CtrlK
BlogDocsLog inGet started
Tessl Logo

sdk-install

Install and initialize the correct LaunchDarkly SDK during onboarding by running nested skills in order: detect, plan, apply. Parent onboarding Step 6 is first flag.

56

Quality

63%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

Optimize this skill with Tessl

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

Quality

Content

70%

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 orchestration skill that clearly sequences three nested sub-skills with good progressive disclosure and workflow clarity. Its main weakness is that it contains no executable code or commands itself, relying entirely on referenced files for actionability, and includes some verbose cautionary notes that could be condensed. The blocking/non-blocking decision point framework is a strong design choice for guiding Claude through interactive workflows.

Suggestions

Trim repeated cautionary notes (e.g., 'Do not ask for keys', 'Do not skip ahead') into a single concise constraints section to improve token efficiency.

Consider adding a brief concrete example of what a blocking decision point interaction looks like in practice to improve actionability.

DimensionReasoningScore

Conciseness

The skill is mostly efficient but includes some redundant information—the key types table and repeated reminders about not asking for keys early, not skipping ahead, and not hardcoding keys add moderate verbosity. The repeated cross-references to parent skill behavior could be tightened.

2 / 3

Actionability

The skill provides a clear ordered workflow and references to nested skills, but contains no executable code or commands itself. It acts as an orchestration layer pointing to other files, so actionability depends entirely on those referenced skills. The guidance is specific about sequencing and blocking/non-blocking decision points, but lacks concrete examples of what to actually do.

2 / 3

Workflow Clarity

The three-step workflow is clearly sequenced with an ordered table, explicit roles for each step, blocking vs non-blocking decision point conventions, and clear continuation instructions after Step 3. Edge cases like dual-SDK and monorepo scenarios are addressed with specific guidance on what constitutes completion evidence.

3 / 3

Progressive Disclosure

The skill is well-structured as an orchestration overview with clear one-level-deep references to detect, plan, and apply nested skills, plus shared references. Navigation is easy with a references section and inline links. Content is appropriately split between this overview and the nested skills.

3 / 3

Total

10

/

12

Passed

Description

57%

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 identifies a clear niche (LaunchDarkly SDK onboarding) and is unlikely to conflict with other skills, but it lacks an explicit 'Use when...' trigger clause and relies on internal jargon ('nested skills', 'Step 6') that doesn't help Claude match user requests. The sub-steps (detect, plan, apply) are mentioned without explaining what they concretely do.

Suggestions

Add an explicit 'Use when...' clause with natural trigger terms like 'Use when the user asks to install, set up, or initialize a LaunchDarkly SDK, feature flag SDK, or mentions LaunchDarkly onboarding'.

Expand the concrete actions beyond internal sub-skill names—describe what detect, plan, and apply actually do (e.g., 'detects the project language/framework, plans the SDK integration, and applies the SDK installation and configuration').

DimensionReasoningScore

Specificity

Names the domain (LaunchDarkly SDK) and some actions (install, initialize, detect, plan, apply), but the actions 'detect, plan, apply' are vague sub-skill references rather than concrete descriptions of what each step does.

2 / 3

Completeness

The 'what' is partially addressed (install and initialize LaunchDarkly SDK via nested skills), but there is no explicit 'Use when...' clause. The mention of 'onboarding' and 'Step 6' implies context but doesn't clearly state when Claude should select this skill.

2 / 3

Trigger Term Quality

Includes relevant keywords like 'LaunchDarkly', 'SDK', 'install', 'initialize', and 'onboarding', which users might naturally say. However, it misses common variations like 'feature flags', 'feature flag SDK', 'LD SDK', or 'set up LaunchDarkly'.

2 / 3

Distinctiveness Conflict Risk

The description is quite specific to LaunchDarkly SDK installation and initialization during onboarding, with references to a specific step number and nested skill orchestration. This is unlikely to conflict with other skills.

3 / 3

Total

9

/

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.