Name: tooluniverse-residue-functional-mechanism-interpretation
Rating: 64.8 (1 reviews)
Author: mims-harvard

Blog Docs Log inGet 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

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 ./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

81%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 strong, highly actionable workflow document: sequenced steps with real validation checkpoints, executable domain-specific code, honest limitations, and explicit decision rules. The main improvement opportunities are offloading the long visualization script to a reference file and tightening a few narrative sections.

Suggestions

Move the full Step 7 matplotlib script to a references/ file (e.g. references/heatmap.md) and keep only the alignment-check and cell-color rules inline, shortening SKILL.md substantially.

Define or briefly note the assumed context variables (pos_index, wt_vec, hotspot_results, amino_acid_order, positions, sequence) so the code blocks are fully copy-paste runnable.

Trim the Step 0 KRAS worked example to 2-3 sentences, keeping the decision rule and the mismatch-reporting obligation which carry the instructional value.

Dimension	Reasoning	Score
Conciseness	The body is dense with domain-specific knowledge Claude does not already have (TU tool APIs, SAE labeling costs, assay-specific pitfalls like the +2 registration error), but the ~75-line inlined matplotlib script in Step 7 and the long worked KRAS anecdote could be trimmed, matching the 'minor instances that could be trimmed' anchor rather than the maximally lean anchor at 5.	4 / 5
Actionability	Every step ships concrete, mostly executable code with real tool calls and literal parameters (e.g. Structure_annotate_per_residue(pdb_id="6VJJ", ...)), numeric decision thresholds, and a rendered output example; minor gaps remain in assumed-but-undefined variables (pos_index, wt_vec, hotspot_results, amino_acid_order), keeping it just below the fully copy-paste-ready anchor.	4 / 5
Workflow Clarity	Steps 0-7 are explicitly sequenced with skip conditions (Path A vs B), a premise-check decision rule with numeric thresholds (top 25%/50% and transparent mismatch reporting), an alignment assert landmark before plotting, and fallbacks for low-power cases — matching the 'explicit validation steps; feedback loops' anchor.	5 / 5
Progressive Disclosure	Well-structured single-file skill with clear headers, tables, and cross-references to sibling skills and no nested references, so navigation is easy; however no bundle files exist and long self-contained blocks (the full Step 7 plotting script, the mechanism interpretation table) are inlined in a ~500-line file, which is a minor organization gap rather than an ideal split.	4 / 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.

A highly specific, concrete, third-person description that clearly states what the skill does and what it returns, with excellent distinctiveness. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness and leaves the 'when to use it' only weakly implied.

Suggestions

Append an explicit trigger clause, e.g. 'Use when you have a list of protein residues (from DMS hotspots, ClinVar, literature, or conservation) and need to explain why each is functionally critical.'

Add one or two plainer natural-language trigger phrases (e.g. 'why is this residue/mutation important', 'active site') alongside the technical vocabulary so non-specialist phrasings still match.

Dimension	Reasoning	Score
Specificity	Enumerates concrete actions and inputs (structural context, UniProt active/binding/PTM/disulfide sites, optional SAE and DMS evidence) and a concrete output vocabulary of per-cluster mechanism calls, all in third-person voice; this matches the 'comprehensive coverage' anchor with no notable gaps.	5 / 5
Completeness	The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'Accepts residues from any source' describes inputs, not usage occasions — so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Good natural-keyword coverage ('residues', 'functionally critical', 'hotspots', 'ClinVar recurrent variants', 'conserved positions'), but the phrasing skews technical (DMS, SAE, UniProt) and misses plainer user phrasings like 'why is this mutation important' or 'active site', so it falls short of the comprehensive-synonym anchor at 5.	4 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche (per-cluster mechanism interpretation for residue sets from DMS/ClinVar/literature/conservation sources) with distinct triggers and a unique output format, giving minimal overlap risk with sibling single-variant 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
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: 164aaf1

Reviewed: 6 days 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.