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 findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/onboarding/sdk-install/detect/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.

The body is a well-structured, highly actionable detection workflow with explicit validation checkpoints and clean one-level-deep navigation; its only real weakness is repeated blocking-question boilerplate and minor preamble that inflate the token budget.

Suggestions

Define the D5 blocking-question pattern once (the "Call your structured question tool now / STOP / do not write as text / wait for selection" block) and reference it by name at each gate instead of repeating the full boilerplate five times.

Trim the opening preamble ("Before installing anything, you must understand the project. Identify what the project is built with...") since the section headings already convey this.

DimensionReasoningScore

Conciseness

The body is mostly dense, reference-style tables that assume Claude's competence, but the D5 blocking-question boilerplate ("Call your structured question tool now. ... STOP. Do not write the question as text. Do not continue until the user selects an option.") is repeated ~5 times and the opening preamble restates the headings, so it could be tightened.

2 / 3

Actionability

Guidance is concrete and specific for an instruction-only detection skill: exact indicator filenames (package.json, go.mod, pom.xml), exact entrypoint paths per stack, and a copy-paste-ready search string ("launchdarkly, ldclient, ld-client, LDClient, @launchdarkly, launchdarkly-").

3 / 3

Workflow Clarity

A clearly sequenced multi-step process (sections 1→6, SDK confirmation, decision tree) with explicit validation checkpoints — the D5 BLOCKING gates and the section 5a three-state workspace classification — and feedback loops ("re-run detection scoped to that folder").

3 / 3

Progressive Disclosure

Well-organized into clear sections with well-signaled, one-level-deep references (sibling skills via ../plan/SKILL.md, ../apply/SKILL.md, ../../first-flag/SKILL.md, and externalized SDK recipes at ../../references/sdk/recipes.md); the inline indicator tables are core operational content that belongs inline, and navigation pointers ("Next:") make routing easy.

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 is specific and well-scoped to a clear LaunchDarkly onboarding niche, but it lacks an explicit "Use when..." trigger clause and leans on technical vocabulary over natural user phrasings, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. "Use when onboarding a LaunchDarkly SDK into an existing repository and you need to identify its stack", to satisfy the completeness "when" requirement.

Surface natural user-facing terms ("tech stack", "identify languages and frameworks", "find existing LaunchDarkly usage") alongside the technical ones to improve trigger-term coverage.

Drop the intra-tree navigation tail ("Nested under sdk-install; next is plan.") from the description — it is structural metadata, not capability or trigger information.

DimensionReasoningScore

Specificity

Lists multiple concrete detection actions — "languages, frameworks, package managers, monorepo targets, entrypoints, existing LD usage" — matching the score-3 anchor of enumerating specific concrete actions rather than vague language.

3 / 3

Completeness

Clearly answers "what" (detect repository stack with the listed facets) but provides no "Use when..." trigger clause; the "when" is only implied by the onboarding context, which caps completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

Terms like "repository stack", "LaunchDarkly SDK onboarding", "monorepo targets", "entrypoints" are relevant but lean technical; common user phrasings (e.g. "tech stack", "identify my languages and frameworks") are missing, so coverage is partial rather than full.

2 / 3

Distinctiveness Conflict Risk

The niche is narrow and explicit — "Detect repository stack for LaunchDarkly SDK onboarding", nested under sdk-install — so it is unlikely to trigger for unrelated skills and matches the clear-niche anchor.

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: 11 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.