CtrlK
BlogDocsLog inGet started
Tessl Logo

apply

Apply LaunchDarkly SDK onboarding: install dependency (or dual-SDK pair), configure env and secrets with consent, add init at entrypoint(s), verify compile. Nested under sdk-install; next is run.

64

Quality

76%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/onboarding/sdk-install/apply/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

This is a well-structured, highly actionable skill that clearly sequences a multi-step SDK installation workflow with strong safety gates (blocking decision points for secrets and dependency changes). Its main weakness is verbosity — dual-SDK reminders are repeated in nearly every section and the D7 option flows are exhaustively detailed, consuming more tokens than necessary. Progressive disclosure and workflow clarity are excellent, with clear references to supporting files and explicit validation checkpoints.

Suggestions

Consolidate the repeated dual-SDK reminders into a single prominent callout at the top (e.g., a 'Dual SDK note' box) and reference it from each step instead of restating the full guidance each time.

Condense the D7 option flows — the sub-steps for each option could be shortened to 1-2 lines each since Claude can infer standard behaviors like 'ask for file path' without explicit enumeration.

DimensionReasoningScore

Conciseness

The skill is thorough but verbose in places — the D7 decision point exhaustively spells out all four option flows with sub-steps that could be condensed, and the dual-SDK reminders are repeated across nearly every section. Some of this repetition is warranted for safety but overall the token budget could be tightened by ~30%.

2 / 3

Actionability

Provides concrete MCP tool calls (`get-environments`), exact env variable names per framework, specific dashboard URLs with interpolation patterns, explicit `.gitignore` instructions, and a clear build-verify step. The guidance is specific and executable throughout, even though init code samples are deliberately deferred to referenced recipe files.

3 / 3

Workflow Clarity

Four clearly numbered steps with explicit sequencing (install → env/secrets → init → verify compile). Blocking decision points (D7, D8) with STOP directives serve as validation checkpoints, and there's a feedback loop for install conflicts and a hard gate ('do not proceed if the code doesn't compile') before the next phase.

3 / 3

Progressive Disclosure

The skill clearly positions itself in the parent workflow (prior: plan, next: run), references SDK recipes, snippet detail files, detect skill, and parent SKILL.md with relative links. Content is appropriately split — init code samples live in referenced recipe/snippet files rather than inline, and navigation is one level deep and well-signaled.

3 / 3

Total

11

/

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 excels at specificity and distinctiveness by naming concrete LaunchDarkly SDK onboarding steps and carving out a clear niche. However, it lacks an explicit 'Use when...' clause to guide skill selection, and could benefit from more natural trigger terms that users would actually say (e.g., 'feature flags', 'set up LaunchDarkly'). The workflow metadata ('Nested under sdk-install; next is run') is useful for orchestration but doesn't help with trigger matching.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to set up or install a LaunchDarkly SDK, integrate feature flags into their project, or onboard a new application with LaunchDarkly.'

Include natural trigger terms users would say, such as 'feature flags', 'feature flag SDK', 'set up LaunchDarkly', 'LD integration', or 'add LaunchDarkly to my project'.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: install dependency (or dual-SDK pair), configure env and secrets with consent, add init at entrypoint(s), verify compile. These are clear, actionable steps.

3 / 3

Completeness

The 'what' is well-covered with specific actions, but there is no explicit 'Use when...' clause. The phrase 'Nested under sdk-install; next is run' describes workflow positioning rather than trigger conditions. Per rubric guidelines, missing 'Use when' caps completeness at 2.

2 / 3

Trigger Term Quality

Includes relevant terms like 'LaunchDarkly', 'SDK', 'onboarding', 'install dependency', 'env', 'secrets', but misses common user-facing variations like 'feature flags', 'feature flag SDK', 'LD setup', or language-specific SDK names that users might naturally say.

2 / 3

Distinctiveness Conflict Risk

Very specific to LaunchDarkly SDK onboarding with a clear niche. The mention of 'LaunchDarkly', 'dual-SDK pair', and the specific workflow steps make it highly unlikely to conflict with other skills.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
launchdarkly/ai-tooling
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.