launchdarkly/agent-skills
41 skills92.1k installs820 starsGitHub
Install
npx skills add https://github.com/launchdarkly/agent-skillsSkills in this repo
1Onboardingonboarding orchestrates LaunchDarkly setup in an existing codebase through Steps 0-6 plus follow-through documentation. Kickoff shows a roadmap, creates native task tracking, and runs Steps 0-3 silently: write LAUNCHDARKLY_ONBOARDING.md resumable log, explore language and framework, detect agent environment, and install launchdarkly-flag companion skills via npx skills add. Step 4 configures hosted MCP with OAuth through mcp-configure; get-environments supplies SDK keys and create-feature-flag supports Step 6. Step 5 runs nested sdk-install detect, plan, and apply with blocking D5 SDK scope, D7 secret consent, and D8 dependency approval gates. Step 6 creates a first boolean flag, evaluates, toggles, and adds an interactive demo via first-flag. Core principles: detect do not guess, minimal changes, match existing env patterns, validate end to end, and defer credential questions until MCP OAuth or D7. Resuming reads LAUNCHDARKLY_ONBOARDING.md and continues from the logged next step. Success replaces the working log with LAUNCHDARKLY.md and editor rules. Requires npx on PATH and infers account status through OAuth rather than asking upfront.3.8kinstalls2Launchdarkly Flag DiscoveryLaunchDarkly Flag Discovery audits feature flag inventory in a LaunchDarkly project using the hosted MCP server. Prerequisites require list-flags, get-flag, and get-flag-status-across-envs, with optional find-stale-flags, get-flag-health, and check-removal-readiness for deeper analysis. Workflow starts by confirming projectKey and whether the user wants a broad audit, targeted investigation, or cleanup planning. Broad audits list flags in production, segment by state and temporary versus permanent type, and summarize scale. Cleanup planning prioritizes find-stale-flags candidates such as never_requested, inactive_30d, and launched_no_changes with tunable inactiveDays. Targeted reviews use get-flag-health for lifecycle, last requested, targeting complexity, and cross-environment consistency. Categorization groups flags into ready to remove, likely safe, needs investigation, or leave alone, respecting that launched means fully rolled out and inactive may still be referenced in unreleased code. check-removal-readiness returns safe, caution, or blocked verdicts. Weights in API responses scale by 1000 and must convert to percentages. Discovery only; cleanup and targeting changes delega.3kinstalls3Launchdarkly Flag CleanupThe launchdarkly-flag-cleanup skill removes feature flags from code while preserving production behavior after rollouts complete. Prerequisites require the hosted LaunchDarkly MCP server with check-removal-readiness orchestrating flag config, cross-environment status, dependencies, code references, and expiring targets, plus get-flag for per-environment forward values. Workflow explores codebase references including variation, boolVariation, useFlags, constants, tests, and wrappers before querying LaunchDarkly rather than guessing values. Readiness returns safe, caution, or blocked verdicts; blocked states stop until dependents or active targeting resolve. Forward value selection uses fallthrough.variation when all critical environments are ON with matching rules, or offVariation when uniformly OFF; differing ON states or variations across environments are not safe. Users must confirm a cleanup plan listing forward value, file references, planned edits, readiness verdict, and archive intent before edits. Removal keeps the winning branch, deletes dead code and flag-only imports, and avoids unrelated refactors. Verification runs build, lint, tests, and a final flag key search.3kinstalls4Launchdarkly Flag CreateThe launchdarkly-flag-create skill introduces new feature flags that match how the codebase already evaluates flags. Step one explores SDK imports, wrapper utilities, constant key files, variation call patterns, and context construction before creating anything. Step two picks boolean or multivariate flag kinds from user intent: toggles and rollouts use boolean true/false; A/B tests and config objects use multivariate string, number, or JSON variations. Defaults mark flags temporary unless the user says permanent, generate keys from names in the project's naming style, and suggest tags from feature context. Step three calls create-flag via the LaunchDarkly MCP server; new flags start with targeting OFF in all environments serving offVariation. Step four adds evaluation code using the same wrapper and default-fallback patterns, wrapping new behavior with safe existing-behavior defaults when the SDK is unreachable. Step five verifies compile/lint, get-flag confirmation, and both on/off code paths. Requires LaunchDarkly MCP with create-flag and get-flag. Flag keys are immutable; use the flag-targeting skill to enable rollouts after creation.3kinstalls5Launchdarkly Flag TargetingThe launchdarkly-flag-targeting skill changes who sees which variation for existing LaunchDarkly flags. Evaluation order matters: OFF serves offVariation; individual targets win; custom rules evaluate top to bottom; default fallthrough applies last. Step one confirms environment, fetches get-flag state including on, fallthrough, rules, targets, and prerequisites. Step two maps user intent to toggle-flag, update-rollout with percentage weights summing to 100, update-targeting-rules, update-individual-targets, or copy-flag-config between environments. Step three runs the safety checklist: correct environment, approval-required responses, prerequisite flags, rule ordering impact, and audit comments especially in production. Step four applies mutations; human-friendly percentages like 80 mean 80 percent. Step five re-fetches and describes resulting behavior in plain language. When requiresApproval is true, create approval requests instead of bypassing, then apply after review. Launched flags remain ON; cleanup skill handles removal. Requires LaunchDarkly MCP with get-flag, toggle-flag, update-rollout, update-targeting-rules, and update-individual-targets.3kinstalls6Launchdarkly Metric ChooseYou 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 This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment Required MCP tools list metrics inventory available metrics with their types and event keys list metric events check which event keys have recent activity Optional MCP tools enhance workflow list release policies fetch project level policies that configure which metrics auto attach to guarded rollouts Use this for the guarded rollout and release policy paths2.7kinstalls7Launchdarkly Metric CreateYou re using a skill that will guide you through creating a LaunchDarkly metric For custom metrics getting events flowing comes first before the metric is created Your job is to determine the right metric kind instrument the event if it isn t already flowing including SDK setup and environment wiring check for duplicates propose a metric config get explicit confirmation then create and verify This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment Required MCP tools create metric create the metric get metric verify it after creation get environment fetch the client side SDK key when instrumenting Optional MCP tools enhance workflow list metrics check for existing metrics with the same event key and understand naming conventions list metric events discover which event keys have recent activity before committing to one custom metrics only Two Different Projects Never Confuse Them2.7kinstalls8Launchdarkly Metric InstrumentYou re using a skill that will guide you through adding a track call to a codebase so a LaunchDarkly metric can measure it Your job is to detect the SDK in use find the right place in code to add the call write it correctly and verify that events are reaching LaunchDarkly This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment Required MCP tools list metric events verify events are flowing after instrumentation Optional MCP tools enhance workflow get project retrieve the SDK key for the right environment when SDK initialization is needed Before writing any code understand the LaunchDarkly setup already in this codebase The launchdarkly metric instrument agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.7kinstalls9Aiconfig ToolsThis skill has been renamed Do not follow any instructions here and do not perform the task from this skill Invoke the tools skill instead it contains the current complete instructions If you arrived here from an old reference documentation a saved prompt or automation update it from aiconfig tools to tools The aiconfig tools agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.6kinstalls10Aiconfig ProjectsThis skill has been renamed Do not follow any instructions here and do not perform the task from this skill Invoke the projects skill instead it contains the current complete instructions If you arrived here from an old reference documentation a saved prompt or automation update it from aiconfig projects to projects The aiconfig projects agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.6kinstalls11Aiconfig CreateDeprecated renamed to configs create This skill has been renamed Do not follow any instructions here and do not perform the task from this skill Invoke the configs create skill instead it contains the current complete instructions If you arrived here from an old reference documentation a saved prompt or automation update it from aiconfig create to configs create The aiconfig create agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.6kinstalls12Aiconfig UpdateDeprecated renamed to configs update This skill has been renamed Do not follow any instructions here and do not perform the task from this skill Invoke the configs update skill instead it contains the current complete instructions If you arrived here from an old reference documentation a saved prompt or automation update it from aiconfig update to configs update The aiconfig update agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.6kinstalls13Aiconfig VariationsDeprecated renamed to configs variations This skill has been renamed Do not follow any instructions here and do not perform the task from this skill Invoke the configs variations skill instead it contains the current complete instructions If you arrived here from an old reference documentation a saved prompt or automation update it from aiconfig variations to configs variations The aiconfig variations agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.6kinstalls14Aiconfig TargetingDeprecated renamed to configs targeting This skill has been renamed Do not follow any instructions here and do not perform the task from this skill Invoke the configs targeting skill instead it contains the current complete instructions If you arrived here from an old reference documentation a saved prompt or automation update it from aiconfig targeting to configs targeting The aiconfig targeting agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.5kinstalls15Aiconfig Online EvalsThis skill has been renamed Do not follow any instructions here and do not perform the task from this skill Invoke the online evals skill instead it contains the current complete instructions If you arrived here from an old reference documentation a saved prompt or automation update it from aiconfig online evals to online evals The aiconfig online evals agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.5kinstalls16Launchdarkly Experiment SetupThe launchdarkly-experiment-setup skill "Set up and run experiments in LaunchDarkly. Create experiments with metrics, treatments, and flag config, start iterations to collect data, swap design between iterations, and stop with a winner." It covers create-experiment - create a new experiment with its initial iteration hypothesis, metrics, treatments, flag config .. Key workflows include start-experiment-iteration - begin collecting data for an experiment's current draft iteration.. Step 1: Prepare Metrics 1. Use list-metrics to find existing metrics. 2. If you need a new one, use create-metric and note the key. 3. Decide which is the primary metric a single metric or a funnel group . You'll pass its key as primarySingleMetricKey or primaryFunnelKey on the iteration. | Goal | Metric type | Example key | |------|-------------|-------------| | Conversion | Custom conversion | c Developers invoke launchdarkly-experiment-setup when the task matches the triggers and reference files in SKILL.md for grounded, stepwise execution.2.4kinstalls17Launchdarkly Guarded RolloutThe launchdarkly-guarded-rollout skill "Configure guarded rollouts with progressive traffic increases, metric monitoring, and automatic rollback. Use when releasing features gradually with safety thresholds." It covers start-guarded-rollout -- start a progressive rollout with monitoring. Key workflows include get-flag -- inspect the flag and its variations. Step 1: Prepare Before starting a guarded rollout: 1. Use get-flag to inspect the flag - note the variation IDs for test and control 2. Use list-metrics to find metrics suitable for monitoring 3. Ensure the flag is on in the target environment use toggle-flag if needed 4. Confirm there's no active guarded rollout on this flag already Step 2: Design Stages Plan the rollout progression. A typical Developers invoke launchdarkly-guarded-rollout when the task matches the triggers and reference files in SKILL.md for grounded, stepwise execution.2.4kinstalls18Aiconfig MigrateDEPRECATED redirect this skill was renamed to migrate Do not use this skill invoke migrate instead Kept only so old references to aiconfig-migrate still point users to the new name name aiconfig-migrate description DEPRECATED redirect this skill was renamed to migrate Do not use this skill invoke migrate instead Kept only so old references to aiconfig-migrate still point users to the new name license Apache-2 0 metadata version 0 1 0 Deprecated renamed to migrate This skill has been renamed Do not follow any instructions here and do not perform the task from this skill Invoke the migrate skill instead it contains the current complete instructions If you arrived here from an old reference documentation a saved prompt or automation update it from aiconfig-migrate to migrate name aiconfig-migrate description DEPRECATED redirect this skill was renamed to migrate Do not use this skill invoke migrate instead Kept only so old references to aiconfig-migrate still point users to the new name license Apache-2 0 metadata version 0 1 0 Deprecated renamed to2.4kinstalls19Aiconfig Ai MetricsDEPRECATED 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 aiconfig-ai-metrics still point users to the new name name aiconfig-ai-metrics description 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 aiconfig-ai-metrics still point users to the new name license Apache-2 0 metadata version 0 1 0 Deprecated renamed to built-in-metrics This skill has been renamed Do not follow any instructions here and do not perform the task from this skill Invoke the built-in-metrics skill instead it contains the current complete instructions If you arrived here from an old reference documentation a saved prompt or automation update it from aiconfig-ai-metrics to built-in-metrics name aiconfig-ai-metrics description 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 aiconfig-ai-metrics still point users to the new name license Apache-2 0 metadata version 0 1 0 Deprecated renamed to2.4kinstalls20Aiconfig Custom MetricsDEPRECATED redirect this skill was renamed to custom-metrics Do not use this skill invoke custom-metrics instead Kept only so old references to aiconfig-custom-metrics still point users to the new name name aiconfig-custom-metrics description DEPRECATED redirect this skill was renamed to custom-metrics Do not use this skill invoke custom-metrics instead Kept only so old references to aiconfig-custom-metrics still point users to the new name license Apache-2 0 metadata version 0 1 0 Deprecated renamed to custom-metrics This skill has been renamed Do not follow any instructions here and do not perform the task from this skill Invoke the custom-metrics skill instead it contains the current complete instructions If you arrived here from an old reference documentation a saved prompt or automation update it from aiconfig-custom-metrics to custom-metrics name aiconfig-custom-metrics description DEPRECATED redirect this skill was renamed to custom-metrics Do not use this skill invoke custom-metrics instead Kept only so old references to aiconfig-custom-metrics still point users to the new name license Apache-2 0 metadata version 0 1 0 Deprecated renamed to2.3kinstalls21ApplyApply LaunchDarkly SDK onboarding: install dependency (or dual-SDK pair), configure env and secrets with consent, add init at entrypoint(s), verify compile. Nested under sdk-install; next is run. The apply skill documents workflows and patterns from the repository SKILL.md. --- name: apply description: "Apply LaunchDarkly SDK onboarding: install dependency (or dual-SDK pair), configure env and secrets with consent, add init at entrypoint(s), verify compile. Nested under sdk-install; next is run." license: Apache-2.0 compatibility: Requires integration plan and LaunchDarkly credentials (see parent onboarding) metadata: author: launchdarkly version: "0.2.0" --- # Apply code changes (SDK install) Execute the integration plan. Install the SDK(s) and add the minimal code needed to initialize **each** tracked surface. This skill is nested under [LaunchDarkly SDK Install (onboarding)](../SKILL.md); the parent **Step 3** is **apply**. **Prior:** [Generate integration plan](../plan/SKILL.md). **Next:** [Start the application](../run/SKILL.md).2.3kinstalls22DetectDetect repository stack for LaunchDarkly SDK onboarding: languages, frameworks, package managers, monorepo targets, entrypoints, existing LD usage. Nested under sdk-install; next is plan. The detect skill documents workflows and patterns from the repository SKILL.md. --- name: detect description: "Detect repository stack for LaunchDarkly SDK onboarding: languages, frameworks, package managers, monorepo targets, entrypoints, existing LD usage. Nested under sdk-install; next is plan." license: Apache-2.0 compatibility: Requires access to the project repository metadata: author: launchdarkly version: "0.1.0" --- # Detect repository stack (SDK install) Before installing anything, you must understand the project. Identify what the project is built with and whether LaunchDarkly is already present. This skill is nested under [LaunchDarkly SDK Install (onboarding)](../SKILL.md); the parent **Step 1** is **detect**. **Next:** [Generate integration plan](../plan/SKILL.md) unless the decision tree sends you elsewhere. Language and framework Look for the indicator files below (and related root layout), then read the relevant manifests to infer language and framework.2.3kinstalls23First FlagCreate a boolean first flag add evaluation toggle on off for end-to-end proof Parent onboarding Step 6 uses MCP API or ldcli optional flag-create skill The first-flag skill documents workflows and patterns from the repository SKILL md name first-flag description Create a boolean first flag add evaluation toggle on off for end-to-end proof Parent onboarding Step 6 uses MCP API or ldcli optional flag-create skill license Apache-2 0 compatibility Requires SDK installed parent Step 5 and LaunchDarkly project access metadata author launchdarkly version 0 1 0 Create first feature flag The SDK is connected Now help the user create their first feature flag and see it work end-to-end This skill is nested under LaunchDarkly onboarding SKILL md the parent Step 6 is first flag Prior Apply code changes sdk-install apply SKILL md Optional Flag Create skill already installed If the launchdarkly-flag-create skill from github com launchdarkly ai-tooling https github com launchdarkly ai-tooling is available in the session install with npx skills add launchdarkly ai-tooling skill launchdarkly-flag-create y agent agent you2.3kinstalls24Mcp ConfigureConfigure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP). Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents. OAuth authentication; no API keys for the hosted server. The mcp-configure skill documents workflows and patterns from the repository SKILL.md. --- name: mcp-configure description: "Configure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP). Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents. OAuth authentication; no API keys for the hosted server." license: Apache-2.0 compatibility: Requires an MCP-compatible coding agent and a LaunchDarkly account metadata: author: launchdarkly version: "0.1.0" --- # LaunchDarkly MCP Server Configuration (onboarding) Configures the LaunchDarkly hosted MCP server so flag management skills and onboarding can use MCP tools. Uses OAuth for authentication - no API keys needed for the hosted server.2.3kinstalls25PlanGenerate a minimal LaunchDarkly SDK integration plan from detected stack: choose SDK type(s), dual-SDK server+client when required, files to change, env conventions. Nested under sdk-install; follows detect, precedes apply. The plan skill documents workflows and patterns from the repository SKILL.md. --- name: plan description: "Generate a minimal LaunchDarkly SDK integration plan from detected stack: choose SDK type(s), dual-SDK server+client when required, files to change, env conventions. Nested under sdk-install; follows detect, precedes apply." license: Apache-2.0 compatibility: Requires completed or equivalent detect context (see sibling detect skill) metadata: author: launchdarkly version: "0.2.0" --- # Generate integration plan (SDK install) Based on what you detected, choose the right SDK and plan the minimal set of changes needed. This skill is nested under [LaunchDarkly SDK Install (onboarding)](../SKILL.md); the parent **Step 2** is **plan**. **Prior:** [Detect repository stack](../detect/SKILL.md).2.3kinstalls26Sdk InstallInstall and initialize the correct LaunchDarkly SDK during onboarding by running nested skills in order: detect, plan, apply. Parent onboarding Step 6 is first flag. The sdk-install skill documents workflows and patterns from the repository SKILL.md. --- name: sdk-install description: "Install and initialize the correct LaunchDarkly SDK during onboarding by running nested skills in order: detect, plan, apply. Parent onboarding Step 6 is first flag." license: Apache-2.0 compatibility: Requires a supported language/framework in the project. SDK credentials are required by [Apply](apply/SKILL.md), not for [Detect](detect/SKILL.md) / [Plan](plan/SKILL.md) alone (see parent onboarding **Prerequisites**). metadata: author: launchdarkly version: "0.2.0" --- # LaunchDarkly SDK Install (onboarding) Installs and initializes the right LaunchDarkly SDK for the user’s project by following **three nested skills in order**. **Do not** skip ahead to feature flags here - the parent [LaunchDarkly onboarding](../SKILL.md) continues with **Step 6: First feature flag** using [Create first feature flag](../first-flag/SKILL.md).2.3kinstalls27Aiconfig SnippetsThe aiconfig-snippets skill is a deprecated redirect renamed to snippets and must not be used for task execution. Old references in documentation, saved prompts, or automation should update from aiconfig-snippets to snippets. Agents arriving via legacy names should invoke the snippets skill instead, which contains current complete instructions for LaunchDarkly AI Config snippet workflows. This catalogue entry exists only to point users and agents to the correct skill name without performing the underlying task from deprecated content. Invoke detection when automation still references aiconfig-snippets so agents route to snippets immediately. DEPRECATED: renamed to snippets skill. Do not follow instructions in this skill file. Invoke snippets for current LaunchDarkly AI Config guidance. Update old docs and automation from aiconfig-snippets to snippets. Kept only for backward-compatible name resolution. Deprecated redirect from aiconfig-snippets to the renamed snippets skill for LaunchDarkly AI Config.2.2kinstalls28Aiconfig Agent GraphsThe aiconfig-agent-graphs skill is a deprecated redirect renamed to agent-graphs and must not execute tasks from this file. Legacy references in documentation, saved prompts, or automation should update from aiconfig-agent-graphs to agent-graphs. Agents arriving via old names should invoke agent-graphs which contains current complete instructions for LaunchDarkly AI Config agent graph workflows. This catalogue entry exists only for backward-compatible name resolution without performing deprecated instructions. Invoke detection when automation still references aiconfig-agent-graphs so agents route to agent-graphs immediately for graph-based agent configuration work. DEPRECATED: renamed to agent-graphs skill. Do not follow instructions in this skill file. Invoke agent-graphs for current LaunchDarkly graph guidance. Update old references from aiconfig-agent-graphs to agent-graphs. Kept only for backward-compatible name resolution. Deprecated redirect from aiconfig-agent-graphs to the renamed agent-graphs skill for LaunchDarkly AI Config.2.2kinstalls29Toolstools is an agent skill that equips AI coding agents with a comprehensive library of 20+ specialized capabilities. Builders use it to let agents independently perform web research, execute Python or shell code, control a headless browser, read and edit files, and interact with git. The skill follows strict permission models so users retain control over network, filesystem, and shell access. It is ideal when you want your agent to move beyond simple chat and actually act on your codebase and the outside world. The package is maintained by LaunchDarkly and distributed through the skills.sh registry with 685 installs.1.6kinstalls30Built In Metricsbuilt-in-metrics is a launchdarkly/agent-skills package listed with 684 installs on skills.sh that wires agent sessions to LaunchDarkly metric reporting. The skill lets agents emit performance, usage, and quality signals automatically instead of developers writing bespoke telemetry plumbing. Teams reach for built-in-metrics when operating feature-flagged or experiment-driven services and wanting agent activity observable in LaunchDarkly. It targets runtime metric collection during agent workflows rather than scaffolding application business logic.1.6kinstalls31Snippetssnippets is an Apache-2.0 LaunchDarkly agent skill (version 0.1.0) for creating and managing prompt snippets—reusable text blocks referenced inside config variation prompts. The skill guides identifying reusable instruction text, creating snippets, wiring references into config variations, and verifying correct linkage. It requires the remotely hosted LaunchDarkly MCP server. Developers reach for snippets when multiple LaunchDarkly configs share common personas, guardrails, or system instructions and duplicating prompt text would cause drift. Claude or Cursor agents use it to generate high-quality reusable code-adjacent prompt blocks that follow consistent patterns across configs.1.6kinstalls32Agent Graphsagent-graphs is an Apache-2.0 LaunchDarkly agent skill (version 0.1.0) that guides creation and management of agent graphs—directed graphs of configs connected by edges with handoff logic. The skill walks through graph topology design, node creation, edge wiring, and verification that routing between config nodes works correctly. It requires the remotely hosted LaunchDarkly MCP server as a prerequisite. Developers reach for agent-graphs when building multi-agent workflows where configs must route to each other based on handoff conditions. Claude or Cursor agents use it to break complex work into structured, parallelizable graphs of subtasks rather than monolithic single-agent prompts.1.6kinstalls33Projectsprojects is a LaunchDarkly agent-skills package entry with 682 installs on skills.sh that enables coding agents to manage LaunchDarkly project contexts during feature-flag workflows. It supports creating new LaunchDarkly projects, switching active project scope, and maintaining structured context including goals, constraints, and task lists so flag operations target the correct environment. Developers reach for projects when onboarding new services into LaunchDarkly, organizing flags across multiple products, or ensuring agent-driven flag changes apply to the intended LaunchDarkly project. The skill reduces misconfigured flag edits caused by agents operating against the wrong LaunchDarkly project or environment.1.6kinstalls34Configs Createconfigs-create is a LaunchDarkly agent skill listed on skills.sh with 681 installs that generates feature flag configurations an agent can apply directly. It targets developers using Claude, Cursor, or other coding agents who want LaunchDarkly flag definitions created programmatically instead of hand-written YAML. The skill originates from launchdarkly/agent-skills on GitHub and ranks among the catalog's feature-flag tooling entries. Developers reach for configs-create when spinning up new feature toggles, rollout rules, or environment-specific flag variations as part of application integration work.1.6kinstalls35Configs Targetingconfigs-targeting is a LaunchDarkly agent-skills package entry with 681 installs on skills.sh that enables coding agents to manage feature flag targeting configurations through conversational prompts. It covers reading existing flag targeting rules, creating new audience segments, and updating rollout conditions without switching to the LaunchDarkly dashboard. Developers reach for configs-targeting when rolling out features to percentage rollouts, user segments, or environment-specific audiences and want the agent to apply LaunchDarkly API changes directly. The skill fits teams using LaunchDarkly for progressive delivery who want flag targeting edits co-located with code changes in Claude Code, Cursor, or similar agent environments.1.6kinstalls36Configs Variationsconfigs-variations is a LaunchDarkly agent-skills package entry with 682 installs on skills.sh that enables coding agents to manage feature flag variations through conversational commands. It supports reading current flag variation payloads, generating new variation definitions, and updating configuration values for multivariate or boolean flags without leaving the IDE. Developers reach for configs-variations when adding new flag values, renaming variations, or syncing JSON configuration payloads with application code during feature development. The skill pairs with other LaunchDarkly agent-skills for teams practicing progressive delivery who want variation management embedded in agent-assisted development workflows.1.6kinstalls37Online Evalsonline-evals is a LaunchDarkly agent skill from launchdarkly/agent-skills with 679 installs on skills.sh. It enables coding agents to set up live A/B tests and statistical evaluations for prompt variants, model choices, or agent behaviors using real user traffic or production-like conditions. Rather than offline prompt playgrounds alone, online-evals ties experimentation to measurable outcomes in running systems. Developers reach for it when LLM or agent changes need controlled rollout with statistical comparison before committing to a single production configuration.1.6kinstalls38Configs Updateconfigs-update is a LaunchDarkly agent skill published in launchdarkly/agent-skills with 681 installs on skills.sh. It lets coding agents modify LaunchDarkly feature flag configurations directly inside Cursor or Claude Code instead of switching to the LaunchDarkly dashboard or raw API calls. The skill focuses on safe, guided updates to flag configs so teams can adjust targeting, variations, and environment settings during active development or operations. Developers reach for configs-update when a flag change is needed mid-session and the agent should apply LaunchDarkly best practices while keeping edits auditable and context-aware.1.6kinstalls39Custom Metricscustom-metrics is a LaunchDarkly agent skill at version 1.0.0-experimental that covers creating, tracking, retrieving, updating, and deleting custom business metrics for configs. Developers define metric kinds through the LaunchDarkly API, emit events through the server SDK, and query results to drive automated flag decisions. The skill requires a LaunchDarkly server SDK and an API token with the writer role for metric management. Teams reach for custom-metrics when feature flags should react to real business signals such as conversion, latency, or usage thresholds instead of static rollout percentages alone.1.6kinstalls40Migratemigrate is a LaunchDarkly agent skill from launchdarkly/agent-skills with 681 installs on skills.sh. It guides coding agents through safe updates, refactors, and migrations when an application’s LaunchDarkly usage evolves, including flag keys, SDK patterns, and related configuration. Instead of manual grep-and-replace across services, the skill structures coordinated changes so code and flag definitions stay consistent. Developers reach for migrate during SDK upgrades, flag renames, environment restructuring, or deprecation of old toggle patterns where breaking production targeting is the main risk.1.6kinstalls41Launchdarkly Flag Commandlaunchdarkly-flag-command is an agent skill from launchdarkly/agent-skills that exposes LaunchDarkly feature flag operations through CLI commands callable from coding agents. The skill lets developers create flags, toggle environments, and inspect flag state while wiring flag keys into application code during release work. Teams reach for launchdarkly-flag-command when feature toggles must align with deploys and agents should manage LaunchDarkly without context-switching to the web console. The workflow covers flag key naming, environment toggles, variation inspection, and linking in-code references to live LaunchDarkly resources. Outcomes include configured flags, updated targeting state, and code paths ready for gradual rollout or kill-switch control.1.5kinstalls