Name: projects
Rating: 56.00000000000001 (1 reviews)
Author: launchdarkly

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

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/agentcontrol/projects/SKILL.md

Quality

Content

71%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 body is a well-structured overview with a clear 5-step workflow, executable verification snippets, and clean one-level-deep references that all resolve to real files. Its main weakness is mild verbosity in the meta introduction and concept explainer rather than any structural gap.

Suggestions

Trim the opening meta paragraph ('You're using a skill that will guide you through...') since it restates the description without adding actionable guidance.

Tighten or move the 'What Are Projects?' explainer into a reference, keeping only the LaunchDarkly-specific facts Claude would not already know.

Make the verification feedback loop explicit: state what to do if the SDK fails to initialize (e.g. check key validity / environment) before reporting, to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete tables, code, and edge cases rather than explaining general concepts Claude knows, but the meta opening paragraph ('You're using a skill that will guide you through...') and the 'What Are Projects?' explainer add length that could be trimmed, fitting the 3-anchor over the leaner 4-anchor.	3 / 5
Actionability	It provides executable curl, jq, and Python SDK snippets plus specific API-key detection steps and good/bad project-key examples; per-language implementation is delegated to reference files, leaving only minor gaps consistent with the 4-anchor rather than fully copy-paste-ready 5-anchor coverage.	4 / 5
Workflow Clarity	A clear 5-step sequence (Explore, Assess, Choose, Implement, Verify) includes an explicit Verify checkpoint with a results checklist and 409-conflict error handling, but the validate-fix-retry loop on SDK-init failure is only implied, so it lands at 4 rather than 5.	4 / 5
Progressive Disclosure	The SKILL.md is a clear overview with well-signaled, one-level-deep references split by 'Language/Stack' and 'Use Case', and all 9 referenced files exist in ./references/, matching the clear-overview easy-navigation 5-anchor.	5 / 5
	Total	16 / 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 names its domain and three high-level actions but stops short of concrete capabilities and omits any explicit 'Use when' trigger guidance, which caps completeness. It is distinct within the LaunchDarkly niche with only minor sibling-skill overlap.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases, e.g. 'Use when setting up a new LaunchDarkly project, creating projects per service/region, or organizing flags and environments.'

Replace generic process verbs ('assess your stack', 'choose the right approach') with concrete capabilities (e.g. 'create projects, clone templates across regions, and save SDK keys to your environment config').

Add natural keyword variations a user might say, such as 'create a LaunchDarkly project' or 'organize feature flags by team', to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('setting up LaunchDarkly projects') and three actions ('assess your stack', 'choose the right approach', 'integrate project management'), but the actions are high-level process verbs rather than concrete capabilities, and 'makes sense for your architecture' is padding, so it sits at the 3-anchor rather than 4.	3 / 5
Completeness	It clearly answers 'what' ('Guide for setting up LaunchDarkly projects in your codebase') but provides no 'Use when...' clause or equivalent trigger guidance, so per the rubric guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	The natural phrase 'LaunchDarkly projects' is present, but coverage is limited to that single keyword with no common variations or synonyms (e.g. 'create a LaunchDarkly project', 'feature flags', 'project setup'), matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'LaunchDarkly projects' is a clear niche, but the skill family includes closely related skills (sdk, configs-create) covering adjacent concerns, giving minor overlap risk consistent with the 4-anchor rather than the minimal-conflict 5-anchor.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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
Commit: add614f

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.