Index of every page on this site: llms.txt
All skills
launchdarkly avatar

/launchdarkly-flag-qualitative-feedback-setup

@f0ee110 official
Run it yourself

Integrate LaunchDarkly qualitative user feedback into a JavaScript/TypeScript codebase. Guides framework and design system detection, builds the sendFeedback utility and feedback widget matching existing project patterns. Use when the user wants to add a Give Feedback widget, collect user sentiment tied to feature flags, set up feedback collection, or wire up the $ld:feedback tracking event.

Use this Skill: https://skilld.dev/gh/launchdarkly/ai-tooling/launchdarkly-flag-qualitative-feedback-setup

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

README.md

≈1.2k tokens on demand. Your agent reads this file only when SKILL.md points to it.

LaunchDarkly Qualitative Feedback Skill

An Agent Skill that walks users through a step-by-step wizard to add LaunchDarkly's qualitative user feedback feature to a JavaScript/TypeScript codebase, adapting to the project's framework and design system.

Overview

This skill guides users through an interactive wizard:

  1. Verify setup — checks the SDK (client-side, v3.0+), framework, and design system
  2. Gather requirements — asks about the target flag, prompt text, feedback type, and widget placement
  3. Verify the flag — confirms or creates the flag in LaunchDarkly
  4. Confirm the plan — summarizes planned changes and waits for approval
  5. Generate code — creates the sendFeedback utility and feedback widget matching existing project patterns
  6. Verify — confirms the build passes and everything is wired up correctly

Along the way the skill:

  • Detects the UI framework (React, Vue, Angular, Svelte, vanilla JS) and design system (MUI, Chakra, shadcn, Tailwind, etc.)
  • Identifies or creates the feature flag to attach feedback to
  • Optionally links feedback to session replays via LaunchDarkly observability

Widget Styles

The skill asks two questions to determine the widget style: feedback type and icon style.

Feedback type:

Type Description
Sentiment + text Popover with sentiment buttons and a text area for comments
Sentiment only Inline one-click sentiment buttons, no popover or text input
Text only Popover with a text area, no sentiment buttons

Icon style (when sentiment is involved):

Style Buttons
Thumbs up / down Two buttons: positive / negative
Smiley faces Three buttons: positive / neutral / negative

This produces five widget variants:

Type Icons Template
Sentiment + text Thumbs PopoverFeedback with icons="thumbs"
Sentiment + text Smileys PopoverFeedback with icons="smileys"
Sentiment only Thumbs InlineFeedback with icons="thumbs"
Sentiment only Smileys InlineFeedback with icons="smileys"
Text only — PopoverFeedback with icons="none"

All widget components accept flagKey and prompt as props and track a submitted state that replaces the widget with a confirmation message after feedback is sent.

Installation (Local)

For now, install by placing this skill directory where your agent client loads skills.

Examples:

  • Generic: copy skills/feature-flags/launchdarkly-flag-qualitative-feedback-setup/ into your client's skills path

Prerequisites

This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment. The remote server provides higher-level, agent-optimized tools that orchestrate multiple API calls and return pruned, actionable responses.

The target application must use the LaunchDarkly JavaScript SDK v3.0+ (client-side).

Usage

Once installed, the skill activates automatically when a user asks about collecting user feedback:

Add a Give Feedback widget for my new search feature
Set up qualitative feedback collection on the checkout-redesign flag
I want to collect user sentiment on my feature rollout
Wire up the LaunchDarkly feedback popover using our shadcn components

Structure

launchdarkly-flag-qualitative-feedback-setup/
├── SKILL.md                       # Wizard workflow and agent instructions
├── marketplace.json
├── README.md
└── references/
    ├── client-side-sdk-list.md    # SDK packages that support qualitative feedback
    ├── server-side-sdk-list.md    # SDK packages that do NOT support qualitative feedback
    ├── sendFeedback.ts            # Template: sends $ld:feedback event with session replay support
    ├── PopoverFeedback.tsx        # Template: popover with text area + configurable sentiment icons
    └── InlineFeedback.tsx         # Template: inline one-click sentiment buttons

Related

License

Apache-2.0

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts11d3 checks · Risk SAFE
  • Gen Agent Trust Hub15d

    This skill provides a secure, step-by-step wizard for integrating LaunchDarkly qualitative feedback widgets into JavaScript or TypeScript projects. It features extensive user confirmation gates, uses official vendor resources, and generates code with built-in data sanitization.

  • Socket11d

    No alerts

  • Snyk15d

    Risk: LOW · No issues

Signed by skilld at f0ee110. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago
compatibility
Requires the remotely hosted LaunchDarkly MCP server
metadata
{
  "author": "launchdarkly",
  "version": "1.0.0-experimental"
}

README badge

README badge for launchdarkly/ai-tooling/launchdarkly-flag-qualitative-feedback-setup