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

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, clearly sequenced workflow with strong validation checkpoints and executable code throughout. The main weaknesses are a monolithic structure with no progressive disclosure into bundle files and a verbose inline visualization section that inflates token cost.

Suggestions

Move the Step 7 plotting code and the interpretation/limitations tables into a reference file (e.g. references/visualization.md) and link to it from SKILL.md, improving both conciseness and progressive_disclosure.

Trim the narrative framing paragraphs (e.g. 'The core user question') since the When-to-use section already conveys intent.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient actionable workflow, but it carries narrative padding ('The core user question: Why are these residues functionally critical?') and a very long inline Step 7 plotting block (~100 lines of matplotlib) that could be trimmed or moved out. It is above the 1-anchor because it does not explain basic concepts Claude already knows, but below the 3-anchor for the inline bulk.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python for every step — Structure_annotate_per_residue, UniProt_get_function_by_accession, ESM_get_region_sae_features, the permutation test, and call_mechanism — with concrete tool names and parameters. Matches the anchor for fully executable code and specific examples.	3 / 3
Workflow Clarity	Steps 0–7 are clearly sequenced with explicit validation checkpoints: the Step 0 premise check has a ranked decision rule ('below top 50% → REPORT THIS MISMATCH TRANSPARENTLY'), and Step 7 includes an alignment landmark assert with error-recovery guidance. This matches the 3-anchor's explicit validation steps and feedback loops.	3 / 3
Progressive Disclosure	The skill is a single monolithic SKILL.md with no bundle files (references/, scripts/, assets/ are absent), and content that could be split — the Step 7 visualization, the interpretation table, and the honest-limitations section — is inline. Sections are well-organized, so it clears the 1-anchor, but content that should be separate is inline, keeping it at 2.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, well-scoped description that names concrete actions, multiple natural source triggers, and a clear distinct output. Its main gap is the absence of an explicit 'Use when...' trigger clause, which keeps completeness at 2.

Suggestions

Add an explicit 'Use when ...' trigger clause (e.g. 'Use when you have a list of residues and need to explain why each is functionally critical') to lift completeness to 3.

Lead with the user-facing trigger before the implementation detail of evidence sources, so the 'when' reads as naturally as the 'what'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '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' and 'Returns a per-cluster mechanism call: catalytic / ligand-binding / interface / structural-core / PTM / regulatory / unknown' — matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It clearly answers 'what' (combine evidence sources, return a per-cluster mechanism call) and 'accepts residues from any source', but there is no explicit 'Use when...' clause or equivalent trigger guidance, so per the guideline completeness is capped at 2 rather than reaching the 3-anchor's explicit when-triggers.	2 / 3
Trigger Term Quality	Covers natural domain terms a target user would say — 'residues functionally critical', 'DMS hotspots (top-K by max effect)', 'ClinVar recurrent variants', 'literature-reported hot regions', 'evolutionarily conserved positions' — giving good coverage of the ways residues arrive. It is not the 2-anchor because it goes well beyond a single generic phrase.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply defined — per-cluster functional mechanism interpretation of residues — and it explicitly distinguishes itself from sibling skills by what it returns, making it unlikely to trigger for the wrong skill. It is above the 2-anchor because it is not merely 'somewhat specific'.	3 / 3
	Total	11 / 12 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: 089eb8e

Reviewed: about 7 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.