@skills · Owner
Agent skills by launchdarkly
51 skills indexed from github.com/launchdarkly. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.
- agent-graphs · Skill · 24 stars
Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs ro
- agent-skills · Collection · 24 stars
- agentcontrol · Collection · 24 stars
- aiconfig-agent-graphs · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to agent-graphs. Do not use this skill; invoke agent-graphs instead. Kept only so old references to aiconfig-a
- aiconfig-ai-metrics · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to built-in-metrics. Do not use this skill; invoke built-in-metrics instead. Kept only so old references to ai
- aiconfig-create · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to configs-create. Do not use this skill; invoke configs-create instead. Kept only so old references to aiconf
- aiconfig-custom-metrics · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to custom-metrics. Do not use this skill; invoke custom-metrics instead. Kept only so old references to aiconf
- aiconfig-migrate · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to migrate. Do not use this skill; invoke migrate instead. Kept only so old references to aiconfig-migrate sti
- aiconfig-online-evals · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to online-evals. Do not use this skill; invoke online-evals instead. Kept only so old references to aiconfig-o
- aiconfig-projects · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to projects. Do not use this skill; invoke projects instead. Kept only so old references to aiconfig-projects
- aiconfig-snippets · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to snippets. Do not use this skill; invoke snippets instead. Kept only so old references to aiconfig-snippets
- aiconfig-targeting · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to configs-targeting. Do not use this skill; invoke configs-targeting instead. Kept only so old references to
- aiconfig-tools · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to tools. Do not use this skill; invoke tools instead. Kept only so old references to aiconfig-tools still poi
- aiconfig-update · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to configs-update. Do not use this skill; invoke configs-update instead. Kept only so old references to aiconf
- aiconfig-variations · Skill · 24 stars
DEPRECATED redirect — this skill was renamed to configs-variations. Do not use this skill; invoke configs-variations instead. Kept only so old references t
- alert-investigation · Skill · 24 stars
Investigates a triggered observability alert and returns a structured diagnosis with likely cause, scope, and next steps.
- built-in-metrics · Skill · 24 stars
Instrument an existing codebase with LaunchDarkly config tracking. Walks the four-tier ladder (managed runner → provider package → custom extractor + track
- configs-create · Skill · 24 stars
Create and configure configs in LaunchDarkly. Helps you choose between agent vs completion mode, create the config, add variations with models and prompts,
- configs-targeting · Skill · 24 stars
Configure config targeting rules to control which variations serve to different users. Enable percentage rollouts, attribute-based rules, segment targeting
- configs-update · Skill · 24 stars
Update, archive, and delete LaunchDarkly configs and their variations. Use when you need to modify config properties, change model parameters, update instr
- configs-variations · Skill · 24 stars
Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters to find what works best through syste
- create-fix-pr · Skill · 24 stars
Investigates a root cause and files a minimal fix PR for a reported bug or observability finding.
- create-graph · Skill · 24 stars
Creates observability dashboards and graphs from logs, traces, errors, sessions, metrics, and events data by previewing charts inline and saving them to a
- custom-metrics · Skill · 24 stars
Create, track, retrieve, update, and delete custom business metrics for configs. Covers full lifecycle: define metric kinds via API, emit events via SDK, a
- experiments · Collection · 24 stars
- feature-flags · Collection · 24 stars
- flag-and-release-change · Skill · 24 stars
Drive a pull request's change end to end: decide it's flag-worthy, create the guarding flag, wire the new code path behind it on the PR branch, and record
- flag-release · Skill · 24 stars
Record an automated rollout for an existing LaunchDarkly flag that guards a pull request's change, so the change releases safely when the PR merges. Honors
- investigate · Skill · 24 stars
Analyzes observability data — logs, traces, errors, sessions, and metrics — to find root cause and actionable evidence. Use when the user reports a bug, an
- launchdarkly-experiment-setup · Skill · 24 stars
Set up and run experiments in LaunchDarkly. Create experiments with metrics, treatments, and flag config, start iterations to collect data, swap design bet
- launchdarkly-flag-cleanup · Skill · 24 stars
Safely remove a feature flag from code while preserving production behavior. Use when the user wants to remove a flag from code, delete flag references, or
- launchdarkly-flag-command · Skill · 24 stars
Resolve `/flag` style requests into the right LaunchDarkly flag lookup flow. Use when the user types `/flag`, asks to quickly find a flag by name/key, want
- launchdarkly-flag-create · Skill · 24 stars
Create and configure LaunchDarkly feature flags in a way that fits the existing codebase. Use when the user wants to create a new flag, wrap code in a flag
- launchdarkly-flag-discovery · Skill · 24 stars
Audit your LaunchDarkly feature flags to understand the landscape, find stale or launched flags, and assess removal readiness. Use when the user asks about
- launchdarkly-flag-drift · Skill · 24 stars
Detect and reconcile drift between a feature flag's in-code SDK fallback default and its LaunchDarkly default rule (fallthrough). Use when a flag's default
- launchdarkly-flag-qualitative-feedback-setup · Skill · 24 stars
Integrate LaunchDarkly qualitative user feedback into a JavaScript/TypeScript codebase. Guides framework and design system detection, builds the sendFeedba
- launchdarkly-flag-targeting · Skill · 24 stars
Control LaunchDarkly feature flag targeting including toggling flags on/off, percentage rollouts, targeting rules, individual targets, and copying flag con
- launchdarkly-guarded-rollout · Skill · 24 stars
Configure guarded rollouts with progressive traffic increases, metric monitoring, and automatic rollback. Use when releasing features gradually with safety
- launchdarkly-metric-choose · Skill · 24 stars
Choose the right metrics for a LaunchDarkly experiment, guarded rollout, or release policy. Use when the user wants to know which metrics to use, which is
- launchdarkly-metric-create · Skill · 24 stars
Create a LaunchDarkly metric that measures what matters for an experiment or rollout. Use when the user wants to create a metric, track an event, measure p
- launchdarkly-metric-instrument · Skill · 24 stars
Instrument a LaunchDarkly metric event in a codebase by adding a track() call. Use when the user wants to wire up an event, instrument an action for a metr
- metrics · Collection · 24 stars
- migrate · Skill · 24 stars
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move th
- observability · Collection · 24 stars
- onboarding · Skill · 24 stars
Scripted onboarding for LaunchDarkly: quiet execution, fixed sequence, SDK install, first flag with a live reveal, MCP offered afterwards. Enforces step co
- online-evals · Skill · 24 stars
Attach judges to config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.
- projects · Skill · 24 stars
Guide for setting up LaunchDarkly projects in your codebase. Helps you assess your stack, choose the right approach, and integrate project management that
- should-flag-change · Skill · 24 stars
Decide whether a given code change should be placed behind a LaunchDarkly feature flag. Use when a developer asks whether a change should be behind a flag,
- skills · Collection · 24 stars
- snippets · Skill · 24 stars
Create and manage prompt snippets — reusable text blocks referenced inside config variation prompts. Keeps common instructions, personas, and guardrails co
- tools · Skill · 24 stars
Give your agents capabilities through tools (function calling). Helps you identify what your agent needs to do, create tool definitions, and attach them to