CtrlK
BlogDocsLog inGet started
Tessl Logo

data-processing

Process JSON with jq and YAML/TOML with yq. Filter, transform, query structured data efficiently. Triggers on: parse JSON, extract from YAML, query config, Docker Compose, K8s manifests, GitHub Actions workflows, package.json, filter data.

96

1.20x

Quality

100%

Does it follow best practices?

Impact

82%

1.20x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

90%

-4%

Customer Order Report Generator

JSON filtering and transformation

Criteria
Without context
With context

Uses jq for JSON

100%

100%

select() filter

100%

100%

map() projection

40%

0%

length for counting

100%

100%

Raw output flag

100%

100%

Compact output flag

100%

100%

Multi-field extraction

100%

100%

Nested path access

100%

100%

Output files produced

100%

100%

Script or commands logged

100%

100%

Without context: $0.2577 · 1m · 14 turns · 19 in / 4,449 out tokens

With context: $0.5970 · 1m 58s · 31 turns · 282 in / 7,496 out tokens

90%

Kubernetes Deployment Audit and Image Update

Kubernetes YAML processing with yq

Criteria
Without context
With context

Uses yq for YAML

100%

100%

Container image extraction

100%

100%

In-place YAML edit

100%

100%

Keys enumeration

0%

0%

Nested field access

100%

100%

inventory.json produced

100%

100%

Updated YAML file

100%

100%

Script or commands logged

100%

100%

Without context: $0.2520 · 1m 5s · 18 turns · 21 in / 3,896 out tokens

With context: $0.7551 · 2m 30s · 37 turns · 45 in / 8,590 out tokens

67%

45%

Service Deployment Report Generator

TOML and Docker Compose processing with yq

Criteria
Without context
With context

Uses yq for TOML

0%

33%

TOML to JSON conversion

0%

0%

Docker Compose service names

0%

100%

Service image extraction

0%

100%

Raw output used

0%

100%

Compact JSON output

0%

0%

report.json produced

100%

100%

Script or commands logged

50%

100%

Without context: $0.3148 · 1m 17s · 20 turns · 26 in / 4,986 out tokens

With context: $0.5713 · 1m 47s · 32 turns · 34 in / 6,081 out tokens

Repository
NeverSight/skills_feed
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.