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

78%

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 ./plugin/skills/tooluniverse-residue-functional-mechanism-interpretation/SKILL.md

Quality

Content

70%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 highly actionable, well-sequenced workflow with strong validation checkpoints and executable code throughout. Its weaknesses are token efficiency (some over-explanation and a large inline visualization block) and progressive disclosure (monolithic single-file content that could be split into references).

Suggestions

Move the Step 7 visualization code and the interpretation/cross-reference tables into reference files (e.g. VISUALIZATION.md, MECHANISMS.md) and signal them one level deep, improving both conciseness and progressive_disclosure.

Trim concept explanations Claude already knows (P-loop, hydrophobic core, what ΔΔG implies) and keep only the TU-tool-specific contract notes to lift conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code blocks, but it re-explains domain concepts Claude already knows (e.g. what a P-loop or hydrophobic core implies) and the Step 7 visualization code plus lengthy prose on alignment pitfalls could be trimmed or moved to a reference.	3 / 5
Actionability	Provides fully executable, copy-paste-ready Python for every step (clustering, structural/UniProt/SAE gathering, permutation tests, mechanism synthesis, visualization) with concrete tool names and parameters covering the common cases.	5 / 5
Workflow Clarity	Steps 0–7 are clearly sequenced with explicit validation checkpoints (Step 0 premise check with decision thresholds, Step 7 alignment assertions, honest-mismatch reporting rule), plus error-recovery feedback loops for fragile operations.	5 / 5
Progressive Disclosure	No bundle files exist and the body inlines a large amount of reference-style material (full matplotlib visualization code, interpretation table, cross-reference list) that reads as separate-file content; structure is present but not split or signaled as one-level-deep references.	3 / 5
	Total	16 / 20 Passed

Description

87%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, specific, third-person description that clearly conveys both the scientific task and the output taxonomy, with rich trigger-term coverage. It falls just short of a perfect score because it lacks an explicit 'Use when...' trigger clause, relying on implicit 'when' guidance via the accepted-source list.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a user has a list of residues (from any source) and asks why they are functionally critical,' to satisfy the completeness anchor for a 5.

Tighten the source enumeration (DMS hotspots, ClinVar, literature, conserved, user-curated) so the description reads as triggers rather than an exhaustive list, reducing overlap with sibling variant-interpretation skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — combine structural context, UniProt features, SAE evidence, DMS data — and returns a per-cluster mechanism call with seven enumerated output categories, giving comprehensive coverage.	5 / 5
Completeness	Clearly states what it does and enumerates sources/residue types, but the 'when' is implied through 'Accepts residues from any source' rather than an explicit 'Use when...' trigger clause, capping completeness below 5 per the missing-trigger guidance.	4 / 5
Trigger Term Quality	Covers natural terms a user would say ('residues', 'functionally critical', 'hotspots', 'ClinVar recurrent variants', 'conserved positions') plus technical synonyms (DMS, SAE, PTM, UniProt), achieving comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	The domain is narrow (per-cluster mechanism calls from multi-evidence synthesis) and distinct from sibling skills, but the long enumeration of residue sources introduces minor overlap risk with the variant/LoF/SAE skills it lists.	4 / 5
	Total	18 / 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: plugin/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.