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.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

85%Weight 40%Scale 1-3

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

The body is a well-structured, concise orchestrator with a clear sequenced workflow and strong progressive disclosure into nested skills. Its main gap is actionability: it points to nested skills for executable steps rather than providing any copy-paste-ready code or commands directly.

Suggestions

Include at least one minimal executable snippet inline (e.g. a one-line SDK install/init example for the most common stack) so the body is actionable without always opening a nested skill.

Surface the compile-check/validation step as an explicit checkpoint in the main workflow table rather than only inside the Apply row, to make the feedback loop visible at the orchestration level.

Consolidate the repeated 'see parent onboarding' prerequisite pointers into a single Prerequisites note to trim redundant cross-references.

DimensionReasoningScore

Conciseness

The body is lean and operational — tables, bullets, and cross-references with no padding explaining what an SDK is or how libraries work; every line carries actionable guidance, matching the 'every token earns its place' anchor.

3 / 3

Actionability

Orchestration guidance is concrete (run detect → plan → apply, 'Prefer TypeScript in TypeScript projects', 'Add .env.example entries'), but the body itself contains no executable code/commands — the actual executable steps live in the nested skills, so it stops at 'some concrete guidance but incomplete' from this file alone.

2 / 3

Workflow Clarity

Clear ordered sequence (Detect → Plan → Apply) with explicit blocking/non-blocking decision points, 'Do NOT batch tool calls across blocking boundaries', a compile-check validation in Apply, and edge-case branches — matching the anchor for clear sequence with explicit validation and feedback loops.

3 / 3

Progressive Disclosure

The SKILL.md is an overview that delegates detail to one-level-deep nested skills (detect/SKILL.md, plan/SKILL.md, apply/SKILL.md) and shared references (recipes.md, snippets/), with well-signaled links and a References section — the textbook overview-to-details split.

3 / 3

Total

11

/

12

Passed

Description

67%Weight 40%Scale 1-3

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 and occupies a distinct niche, but it lacks an explicit 'Use when...' trigger and relies on internal orchestration jargon rather than natural user phrasing. Adding concrete trigger terms would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause with natural triggers, e.g. 'Use when the user needs to install or set up the LaunchDarkly SDK in their project.'

Replace internal labels ('nested skills', 'detect, plan, apply', 'Step 6') with user-facing terms like 'set up', 'add', or 'integrate LaunchDarkly'.

Drop the 'Parent onboarding Step 6 is first flag' detail from the description; it is parent-flow context that dilutes the skill's own trigger signal.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Install and initialize the correct LaunchDarkly SDK' and 'running nested skills in order: detect, plan, apply' — matching the anchor for several specific concrete actions.

3 / 3

Completeness

The 'what' is explicit (install/initialize the SDK) but there is no 'Use when...' trigger clause; 'during onboarding' is only an implied/contextual 'when', so per the guideline completeness is capped at 2.

2 / 3

Trigger Term Quality

Includes relevant terms a user might say ('LaunchDarkly SDK', 'onboarding') but leans on internal jargon ('nested skills', 'detect, plan, apply', 'Step 6') and misses common variations like 'set up', 'add', or 'feature flags'.

2 / 3

Distinctiveness Conflict Risk

Targets a clear niche — LaunchDarkly SDK installation during onboarding — and is unlikely to trigger for unrelated skills; 'Parent onboarding Step 6 is first flag' further distinguishes it from flag-creation work.

3 / 3

Total

10

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 14 missing, 10 suspicious

Warning

Total

15

/

16

Passed

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.