esm

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

Quality

75%

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%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 body is highly actionable with executable examples and excellent progressive disclosure through real reference files. Its main weaknesses are inlined time-sensitive version information affecting conciseness and missing validation/feedback loops in batch generation workflows.

Suggestions

Move the pinned PyPI version and date ("3.2.3 (Oct 14, 2025)") into a versioned or "current release" subsection separate from the concise install instructions so time-sensitive info does not bloat the main flow.

Add validation/error-recovery to the Forge batch example (e.g., check `async_generate` results, retry on rate-limit errors, handle failed items) so batch workflows include explicit feedback loops.

Tighten the per-section "When to use" bullet lists where they restate capability headings, to reduce prose that duplicates nearby context.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with lean code blocks, but inlined time-sensitive information ("Current PyPI release: 3.2.3 (Oct 14, 2025)") and some explanatory prose could be trimmed or moved to a versioned/deprecated section, pulling it below level 4.	3 / 5
Actionability	Provides copy-paste-ready, executable Python covering the common cases (generation, structure prediction, inverse folding, embeddings, function conditioning, chain-of-thought, async batch) with specific imports and parameters.	5 / 5
Workflow Clarity	Chain-of-thought and authentication show sequenced steps, but the batch/Forge generation workflows lack validation checkpoints or error-recovery feedback loops, which caps batch-operation workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Clear overview body with well-signaled, one-level-deep references to five real files (esm3-api.md, esm-c-api.md, forge-api.md, biohub-platform.md, workflows.md), each inline-signaled and consolidated in a References section for easy navigation.	5 / 5
	Total	16 / 20 Passed

Description

78%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 specific, third-person, and uses a clear "Use when..." trigger with concrete model/client identifiers that a user would naturally say. It is strong on distinctiveness and trigger quality, with only minor gaps in explicit action verbs and synonym coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete targets ("`esm` Python SDK", "ESM3 or ESMC model IDs", "Forge/Biohub inference clients", "ESMFold2 folding workflows") rather than vague language, though they are objects/capabilities more than explicit verb-actions, leaving a minor gap versus the level-5 anchor.	4 / 5
Completeness	Explicit "Use when..." trigger answers the "when" clearly, and the enumerated targets convey the "what", but the "what" is framed indirectly through triggers rather than stated as concrete actions, so it does not fully reach the level-5 anchor.	4 / 5
Trigger Term Quality	Strong coverage of natural domain terms a user would say (ESM3, ESMC, Forge, Biohub, ESMFold2, folding workflows); a few common synonyms like "protein language model", "embeddings", or "structure prediction" are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	A clear niche defined by specific model IDs and clients (ESM3/ESMC/Forge/Biohub/ESMFold2) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 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: 49c6e97

Reviewed: 9 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.