CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pytdc

Therapeutics Data Commons (PyTDC) for AI-ready therapeutic ML datasets and benchmarks; use it when you need standardized dataset loading, meaningful splits (e.g., scaffold/cold-start), and consistent evaluation for ADME/Toxicity/DTI/DDI or molecular optimization.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/pytdc/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A well-structured, highly actionable skill body with a complete runnable example and real, well-organized bundle references. Its weaknesses are redundant code patterns duplicated between Example Usage and Implementation Details, and references listed centrally rather than at their point of use.

Suggestions

Deduplicate the get_split/Evaluator/Oracle patterns: keep one canonical example and have Implementation Details reference it instead of restating near-identical code blocks.

Link reference files at point of use — e.g., point to references/utilities.md from the Splitting Strategies section and references/datasets.md from the Dataset Access Pattern section — rather than only in the flat 'Related references and templates' list.

Add lightweight verification checkpoints to the example workflow, such as asserting expected split sizes or confirming a dataset name exists before training, and drop the hedge 'if present in this skill package' since the files are bundled.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and stays on TDC-specific material, but the Example Usage script and Implementation Details repeat the same patterns — get_split(method="scaffold", seed=..., frac=[0.7, 0.1, 0.2]) appears twice, and Evaluator and Oracle usage each appear in both the example and later sections — so it could be meaningfully tightened. Not a 2 because there is no padded prose or generic filler; not a 4-5 because the duplicated code blocks are unnecessary tokens.

3 / 5

Actionability

The body provides a complete, copy-paste runnable five-step example (load ADME dataset, scaffold split, train baseline, evaluate with Evaluator, query Oracle) plus concrete install commands and specific API patterns like 'from tdc.single_pred import ADME' and get_split parameters. The '<problem>/<Task>' template in Implementation Details is placeholder-style, but the fully executable example covers the common cases.

5 / 5

Workflow Clarity

The Example Usage section lays out a clear numbered 1-5 sequence (load → split → train → evaluate → oracle) and the Implementation Details sections are well-ordered. This is not a destructive or batch-operation skill, so the validation cap does not apply, but there are no explicit verification checkpoints (e.g., checking split sizes or dataset availability), keeping it at 4 rather than 5.

4 / 5

Progressive Disclosure

The bundle structure matches the body: all six referenced files (references/oracles.md, references/utilities.md, references/datasets.md, and three scripts/) exist, are one level deep, and are listed in a dedicated section with inline pointers (e.g., oracles.md referenced from the Oracles section). Minor gaps keep it from 5: references are presented mostly as a flat list rather than at point of use — utilities.md is never linked from the splitting section where it is most relevant, and the list itself hedges with 'if present in this skill package'.

4 / 5

Total

16

/

20

Passed

Description

73%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.

A strong, niche-targeted description with an explicit 'use when' clause and concrete domain capabilities. Its main weaknesses are the second-person phrasing ('use it when you need') and a 'what' stated as an identification rather than explicit actions.

Suggestions

Rewrite in third person to remove the second-person trigger phrasing, e.g., 'Provides standardized loading of therapeutic ML datasets... Use when working with ADME/Toxicity/DTI/DDI datasets, scaffold or cold-start splits, or molecular optimization.'

Lead with action verbs for the 'what' (e.g., 'Loads curated drug-discovery datasets, generates scaffold/cold-start splits, and evaluates models with unified metrics') to sharpen specificity and completeness.

Add a few natural synonyms users might say, such as 'drug discovery', 'bioactivity', or 'benchmarking ML models' to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain and several concrete capabilities ('standardized dataset loading', 'meaningful splits (e.g., scaffold/cold-start)', 'consistent evaluation for ADME/Toxicity/DTI/DDI'), which is a base 4; however 'use it when you need' is second-person voice, so the voice guideline applies a 1-point penalty, landing at 3.

3 / 5

Completeness

Both 'what' ('Therapeutics Data Commons (PyTDC) for AI-ready therapeutic ML datasets and benchmarks') and an explicit 'when' ('use it when you need standardized dataset loading, meaningful splits...') are present. The 'what' is a noun-phrase identification rather than the explicit action statement seen in the 5 anchor, so it sits at 4 rather than 5; it is clearly above 3 because the trigger clause is explicit, not implied.

4 / 5

Trigger Term Quality

Good coverage of natural domain terms a drug-discovery ML user would say — 'scaffold', 'cold-start', 'ADME', 'Toxicity', 'DTI/DDI', 'molecular optimization', 'PyTDC' — but misses common synonyms like 'drug discovery', 'bioactivity', or 'benchmark a model'. Not clearly matching the comprehensive-synonyms anchor at 5, and well above the sparse keyword levels of 2-3.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche (therapeutic ML datasets/benchmarks) with distinct triggers like 'PyTDC', 'ADME/Toxicity/DTI/DDI', and 'scaffold/cold-start' splits that virtually no other skill would claim, so conflict risk is minimal.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Evidence Insight/pytdc/SKILL.md

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.