CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

projects

Guide for setting up LaunchDarkly projects in your codebase. Helps you assess your stack, choose the right approach, and integrate project management that makes sense for your architecture.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/agentcontrol/projects/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

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

The content is a strong, highly actionable workflow: concrete MCP tools, executable verification code with expected outputs, and a clear five-step process with real validation checkpoints. Its weaknesses are mild verbosity (conceptual explanations and a duplicated reference list) and small navigation inconsistencies in the references section.

Suggestions

Trim the 'What Are Projects?' section to one or two lines and remove editorial sentences like 'Think of projects as separate applications...' to tighten conciseness.

Remove the duplicated reference listing: keep the links in Step 3 (where they are chosen) or in the final References section, not both, and include multi-language-setup.md in whichever list remains.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands and code, but includes unnecessary padding: the 'What Are Projects?' conceptual explanation, 'Think of projects as separate applications...' , and a References list duplicated between Step 3 and the final section. It sits at anchor 3 (mostly efficient with some unnecessary explanation) rather than 4, since multiple sections could be trimmed.

3 / 5

Actionability

Fully executable guidance throughout: named MCP tools (create-project, get-projects, get-sdk-key), a copy-paste curl verification command with jq shape-handling, and complete Python and Node.js SDK verification snippets with expected outputs and failure signatures ('HTTP error 401', 'LDTimeoutError'). Specific examples cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

A clear five-step sequence with an explicit validation checkpoint in Step 5: fetch to confirm the project exists, test SDK initialization with described error-recovery behavior (jq shape variance, invalid-key outcomes), and a report-results checklist. This matches the anchor for clear sequencing with explicit validation and error-recovery feedback.

5 / 5

Progressive Disclosure

The body is a well-organized overview pointing to nine real, one-level-deep reference files in ./references/, sorted by stack and by use case, which satisfies the bundle-structure guideline. It falls short of 5 only due to minor organization gaps: the reference list is duplicated (Step 3 and final References section) and multi-language-setup.md is omitted from the final References list.

4 / 5

Total

17

/

20

Passed

Description

53%Weight 40%Scale 1-5

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 clearly identifies its domain and purpose but reads more like a summary than a trigger. It lacks any 'Use when...' guidance and its action verbs are process-level rather than concrete capabilities. Adding explicit trigger conditions and concrete actions (create projects, retrieve SDK keys, clone projects) would raise it substantially.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user mentions LaunchDarkly, setting up a LaunchDarkly project, creating projects for new services, or needing SDK keys for an environment.'

Replace process-generic verbs with concrete capabilities: 'Create LaunchDarkly projects, retrieve environment SDK keys, clone projects across regions/teams, and save keys to your app's config.'

Include natural trigger synonyms users would actually say (e.g., 'feature flags', 'environments', 'SDK key') to improve trigger_term_quality and distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain ('setting up LaunchDarkly projects') and lists actions ('assess your stack, choose the right approach, and integrate project management'), but these are process-generic verbs rather than concrete capabilities like creating projects or retrieving SDK keys. It matches anchor 3 (domain plus 1-2 concrete actions) better than anchor 4, whose examples list specific concrete operations.

3 / 5

Completeness

The 'what' is clear (guide for setting up LaunchDarkly projects in a codebase), but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

'LaunchDarkly' and 'projects' are relevant keywords users would say, but common natural phrasings such as 'create a LaunchDarkly project', 'SDK key', 'feature flags', or 'environments' are absent. Some relevant keywords exist but common variations and synonyms are missing, matching anchor 3.

3 / 5

Distinctiveness Conflict Risk

'LaunchDarkly projects' carves out a clear niche with minimal conflict risk against unrelated skills. It is not a 5 because 'projects' alone is generic and there is minor overlap risk with closely related sibling LaunchDarkly skills (configs-create, sdk-install).

4 / 5

Total

13

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

launchdarkly/ai-tooling

Path

skills/agentcontrol/projects/SKILL.md

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.