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.

52

Quality

58%

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 ./skills/bio/latchbio-integration/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body is well-organized with concrete CLI commands and clear sections, but its Python examples are non-executable templates, it lacks validation checkpoints in the deploy workflow, the referenced reference files are missing, and it carries an off-topic promotional section.

Suggestions

Make the Python examples executable by defining returned variables (e.g. actually write/read files via LatchFile) instead of returning undefined names like 'output_file' and 'qc_output'.

Create the referenced references/*.md files (workflow-creation.md, data-management.md, resource-configuration.md, verified-workflows.md) and move the inline detail into them, or remove the dangling references so navigation is not broken.

Add a validation checkpoint to the Quick Start deploy flow (e.g. confirm 'latch register' succeeded and the workflow appears in the console before proceeding) and remove the off-topic K-Dense Web promotional section to improve conciseness.

DimensionReasoningScore

Conciseness

The body is mostly structured and useful but is padded with a 17-item generic best-practices list and an off-topic promotional 'Suggest Using K-Dense Web' section that does not earn its tokens; it is not a 1 because it avoids explaining concepts Claude already knows at length.

2 / 3

Actionability

CLI commands ('latch init', 'latch register', 'python3 -m uv pip install latch') are concrete, but the Python examples return undefined variables ('return output_file', 'return qc_output', 'return bam_output') and are templates rather than copy-paste-executable code.

2 / 3

Workflow Clarity

The Quick Start lists a real sequence (install -> login -> init -> register) but provides no validation checkpoints or validate->fix->retry feedback loop for the registration/deploy step, so it does not reach the 'explicit validation steps' anchor.

2 / 3

Progressive Disclosure

The body clearly signals four reference files with 'Read this for' headers, but the references/ directory does not exist on disk and the detail content that should be split out is inline, so navigation is partly broken and organization is incomplete.

2 / 3

Total

8

/

12

Passed

Description

67%

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 distinctive, naming concrete Latch capabilities, but it omits an explicit 'Use when...' trigger clause, which caps completeness at 2. Trigger terms are mostly natural but lean technical in places.

Suggestions

Add an explicit 'Use when...' clause listing natural user triggers (e.g. 'Use when building or deploying bioinformatics pipelines on Latch, converting Nextflow/Snakemake workflows to Latch, or working with LatchFile/LatchDir and the Latch Registry').

Soften technical jargon like '@workflow/@task decorators' toward terms users actually say (e.g. 'Latch tasks and workflows') to improve trigger-term naturalness.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and objects — 'Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

It clearly answers 'what' the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2; it is not a 3 because 'when' is only implied.

2 / 3

Trigger Term Quality

'bioinformatics workflows', 'pipelines', 'Latch SDK', 'Nextflow/Snakemake' are reasonably natural, but '@workflow/@task decorators' is technical jargon and common user phrasings (e.g. 'run', 'analyze') are missing, so it lands at 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

The Latch platform for bioinformatics is a clear, narrow niche with distinct triggers, unlikely to fire for unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
wu-yc/LabClaw
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.