launchdarkly avatar

Launchdarkly Metric Choose

Before you spin up a LaunchDarkly experiment or guarded rollout, this skill helps you figure out which metrics to actually track. It checks what's already configured in your project's release policies so you don't duplicate guardrails, inventories which metrics have events flowing (avoiding the classic "why isn't this populating" problem), and makes typed recommendations based on context. For experiments, it pushes you to articulate your hypothesis first, then suggests a primary metric plus guardrails and counter-metrics. For guarded rollouts, it leans conservative since each metric is a potential rollback trigger. The workflow is advisory only: it won't create or attach anything, just tell you what makes sense given what you're trying to measure.

skills.sh installs
2.3K
GitHub stars
19
last updated
Jul 14, 2026

Install

$ npx -y skills add launchdarkly/agent-skills --skill launchdarkly-metric-choose --agent claude-code

Installs into .claude/skills of the current project.

Files

LaunchDarkly Metric Choose

You're using a skill that helps users select the right metrics before setting up an experiment, guarded rollout, or release policy. Your job is to understand the feature context, surface what will auto-attach from existing project policies, inventory what's available and healthy, and produce a clear typed recommendation.

This skill is advisory. It does not create metrics, attach them to experiments, or configure rollouts. For those tasks, see the related skills at the end of this document.

Prerequisites

This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment.

Required MCP tools:

  • get-metrics — inventory available metrics with their types and event keys
  • get-metric-events — check which event keys have recent activity

Optional MCP tools (enhance workflow):

  • get-release-policies — fetch project-level policies that configure which metrics auto-attach to guarded rollouts. Use this for the guarded rollout and release policy paths.

Workflow

Step 1: Identify the Context

Ask two questions upfront:

Sponsors

Details

Repository
github.com/launchdarkly/agent-skills
Category
AI & Agent Building
First seen
May 16, 2026

More from launchdarkly/agent-skills

All 41
1launchdarkly avatarlaunchdarkly-metric-createlaunchdarkly/agent-skillslaunchdarkly metric create2.3Kskills.sh installs
2mapbox avatarmapbox-geospatial-operationsmapbox/mapbox-agent-skillsExpert guidance on choosing the right geospatial tool based on problem type, accuracy requirements, and performance needs2.3Kskills.sh installs
3coinbase avatarfundcoinbase/agentic-wallet-skillsAdd money to the wallet. Use when you or the user want to fund, deposit, top up, load, buy USDC, add funds, onramp, or get USDC. Also use when the wallet has in2.3Kskills.sh installs
4k-dense-ai avatarexploratory-data-analysisk-dense-ai/scientific-agent-skillsPerform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ,2.3Kskills.sh installs
5xtone avatarcode-reviewxtone/ai_development_toolsPRやコード変更の汎用コードレビューを実施します。コードの品質、セキュリティ、設計を共通基準で評価し、approve/rejectを判断します。「このPRをレビュー」「コードレビューして」「マージ前チェック」などの依頼や、gh pr viewコマンドの実行時に使用してください。2.3Kskills.sh installs
6lingzhi227 avatarlatex-formattinglingzhi227/agent-research-skillsHandle LaTeX formatting, templates, and styling for academic papers. Set up conference templates (ICML, ICLR, NeurIPS, AAAI, ACL), fix formatting issues, manage2.3Kskills.sh installs