Name: tooluniverse-residue-functional-mechanism-interpretation
Rating: 66.4 (1 reviews)
Author: mims-harvard

Blog Docs Log in Get started

tooluniverse-residue-functional-mechanism-interpretation

Given a set of residues in a protein, explain WHY they are functionally critical by combining structural context (binding interface, ligand pocket, core, secondary structure), UniProt features (active sites, binding sites, PTM sites, disulfides), optional SAE feature evidence, and optional DMS data. Accepts residues from any source: DMS hotspots (top-K by max effect), ClinVar recurrent variants, literature-reported hot regions, evolutionarily conserved positions, or user-curated lists. Returns a per-cluster mechanism call: catalytic / ligand-binding / interface / structural-core / PTM / regulatory / unknown.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-residue-functional-mechanism-interpretation/SKILL.md

The canonical home for this skill is tooluniverse-residue-functional-mechanism-interpretation in mims-harvard/ToolUniverse

Quality

Content

85%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 code, clear sequencing, and strong validation checkpoints, but everything is inlined in one large SKILL.md with no one-level-deep references, leaving progressive disclosure as the weakest dimension. Splitting some detail into referenced files would improve navigability.

Suggestions

Move the long Step 7 visualization code into a referenced file (e.g. references/heatmap.py) and keep only the alignment checkpoint and key rules inline, to improve progressive disclosure.

Tighten the KRAS G12/G13 premise example and heatmap cell-color rules to a few lines each while preserving the pitfall message.

Consider extracting the interpretation table and honest-limitations list into a short reference doc if the skill grows further, keeping SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with actionable code and tables and little re-explanation of basics, though a few prose passages (the KRAS worked example, heatmap cell-color rules) could be tightened without losing value.	4 / 5
Actionability	Fully executable Python throughout with real tool names and parameters (numpy argsort, Structure_annotate_per_residue, UniProt_get_function_by_accession, ESM SAE tools, matplotlib), with concrete Path A/Path B examples covering the common cases.	5 / 5
Workflow Clarity	Clear Step 0-7 sequence with explicit validation checkpoints (premise check with a top-% decision rule, alignment assert in Step 7) and a real feedback loop that requires reporting mismatches transparently before continuing.	5 / 5
Progressive Disclosure	The body is a single large inlined file with no bundle references; sections are well-organized with a cross-reference table, but bulk content like the long Step 7 visualization code that could live one level deep is inlined.	3 / 5
	Total	17 / 20 Passed

Description

75%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 highly specific and distinctive with concrete actions and a clear output contract, but it lacks an explicit 'Use when...' trigger clause, which limits completeness. Adding natural trigger phrasing would raise the trigger-term and completeness scores.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers, e.g. 'Use when explaining why a set of protein residues is functionally important or assigning a mechanism category to each residue/cluster.'

Soften jargon (SAE, DMS, top-K by max effect) in the opening sentence or pair it with plainer synonyms so the description reads in natural user language.

Keep the comprehensive output-category list and source enumeration, as these drive the strong specificity and distinctiveness scores.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (combine structural context, UniProt features, SAE, DMS) and enumerates both residue sources and the full set of output mechanism categories, giving comprehensive coverage rather than just several actions with minor gaps.	5 / 5
Completeness	Has a clear 'what' (synthesize multi-source evidence into a per-cluster mechanism call) but no 'Use when...' clause or explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes relevant natural terms like 'residues', 'functionally critical', 'ClinVar recurrent variants', and 'conserved positions', but leans technical (SAE, DMS, top-K) and omits common phrasings a biologist would actually say.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear narrow niche (residue mechanism interpretation) with specific output categories and is explicitly distinguished from sibling single-variant skills, so conflict risk is minimal.	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
skill_md_line_count	SKILL.md is long (506 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-residue-functional-mechanism-interpretation/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.