CtrlK
BlogDocsLog inGet started
Tessl Logo

latchbio-integration

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

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/latchbio-integration/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

Well-structured content with strong progressive disclosure and concrete commands, but weakened by redundant overview sections and Python examples that are templates rather than fully executable code, plus absent validation feedback loops for risky deploy/batch operations.

Suggestions

Make code examples executable: define the missing variables/functions (e.g. assign output_file, implement process()) or mark them clearly as illustrative templates, so examples are copy-paste ready.

Collapse the overlap between 'Core Capabilities', 'When to Use', and 'Detailed Documentation' key topics into a single concise map to the reference files.

Add an explicit validation checkpoint for registration (e.g. 'Run latch register --dry-run / validate locally with Docker, and only proceed on success') to establish a validate→fix→retry loop.

DimensionReasoningScore

Conciseness

Mostly efficient but carries redundancy — 'Core Capabilities' (lines 15-45), 'Detailed Documentation' key topics (122-194), and 'When to Use' (93-120) restate overlapping material, and the body runs ~340 lines. Not a 3 because not every token earns its place; not a 1 because it avoids explaining concepts Claude already knows.

2 / 3

Actionability

Provides concrete commands (latch init/login/register) and code templates, but the Python examples return undefined variables (output_file, qc_output, bam_output, counts) and call undefined functions (process()), so they are pseudocode rather than copy-paste ready. Not a 3 due to the incomplete/non-executable examples.

2 / 3

Workflow Clarity

Quick Start sequences install→login→init→register and Best Practice #14 ('Test locally with Docker before registration') offers a checkpoint, but there is no explicit validate→fix→retry feedback loop for registration/deploy or batch Registry operations, capping this at 2 per the rubric's destructive/batch-operation note.

2 / 3

Progressive Disclosure

Overview points to four real, one-level-deep reference files (workflow-creation.md, data-management.md, resource-configuration.md, verified-workflows.md — all verified present), each clearly signaled with 'Read this for' and 'Key topics' navigation. Matches the clear-overview, well-signaled one-level-deep anchor.

3 / 3

Total

9

/

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, distinctive description that names concrete actions and natural trigger terms for a well-defined niche. Its main weakness is the absence of an explicit 'Use when' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when building or deploying bioinformatics workflows on Latch, converting Nextflow/Snakemake pipelines, or managing cloud data with LatchFile/LatchDir.'

Trim the technical jargon terms (@workflow/@task decorators, LatchFile/LatchDir) toward natural user phrasing to keep trigger terms user-aligned.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Build pipelines with Latch SDK', 'deploy serverless workflows', 'Nextflow/Snakemake integration' — tied to specific SDK constructs (@workflow/@task decorators, LatchFile/LatchDir), matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers 'what' (build/deploy/integrate pipelines) but has no explicit 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 2 per the rubric guidelines. Not a 3 because the 'when' is entirely missing rather than explicit.

2 / 3

Trigger Term Quality

Covers natural terms users would say — 'Latch', 'bioinformatics workflows', 'pipelines', 'deploy', 'Nextflow', 'Snakemake' — alongside supplementary technical terms; good coverage rather than jargon-only. Not a 2 because common natural variations are present, not just one or two.

3 / 3

Distinctiveness Conflict Risk

'Latch platform for bioinformatics workflows' carves a distinct niche unlikely to conflict with other skills; Latch is a specific named platform. Not a 2 because the named platform and domain make overlap unlikely.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
foryourhealth111-pixel/Vibe-Skills
Reviewed

Table of Contents

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.