CtrlK
BlogDocsLog inGet started
Tessl Logo

alphafold-database

Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

58

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/alphafold-database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 comprehensive executable examples and good use of a one-level-deep reference file, but it is verbose with redundant concept restatements and lacks explicit validation feedback loops for its batch operations.

Suggestions

Consolidate the pLDDT/PAE threshold tables and version notes into a single section to remove repetition and tighten token usage.

Add an explicit validate->fix->retry feedback loop in the batch processing section (e.g., verify the download succeeded before processing, retry on failure).

Move large secondary examples (BigQuery queries, detailed parsing code) into references/api_reference.md to make the body a leaner overview.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes domain competence, but redundancy is more than minor: pLDDT thresholds are repeated across section 3, the 'Confidence Interpretation Guidelines', and 'Key Concepts', and version information is restated in multiple sections.

3 / 5

Actionability

Provides fully executable, copy-paste-ready code across Biopython, REST API, Google Cloud/BigQuery, parsing, and batch processing with concrete URLs, file formats, and function names covering the common cases.

5 / 5

Workflow Clarity

Content is organized as a capability catalog rather than a sequenced workflow; the batch section has try/except error handling but lacks explicit validate->fix->retry checkpoints, so per the batch-operations guideline workflow clarity is capped at 3.

3 / 5

Progressive Disclosure

A real references/api_reference.md is clearly signaled one level deep with a summary of its contents, and the body is well-sectioned, but the body is long with detailed examples (BigQuery queries, parsing code) that could be split out into references.

4 / 5

Total

15

/

20

Passed

Description

70%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 specific and distinctive, clearly naming AlphaFold DB retrieval with concrete actions and strong domain triggers, but it lacks an explicit 'Use when...' trigger clause and omits a few natural synonyms, capping completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when retrieving AI-predicted protein structures, downloading PDB/mmCIF files, or analyzing AlphaFold confidence metrics.'

Include natural synonyms users may say such as 'protein models', '3D structures', or 'AlphaFold structures' to broaden trigger coverage.

Mention bulk/proteome access briefly (e.g., 'bulk proteome datasets via Google Cloud') to make capability coverage comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Retrieve structures by UniProt ID', 'download PDB/mmCIF files', 'analyze confidence metrics (pLDDT, PAE)') but does not cover bulk/GCP access, leaving minor gaps short of comprehensive (anchor 5).

4 / 5

Completeness

The 'what' is clear (access/retrieve/download/analyze), but 'when' is only weakly implied via 'for drug discovery and structural biology' with no explicit 'Use when...' trigger clause, so completeness is capped at 3 per the guideline.

3 / 5

Trigger Term Quality

Good domain keyword coverage with natural terms and file formats ('protein structures', 'UniProt ID', 'PDB/mmCIF', 'pLDDT', 'PAE', 'drug discovery'), but missing common synonyms like 'protein models', '3D structures', or 'AlphaFold structures'.

4 / 5

Distinctiveness Conflict Risk

'Access AlphaFold 200M+ AI-predicted protein structures' names a clear niche with AlphaFold-specific triggers (UniProt ID, pLDDT, PAE) and minimal conflict risk against related protein skills.

5 / 5

Total

16

/

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

skill_md_line_count

SKILL.md is long (519 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
synthetic-sciences/openscience
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.