CtrlK
BlogDocsLog inGet started
Tessl Logo

detect

Detect repository stack for LaunchDarkly SDK onboarding: languages, frameworks, package managers, monorepo targets, entrypoints, existing LD usage. Nested under sdk-install; next is plan.

81

0.98x
Quality

76%

Does it follow best practices?

Impact

85%

0.98x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/onboarding/sdk-install/detect/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

94%

LaunchDarkly SDK Onboarding: Multi-Package Node.js Project

Monorepo target selection and scoped detection

Criteria
Without context
With context

Monorepo detected

100%

100%

Root not assumed as target

100%

100%

Target selection question noted

40%

40%

Runnable package selected

100%

100%

Scoped detection

100%

100%

Framework identified

100%

100%

Package manager identified

100%

100%

Entrypoint identified

100%

100%

LD search performed

100%

100%

SDK recommendation made

100%

100%

No root-level LD search only

100%

100%

77%

LaunchDarkly SDK Onboarding: Ambiguous Workspace

Weak-evidence workspace confidence classification

Criteria
Without context
With context

Weak evidence classification

100%

100%

Weak evidence reasoning

100%

100%

No premature integration

100%

100%

Blocking clarification documented

100%

100%

Multiple lock files noted

100%

100%

Most-recently-modified lock file preferred

16%

0%

LD search performed

100%

100%

LD not found correctly noted

100%

100%

Candidate folders offered

44%

44%

Demo app option mentioned

0%

25%

86%

-3%

LaunchDarkly SDK Onboarding: Full-Stack Next.js Application

Next.js dual-SDK and partial LD install detection

Criteria
Without context
With context

Next.js detected

100%

100%

Both surfaces identified

100%

100%

Server entrypoint identified

100%

100%

Client entrypoint identified

100%

100%

LD search terms used

75%

62%

SDK installed detected

100%

100%

Not initialized detected

100%

100%

Decision tree: apply-code-changes

83%

75%

Dual-SDK scope noted

100%

100%

Package manager identified

100%

100%

No install step recommended

30%

20%

Repository
launchdarkly/ai-tooling
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.