CtrlK
BlogDocsLog inGet started
Tessl Logo

chembl-database

Query ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.

64

Quality

77%

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/chembl-database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A highly actionable, well-structured skill with verified one-level references, but it carries minor boilerplate padding and omits validation checkpoints in its batch query workflows.

Suggestions

Reduce repeated new_client endpoint setup across examples by introducing it once and referencing it, to tighten token usage.

Add validation checkpoints to the workflows (e.g., checking for empty results, handling API errors/timeouts, and noting pagination limits before iterating).

Integrate the rate-limiting and data-reliability notes into the workflow steps where they matter rather than listing them separately.

DimensionReasoningScore

Conciseness

Mostly efficient with compact code blocks and no explanation of basic concepts, but repeated new_client boilerplate across every example and overview statistics that Claude largely knows could be tightened, so it sits at 2 rather than 3.

2 / 3

Actionability

Provides fully executable, copy-paste-ready code with specific endpoints, filter operators, and concrete parameter values throughout the core capabilities and workflows.

3 / 3

Workflow Clarity

Three numbered workflows give clear sequences, but batch/remote-query operations lack validation checkpoints (empty-result, API-error, pagination handling); per the guidelines missing validation in batch operations caps workflow clarity at 2.

2 / 3

Progressive Disclosure

The body is an overview that signals two real one-level-deep bundle files (scripts/example_queries.py and references/api_reference.md, both present) with clear function/section listings, matching the well-signaled one-level-deep reference anchor.

3 / 3

Total

10

/

12

Passed

Description

82%

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 specific, distinctive description with strong action verbs and natural domain trigger terms, but it lacks an explicit 'Use when...' clause so it does not fully state when Claude should invoke the skill.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when searching ChEMBL for bioactive molecules, IC50/Ki activity data, inhibitors, or SAR studies in drug discovery.'

Confirm the trigger phrasing covers common user phrasings like 'find inhibitors' or 'look up a drug's activity' to lift completeness to 3.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as 'Search compounds by structure/properties', 'retrieve bioactivity data (IC50, Ki)', 'find inhibitors', and 'perform SAR studies', matching the multiple-specific-actions anchor rather than the partial-actions anchor at 2.

3 / 3

Completeness

Clearly answers what the skill does but omits an explicit 'Use when...' trigger clause; per the judging guidelines a missing explicit trigger caps completeness at 2 rather than 3.

2 / 3

Trigger Term Quality

Uses natural domain terms a user would say — 'inhibitors', 'IC50', 'Ki', 'SAR studies', 'medicinal chemistry', 'drug discovery' — giving good coverage without leaving out common variations.

3 / 3

Distinctiveness Conflict Risk

Targets a clearly distinct niche (ChEMBL bioactive molecules / drug discovery) with specialized triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

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.