esm

Use when working directly with the `esm` Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.

Quality

72%

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 ./skills/esm/SKILL.md

Quality

Content

72%

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-organized skill body with excellent progressive disclosure and copy-paste-ready code, weakened by moderate verbosity and by missing validation/feedback loops in its batch and destructive-operation workflows.

Suggestions

Trim the overview paragraph, de-duplicate repeated import lines, and move or condense the generic 'Best Practices' bullets and the stub 'Common Workflows' list to tighten conciseness.

Add explicit validation/feedback loops (error handling, retry, and result checks) to the Forge batch-processing example so the batch/destructive workflow earns full workflow-clarity credit.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete code, but it is padded with a restating overview paragraph, repeated import boilerplate across sections, generic best-practice bullets (e.g. 'Implement error handling and retry logic'), and a stub 'Common Workflows' list that could be tightened or moved to a reference.	2 / 3
Actionability	It provides extensive executable, copy-paste-ready Python against the real ESM API plus concrete install commands, auth steps, and specific model IDs, meeting the fully-executable anchor.	3 / 3
Workflow Clarity	The chain-of-thought generation and authentication are clearly sequenced, but batch/destructive Forge operations (async_generate) and the Forge batch example lack validation or feedback loops, which caps workflow clarity at 2 per the rubric notes.	2 / 3
Progressive Disclosure	The SKILL.md is a clear overview with well-signaled, one-level-deep references to five real reference files (all present on disk), with detail appropriately split out and easy navigation via both inline pointers and a References section.	3 / 3
	Total	10 / 12 Passed

Description

72%

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 precise, well-targeted trigger description with strong natural keywords and low conflict risk, but it functions almost entirely as a "when" clause and omits an explicit statement of what the skill does.

Suggestions

Add an explicit capability clause before the trigger, e.g. 'Generate, design, and analyze proteins using ESM protein language models. Use when…', so the description answers both 'what' and 'when'.

Lead with concrete verbs (generate sequences, predict structures, compute embeddings) to lift specificity from naming targets to naming actions.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ("esm Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows") but enumerates trigger targets rather than concrete actions the skill performs, so it falls short of the multiple-specific-actions anchor.	2 / 3
Completeness	It has an explicit, strong "Use when…" trigger (the "when"), but never states what the skill actually does (the "what" is only implied through the listed technologies), so it does not clearly answer both.	2 / 3
Trigger Term Quality	It uses exactly the natural terms a user in this domain would say — ESM3, ESMC, ESMFold2, Forge, Biohub, and "esm" SDK — giving good coverage of likely trigger vocabulary.	3 / 3
Distinctiveness Conflict Risk	The niche is highly specific (ESM protein language models with named model IDs and platforms) with distinct triggers, making conflict with other skills unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/esm/SKILL.md
Commit: 757b63b

Reviewed: about 12 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.