Name: projects
Rating: 61.6 (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

71%

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

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 well-structured and highly actionable with a clear validated workflow and proper progressive disclosure to real reference files. The only weakness is mild conceptual padding in the 'What Are Projects?' and naming-example sections that Claude does not need.

Suggestions

Trim or remove the 'What Are Projects?' explanatory section ('Projects are LaunchDarkly's top-level organizational containers... Think of projects as separate applications, services, or teams') since Claude already knows what LaunchDarkly projects are.

Condense the 'Common Organization Patterns' code blocks into a single compact list or move them into a reference file to reduce inline tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tables, lists, and code blocks, but it includes conceptual padding Claude already knows ('Projects are LaunchDarkly's top-level organizational containers... Think of projects as separate applications, services, or teams'), matching the 'mostly efficient but includes some unnecessary explanation' anchor.	2 / 3
Actionability	It provides concrete executable guidance — a real curl command with headers, runnable Python SDK verification code, specific env-var names for key detection, and good/bad naming examples — matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	A clear 5-step sequence (Explore, Assess, Choose Path, Implement, Verify) includes an explicit validation checkpoint in Step 5 (fetch to confirm existence, test SDK initialization, report results) plus error-recovery guidance (409 conflicts, jq shape handling), matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	SKILL.md serves as a concise overview with nine well-signaled, one-level-deep references in references/, all verified to exist, organized both by language and by use case with a dedicated References section — matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

57%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 clearly communicates the skill's purpose and domain but stays at a high level of abstraction without explicit trigger guidance. Adding a 'Use when...' clause with natural user phrases would lift completeness and trigger_term_quality.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrasings (e.g., 'Use when setting up LaunchDarkly projects, creating environments, or organizing flags by service/team/region').

Replace abstract verbs ('choose the right approach', 'makes sense for your architecture') with concrete capabilities (e.g., 'create projects, clone templates across regions, save SDK keys to .env or secrets managers').

Include common variation terms users would actually say (e.g., 'LaunchDarkly project', 'LD project', 'create environments', 'SDK keys') to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('assess your stack', 'choose the right approach', 'integrate project management') but the actions are high-level and abstract rather than concrete and comprehensive, matching the 'names domain and some actions' anchor rather than the 'lists multiple specific concrete actions' anchor.	2 / 3
Completeness	It clearly answers 'what does this do' but provides no explicit 'when should Claude use it' trigger guidance; per the guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant domain keywords ('LaunchDarkly projects', 'codebase', 'stack') but lacks natural user phrasings and common variations, sitting at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The 'LaunchDarkly projects' niche is distinct and unlikely to trigger for unrelated skills; mild overlap with sibling LaunchDarkly skills is not enough to drop it below the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 12 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: 3 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.