latchbio-integration

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

Quality

65%

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 ./bundled/skills/latchbio-integration/SKILL.md

Quality

Content

65%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 skill body is well-structured with excellent progressive disclosure into four real reference files and strong executable examples, but it carries some inferable platform-feature padding and lacks explicit validation checkpoints for registration and bulk Registry operations.

Suggestions

Trim inferable platform descriptions in 'Core Capabilities' and 'Best Practices' to reduce token weight, keeping only what Claude would not already know.

Add explicit validation/feedback steps to destructive or batch flows (e.g., after `latch register` verify the workflow appears and on failure re-run with `--verbose`; before bulk Registry updates, validate the schema).

Fix the basic workflow example so `output_file` is defined (or returned from a task) to keep all snippets copy-paste runnable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with good use of bullet lists and code blocks, but sections like 'Core Capabilities', 'Best Practices', and 'When to Use' restate platform features Claude can largely infer, adding padding that could be trimmed.	3 / 5
Actionability	Provides concrete, copy-pasteable install/register commands and several executable workflow code examples covering the common cases (RNA-seq, GPU, Registry), with only minor gaps (e.g., the basic example has an undefined 'output_file').	4 / 5
Workflow Clarity	Multi-step registration/setup and troubleshooting flows are present, but the destructive/batch-adjacent registration and bulk Registry operations lack explicit validate-then-proceed checkpoints and feedback loops, capping this dimension at 3.	3 / 5
Progressive Disclosure	The SKILL.md is a clear overview with well-signaled, one-level-deep references (workflow-creation.md, data-management.md, resource-configuration.md, verified-workflows.md), all of which exist as real bundle files, each annotated with 'Read this for' and 'Key topics' for easy navigation.	5 / 5
	Total	15 / 20 Passed

Description

66%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 and distinguishable, naming concrete platform features and integration points, but it lacks any explicit 'Use when' trigger guidance, which caps its completeness. Adding a trigger clause and a few synonyms would move it into the top tier.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user mentions Latch, bioinformatics pipelines, @workflow/@task decorators, or converting Nextflow/Snakemake workflows to Latch.'

Include a couple of natural synonyms users might say (e.g. 'RNA-seq pipeline', 'serverless bioinformatics') to broaden trigger-term coverage.

Consider switching to third-person action voice consistently and keeping it to one tight sentence plus the trigger clause to avoid padding.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions and artifacts ('Build pipelines with Latch SDK', '@workflow/@task decorators', 'deploy serverless workflows', 'LatchFile/LatchDir', 'Nextflow/Snakemake integration'), with only minor coverage gaps (e.g., no mention of Registry or resource config).	4 / 5
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or explicit trigger guidance for when Claude should invoke it, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes strong natural terms ('bioinformatics workflows', 'Nextflow', 'Snakemake', 'Latch SDK') that users would say, though it leans on technical jargon ('serverless workflows', decorator syntax) and lacks synonyms like 'RNA-seq' or 'pipeline'.	4 / 5
Distinctiveness Conflict Risk	The Latch platform and its decorator/file-type vocabulary carve out a clear niche with minimal overlap risk; minor overlap could occur with generic Nextflow/Snakemake skills.	4 / 5
	Total	15 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/latchbio-integration/SKILL.md
Commit: d5ae560

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.