ctd-api

Accesses Comparative Toxicogenomics Database (CTD) for chemical, gene, disease, and pathway interaction data. Invoke when user needs to query CTD, retrieve toxicogenomics data, or investigate chemical-disease relationships.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/ctd-api/SKILL.md

Quality

Content

53%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 delivers concrete, executable CTD guidance with a real script and a well-placed reference file, but it is weighed down by extensive generic boilerplate sections and templated, non-specific workflow/validation checkpoints. Tightening the padding and making validation steps concrete would lift the weakest dimensions.

Suggestions

Remove or condense the generic boilerplate sections ('When to Use', 'When Not to Use', 'Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') that restate template guidance unrelated to CTD, and drop the 'Key Features' block that merely echoes the description.

Replace the abstract 'Recommended Workflow' and 'Quick Validation' checkpoints with concrete CTD-specific validation, e.g. verify the inputType/report combination against references/ctd_api_docs.md and check the returned JSON for the expected report fields before returning the result.

Add one or two more executable examples covering other inputTypes (e.g. disease and pathway queries) so the common cases are copy-paste ready without consulting the reference file.

Dimension	Reasoning	Score
Conciseness	The body carries several generic padded sections ('When to Use', 'When Not to Use', 'Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Quick Validation', 'Recommended Workflow') plus a 'Key Features' block that restates the description verbatim, all of which add little CTD-specific value. Not a 3 because the volume of templated boilerplate goes beyond minor tightening; not a 1 because the CTD-specific sections (parameters, direct links, examples) are not concept explanations Claude already knows.	2 / 5
Actionability	Copy-paste-ready commands like 'python scripts/query_ctd.py --inputType chem --inputTerms "Mercury" --report genes_curated --format json', a documented parameter table, and direct-link URL templates give mostly executable guidance backed by a real script. Not a 5 because valid inputType/report combinations live only in the reference file and only two concrete examples are shown, leaving minor gaps.	4 / 5
Workflow Clarity	A 'Recommended Workflow' sequence and a 'Quick Validation' (--help) step are present, but the checkpoints are generic ('Validate the request against the skill boundary', 'Run a final validation pass') rather than concrete verification of inputs or API results. Not a 4 because the validation checkpoints are implicit/templated rather than explicit and specific; not a 2 because a real sequenced workflow with a validation step does exist.	3 / 5
Progressive Disclosure	The detailed valid-combination table is correctly placed in references/ctd_api_docs.md (a real, one-level-deep, clearly signaled file) and scripts/query_ctd.py exists as referenced, giving good structure. Not a 5 because the SKILL.md itself still inlines considerable generic content that could be trimmed for cleaner navigation.	4 / 5
	Total	13 / 20 Passed

Description

82%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: it clearly states what the skill does and when to invoke it with concrete, natural trigger phrases tied to a distinct domain. Its only weakness is a single accessor action verb rather than a list of several specific operations.

Dimension	Reasoning	Score
Specificity	Quotes 'Accesses Comparative Toxicogenomics Database (CTD) for chemical, gene, disease, and pathway interaction data' name the domain and a concrete action plus data categories, but only one action verb ('Accesses') keeps it from being comprehensive. Not a 4 because it does not list several distinct actions, only one accessor action with enumerated data types.	3 / 5
Completeness	It explicitly answers both 'what' ('Accesses CTD for ... interaction data') and 'when' with concrete trigger phrases ('Invoke when user needs to query CTD, retrieve toxicogenomics data, or investigate chemical-disease relationships'), matching the anchor for clearly and explicitly answering both. Not below 5 because the trigger guidance is explicit and concrete rather than weakly implied.	5 / 5
Trigger Term Quality	'query CTD', 'retrieve toxicogenomics data', and 'investigate chemical-disease relationships' are natural phrases a user would say, giving good keyword coverage. Not a 5 because it lacks synonyms (e.g. 'toxicology') and file/identifier extensions that would round out the coverage.	4 / 5
Distinctiveness Conflict Risk	Targeting a named database (CTD) with toxicogenomics-specific triggers ('chemical-disease relationships', 'toxicogenomics data') gives a clear niche with minimal overlap risk. Not below 5 because the triggers are specific enough that this would not fire for unrelated skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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/ctd-api/SKILL.md
Commit: 63c61d3

Reviewed: 5 hours 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.