Tessl • The management layer for AI agent skills

SkillPublic

uniprot-database

Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).

Quality

88%

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

82%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 content is highly actionable with executable commands for every tool mode and useful workflow/checklist structure. Its main weaknesses are a broken id_mapping reference path and some redundancy around the stream/--limit caveat across multiple sections.

Suggestions

Fix the broken reference: the body cites `references/id_mapping_documentation.md` (lines 86 and 286) but the actual file is `references/id_mapping_databases.md` — update both link paths so navigation resolves.

State the `stream`/`--limit` caveat once in Available Tools and reference back to it; it is currently repeated in Bulk Retrieval Priorities and twice in Common Mistakes.

Embed per-step verification into the Typical Protein Research Workflow checklist (e.g., 'verify reviewed-entry count via `count` before retrieval') so the main workflow carries explicit checkpoints like the search-miss workflow does.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and does not re-explain basic concepts, but the `stream`/`--limit` caveat recurs in Available Tools, Bulk Retrieval Priorities, and twice in Common Mistakes, and several Common Mistakes bullets are duplicative — minor trimming opportunities keep it just below 5.	4 / 5
Actionability	Example Commands give copy-paste `uv run scripts/uniprot_tools.py ...` invocations for every mode (count, search, get, stream, map, sparql, unisave), and the SPARQL query patterns and REST syntax examples are complete and executable, covering the common cases.	5 / 5
Workflow Clarity	A 5-step research checklist, a numbered search-miss fallback loop, and an explicit count-before-bulk validation checkpoint are all present, so the batch-operation cap is avoided; the main workflow checklist itself lacks per-step verification hooks, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Structure is well organized with one-level-deep references to search_query_fields.md and sparql_examples.md, but the body cites `references/id_mapping_documentation.md` (lines 86 and 286) while the actual bundle file is `references/id_mapping_databases.md` — a broken navigation path that prevents a 5.	4 / 5
	Total	17 / 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: concrete actions, explicit use-when triggers, and a clear negative-scope boundary that disambiguates it from sequence-similarity skills. The only minor gap is trigger-term breadth, where a few natural synonyms would push it from good to comprehensive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Access protein metadata, function, taxonomy, and sequences', 'searching for proteins, mapping identifiers', 'retrieving functional annotations and publications' — giving comprehensive coverage rather than vague domain naming.	5 / 5
Completeness	Explicitly answers both 'what' (access metadata/function/taxonomy/sequences across UniProtKB, UniParc, UniRef) and 'when' ('Use when searching for proteins, mapping identifiers...'), with concrete trigger phrases and a negative-scope boundary.	5 / 5
Trigger Term Quality	Natural phrases a user would say are present ('searching for proteins', 'mapping identifiers', 'functional annotations'), but coverage is good rather than comprehensive — common synonyms or extension cues (e.g., 'protein lookup', accession/.fasta mentions) are missing.	4 / 5
Distinctiveness Conflict Risk	Clear UniProt niche with distinct triggers and an explicit carve-out ('Don't use for sequence alignment, protein folding, or sequence similarity search') that minimizes conflict with adjacent skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: google-deepmind/science-skills
Path: skills/uniprot_database/SKILL.md
Revision: 4de6786

Reviewed: 1 month ago

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.

uniprot-database

Table of Contents

Is this your skill?