CtrlK
BlogDocsLog inGet started
Tessl Logo

dnanexus-integration

DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.

57

Quality

67%

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 ./backend/cli/skills/biology/dnanexus-integration/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A well-structured overview with real, clearly signaled reference files and concrete, mostly executable code examples. Its weaknesses are redundancy between the capability sections and the Resources/Quick Start sections, one fabricated dxpy method, and a lack of validation/error-handling checkpoints in its batch and multi-step patterns.

Suggestions

Add error-handling/validation loops to the batch and multi-step pipeline patterns (e.g. check job.describe()['state'] after wait_on_done, wrap launches in try-except as the Best Practices section itself recommends).

Replace the fabricated get_output_ref() in Pattern 2 with a real mechanism (e.g. dxpy.dxlink({'job': job_id, 'field': 'filtered_reads'}) or job.describe()['output']).

Trim duplication: drop the per-section 'See references/x.md for:' bullet lists or the final Resources section, and merge overlapping Quick Start and Common Patterns examples.

DimensionReasoningScore

Conciseness

The body is mostly efficient and does not explain concepts Claude already knows, but it repeats information: each capability section ends with a 'See references/x.md for:' bullet list that is restated in the final Resources section, the When-to-Use section restates the description, and the Quick Start examples overlap the Common Patterns section. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened'; not a 2 since nothing is padded fluff or generic explanation.

3 / 5

Actionability

Mostly executable, copy-paste-ready code: upload/run/wait/download, find_data_objects search, a full app entry point with @dxpy.entry_point, and install/login commands. Not a 5 because Pattern 2 uses a fabricated method (qc_job.get_output_ref(...)), which would fail if copied verbatim, and 'uv pip install dxpy' presumes a uv environment without alternative.

4 / 5

Workflow Clarity

The decision tree and install→login→verify sequence give a clear order, but there are no validation checkpoints: the batch Pattern 1 launches parallel jobs and calls wait_on_done() with no error handling, and the batch/destructive guideline caps workflow clarity at 3 when validation is missing. This is the 'steps listed but validation gaps' anchor, not 2 since the sequencing and routing are otherwise well defined.

3 / 5

Progressive Disclosure

The body is a genuine overview: five capability sections each name a real one-level-deep reference file (all five exist in references/), quick-start code stays inline, and the Resources section lists every file with a one-line description. This matches the 'clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation' anchor; the only cost of the repetition is conciseness, not navigation.

5 / 5

Total

15

/

20

Passed

Description

70%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, uses natural domain trigger terms, and occupies a distinct niche. Its main weakness is the missing explicit 'Use when...' trigger guidance, which both caps completeness and leaves the 'when' only weakly implied by a purpose clause.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when working with DNAnexus, dxpy, the dx CLI, or genomics pipeline jobs on the platform.'

Include common user phrasings and file extensions such as 'dx toolkit', 'dx CLI', '.fastq', '.bam', and '.vcf' to broaden natural trigger coverage.

Convert the noun fragments ('dxpy Python SDK, FASTQ/BAM/VCF') into stated actions (e.g. 'process FASTQ/BAM/VCF files') for more comprehensive capability coverage.

DimensionReasoningScore

Specificity

"Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows" lists several concrete actions, matching the 'lists several specific actions; minor gaps' anchor. It falls short of 5 because fragments like "dxpy Python SDK" and "FASTQ/BAM/VCF" are noun lists rather than stated actions, but it is well above the 1-2 concrete actions of a score-3 description.

4 / 5

Completeness

The 'what' is clear (build apps, manage data, run workflows), but there is no 'Use when...' clause; "for genomics pipeline development and execution" is only a weak purpose statement that implies when. Per the guideline that a missing 'Use when...' clause caps completeness at 3, and the anchor 'has a clear what but when is missing or only weakly implied' fits exactly.

3 / 5

Trigger Term Quality

Natural user terms are present: "DNAnexus", "apps/applets", "upload/download", "dxpy", "workflows", "FASTQ/BAM/VCF", "genomics" — good coverage matching the 'good keyword coverage; a few natural terms missing' anchor. Not a 5 because common variations users would actually say, such as 'dx toolkit', 'dx CLI', or '.fastq/.bam/.vcf' extensions, are absent.

4 / 5

Distinctiveness Conflict Risk

"DNAnexus cloud genomics platform" with dxpy, applets, and DNAnexus-specific data objects carves out a clear niche with distinct triggers and minimal conflict risk — virtually nothing else a user could ask for would match these terms, matching the score-5 anchor.

5 / 5

Total

16

/

20

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
synthetic-sciences/openscience
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.