKILL.md
Commit: 0b42509

Reviewed: 7 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.