latchbio-integration
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
63
46%
Does it follow best practices?
Impact
91%
1.65xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/latchbio-integration/SKILL.mdQuality
Discovery
50%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 excels at specificity and distinctiveness, listing concrete Latch-specific capabilities and technical terms that clearly carve out a unique niche. However, it critically lacks a 'Use when...' clause, which hurts completeness significantly. The trigger terms are appropriate for the domain but could benefit from broader natural language variations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Latch, latch.bio, building bioinformatics pipelines, or deploying workflows on the Latch platform.'
Include broader natural language trigger terms like 'bioinformatics pipeline', 'latch.bio', 'genomics workflow', or 'cloud bioinformatics' to capture more user phrasings.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build pipelines with Latch SDK', '@workflow/@task decorators', 'deploy serverless workflows', 'LatchFile/LatchDir', 'Nextflow/Snakemake integration'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Describes what the skill does (build pipelines, deploy workflows, etc.) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'when' is not even implied clearly, warranting a score closer to 1. | 1 / 3 |
Trigger Term Quality | Includes relevant technical keywords like 'Latch SDK', 'bioinformatics', 'Nextflow', 'Snakemake', 'pipelines', 'workflows', but these are fairly specialized. Missing common user phrasings like 'latch.bio', 'bioinformatics pipeline', or broader terms a user might naturally say. The terms are good for the niche but could include more variations. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with very specific niche terms like 'Latch SDK', 'LatchFile/LatchDir', '@workflow/@task decorators', and 'Latch platform'. Extremely unlikely to conflict with other skills due to the specificity of the Latch bioinformatics ecosystem. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has excellent progressive disclosure with well-organized references to detailed documentation, but suffers from significant verbosity—the 'When to Use This Skill' section, capability overview, and detailed reference descriptions consume many tokens without adding actionable value. Code examples are illustrative but not truly executable, and the workflow lacks validation checkpoints between steps.
Suggestions
Remove the 'When to Use This Skill' section entirely and trim the 'Core Capabilities' overview to a brief bullet list—Claude can infer applicability from the content itself.
Condense the 'Detailed Documentation' section to a simple table or short list of reference files with one-line descriptions instead of multi-line topic lists for each.
Make code examples fully executable by replacing undefined variables (e.g., `output_file`, `qc_output`) with actual implementation or clearly marked placeholder logic.
Add explicit validation steps to the Quick Start and pipeline examples, such as 'Verify registration: `latch get-wf` to confirm workflow appears' and local Docker testing before registration.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose with significant padding. The 'When to Use This Skill' section is unnecessary (Claude can infer this), the 'Core Capabilities' overview restates what the reference files cover, the 'Detailed Documentation' section extensively describes each reference file's contents (table-of-contents style), and the 'Best Practices' are generic advice Claude already knows. Much of this content could be cut by 60%+ without losing actionable information. | 1 / 3 |
Actionability | The CLI commands are concrete and the code examples show real decorator patterns, but the workflow examples are incomplete pseudocode (e.g., `process_file` returns `output_file` without defining it, `quality_control` returns `qc_output` without defining it). The Registry example uses `process()` which is undefined. These are illustrative but not executable. | 2 / 3 |
Workflow Clarity | The Quick Start provides a clear 4-step sequence (install → login → init → register), and the troubleshooting section covers common issues. However, there are no validation checkpoints in the workflow development process—no step to verify registration succeeded, no feedback loop for testing locally before deploying, and the multi-step pipeline examples lack any validation between steps. | 2 / 3 |
Progressive Disclosure | The skill is well-structured with a clear overview pointing to four one-level-deep reference files, each with clear descriptions of what they cover and when to read them. Navigation is straightforward with well-signaled references to workflow-creation.md, data-management.md, resource-configuration.md, and verified-workflows.md. | 3 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
b58ad7e
- 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.