launchdarkly-configs-create
Skill141 starsChanged 8 days agoApache-2.0View on GitHub
Create and configure configs in LaunchDarkly. Helps you choose between agent vs completion mode, create the config, add variations with models and prompts, and verify the setup.
- Reads credentials
In this repository102 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- agentcore-observability-setupSkill
- agentcore-ops-reviewSkill
- aiml-access-diagnosticsSkill
- aiml-gpu-training-cluster-investigationSkill
- analytics-opensearch-expertiseSkill
- aws-backup-coverage-reviewSkill
- aws-eks-healthdashboardSkill
- aws-eks-operations-reviewSkill
- aws-fsxn-operations-reviewSkill
- aws-health-eventsSkill
- aws-natgw-traffic-analysisSkill
- aws-routingSkill
- aws-vpc-dns-investigationSkill
- bedrock-adoption-readinessSkill
- bedrock-operation-reviewSkill
- bluebox-observabilitySkill
- bronto-dataset-discoverySkill
- bronto-error-investigationSkill
- bronto-log-searchSkill
- clickstack-investigationSkill
- cloudtrail-cost-optimizationSkill
- config-cost-optimizationSkill
- coralogix-ai-centerSkill
- coralogix-alertsSkill
- coralogix-case-analyticsSkill
- coralogix-case-managementSkill
- coralogix-casesSkill
- coralogix-dashboardsSkill
- coralogix-dataprimeSkill
- coralogix-datasetsSkill
- coralogix-data-usageSkill
- coralogix-docsSkill
- coralogix-infrastructureSkill
- coralogix-logsSkill
- coralogix-metrics-querySkill
- coralogix-ollySkill
- coralogix-rumSkill
- coralogix-service-catalogSkill
- coralogix-single-caseSkill
- coralogix-spansSkill
- coralogix-viewsSkill
- cribl-investigationSkill
- crm-production-investigation-guidelinesSkill
- database-migration-service-expertiseSkill
- database-rds-devopsSkill
- devops-agent-cost-insightsSkill
- dx-vif-resilienceSkill
- ecs-operation-reviewSkill
- eks-upgrade-readinessSkill
- elastic-csp-investigationSkill
- elastic-k8s-investigationSkill
- elastic-llm-obsSkill
- elastic-onboardingSkill
- elastic-service-reliabilitySkill
- elastic-sre-triageSkill
- enrich-with-aws-security-agentSkill
- eos-cost-analysisSkill
- firehose-operation-reviewSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 8 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 44
Before creating, identify what you're building:
- Distinctive: line 63
Both modes support tools: Not all models support agent mode -- check model compatibility if using agent mode.
- Very specific: line 67
Use create-agent-config with resource: "config" and the first variation's fields to create both in one call.
- Distinctive: line 117
If the user asks for more control or a step-by-step approach, use the individual tools:
- Distinctive: line 127
If you created the config with its first variation in one call, verification is automatic: the response includes the full config with …
- Very specific: line 181
If the response has requiresApproval: true, the environment needs an approved change and nothing was changed: ask the user who should …
- Very specific: line 183
Do not use turnTargetingOn — that semantic-patch instruction does not work for configs.
- Distinctive: line 206
Don't create configs without understanding the use case
- Distinctive: line 207
Don't skip the two-step process (config then variation)
- Distinctive: line 208
Don't try to attach tools during initial creation -- update the variation afterward
- Distinctive: line 209
Don't forget modelConfigKey (models won't show in the UI)
- Very specific: line 210
Don't omit modelName from the initial variation call.
- Very specific: line 211
Don't drop to raw curl + jq for verification.
- Very specific: line 212
Don't consider the workflow complete until the user has been told to run launchdarkly-configs-targeting.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create Config
You're using a skill that will guide you through creating a config in LaunchDarkly. Your job is to understand the use case, choose the right mode, create the config and its variations, and verify everything is set up correctly.
⚠️ This skill creates a config — it does not make it servable. A freshly-created config has its fallthrough pointing at an auto-generated disabled variation, not at the variation you just created. The SDK will return
ai_config.enabled=Falseon every evaluation until you flip targeting on and point the fallthrough at your new variation. This is not a bug — it's the default state. You must run/launchdarkly-configs-targeting(or theupdate-agent-configcall shown in Step 5) before verifying against the SDK, or verification will look like the LD-served path is broken when it isn't. The single most common failure mode users hit with this skill is skipping the targeting step and spending time debuggingenabled=Falsein their application code.
Prerequisites
This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment.
Primary MCP tool:
create-agent-configwithresource: "config"-- create a config with its first variation in one step (recommended): passvariationKey,variationName,modelConfigKey,modelName, andinstructionsormessagesalong with the config fields
Alternative MCP calls (for more control):
create-agent-configwithresource: "config"-- create just the config shell (configKey,name,mode)create-agent-configwithresource: "variation"-- add a variation with model, prompts, and parametersget-agent-configs-- verify the config was created correctly
Optional MCP tools (enhance workflow):
get-agent-configs-- browse existing configs to understand naming conventionscreate-project-- create a project if one doesn't exist yet
Important: Bias Towards Action
When the user provides enough context (use case, model, mode), proceed through the entire workflow without stopping to ask for details you can infer. Use reasonable defaults for unspecified fields: default for variation key, the use case as the basis for instructions/messages, kebab-case for config keys. Complete all steps (create + verify) in one pass.
Workflow
Step 1: Understand the Use Case
Before creating, identify what you're building:
- What framework? LangGraph, LangChain, CrewAI, Strands, OpenAI SDK, Anthropic SDK, custom
- What does the agent need? Just text generation, or tools/function calling?
- Agent or completion? See the decision matrix below
Step 2: Choose Agent vs Completion Mode
This choice is about input schema and framework compatibility, not execution behavior. Agent mode returns an instructions string; completion mode returns a messages array. Both provide provider abstraction, A/B testing, and metrics tracking.
| Your Need | Mode | Why |
| LangGraph, CrewAI, Strands, AutoGen frameworks | Agent | Frameworks expect goal/instruction input |
| Persistent instructions across interactions | Agent | Single instructions string, SDK method: agent_config() (Python) / agentConfig() (Node) |
| Direct OpenAI/Anthropic API calls | Completion | Messages array maps directly to provider APIs |
| Full control of message structure | Completion | System/user/assistant role-based messages |
| One-off text generation | Completion | Standard chat format |
| Need online evaluations (LLM-as-judge) | Completion | Online evals are only available in completion mode |
Both modes support tools. Not all models support agent mode -- check model compatibility if using agent mode. If unsure, start with completion mode (it's the API default and more flexible).
Step 3: Create the Config (Recommended: One Step)
Use create-agent-config with resource: "config" and the first variation's fields to create both in one call. This is the recommended approach: it handles creation, variation setup, and verification automatically.
Config fields:
resource--"config"configKey-- unique identifier (lowercase, hyphens)name-- the config's human-readable namemode--"agent"or"completion"- Optional:
description,tags
Variation fields:
variationKey,variationName-- identifiers for the first variationmodelConfigKey-- a key fromget-ai-model-configs: a globalProvider.model-idkey (e.g.,OpenAI.gpt-4o,Anthropic.claude-sonnet-4-5) or a custom model config's own keymodelName-- the model identifier (e.g.,gpt-4o). Always pass this in the initial call — leaving it off produces a variation that displays "NO MODEL" and forces a second PATCH to set it. The field ismodelName; it is notnameormodel.nameon this endpoint, andnameis only ever the config's name.
For agent mode, provide:
instructions-- a string with the agent's system instructions
Example agent-mode call:
{
"projectKey": "my-project", "resource": "config", "configKey": "support-agent", "name": "Support Agent",
"mode": "agent", "variationKey": "default", "variationName": "Default",
"modelConfigKey": "OpenAI.gpt-4o", "modelName": "gpt-4o",
"instructions": "You are a customer support agent. Help users resolve their issues."
}For completion mode, provide:
messages-- an array of{role, content}objects (system, user, assistant)
Example completion-mode call:
{
"projectKey": "my-project", "resource": "config", "configKey": "product-descriptions", "name": "Product Descriptions",
"mode": "completion", "variationKey": "default", "variationName": "Default",
"modelConfigKey": "Anthropic.claude-sonnet-4-5", "modelName": "claude-sonnet-4-5",
"messages": [
{"role": "system", "content": "You are a product copywriter. Write compelling descriptions."},
{"role": "user", "content": "Write a description for: {{product_name}}"}
]
}Optional:
parameters-- model parameters like{temperature: 0.7, max_tokens: 2000}(match the UI's snake_case keys)
The tool returns the full verified config detail with the variation attached.
Step 3 (Alternative): Two-Step Creation
If the user asks for more control or a step-by-step approach, use the individual tools:
create-agent-configwithresource: "config"and novariationKey-- create the config shellcreate-agent-configwithresource: "variation",configKey,variationKey,variationName, model, and prompts -- add the variationget-agent-configs-- verify the result
Execute all three steps without stopping to ask for details. Infer the variation key (default), name (Default), instructions/messages, and model from the user's request context. If the user asked for GPT-4o agent mode, you have enough to complete the entire flow. Only ask clarifying questions if the mode or model is truly ambiguous.
Step 4: Verify
If you created the config with its first variation in one call, verification is automatic: the response includes the full config with variations. Check:
- Config exists with the correct mode
- Variation has a model assigned (not "NO MODEL")
- Instructions or messages are present
- Parameters are set
Use get-agent-configs with the configKey for the verification call — do not drop to raw curl + jq. The MCP tool returns a typed object you can inspect directly. Hand-rolled jq filters against the REST response routinely break: the configs detail endpoint returns the variation list under different keys depending on expand, and a filter like .variations.items[] will fail with Cannot index array with string "items" when the response shape is a bare array.
Report results:
- Config created with correct structure
- Variation has model assigned
- Flag any missing model or parameters
- Provide config URL:
https://app.launchdarkly.com/projects/{projectKey}/ai-configs/{configKey}
Step 5: Make the variation servable
create-agent-config creates the variation but does not promote it to fallthrough. The new config will return enabled=False to every consumer until targeting is updated. This is the single most common "I created a config but my SDK still gets the fallback" failure. The workflow is not complete until this step is done.
What to tell the user
Print this checklist verbatim to the user after Step 4, then wait for confirmation. Do not claim the skill succeeded until the user confirms the fallthrough was flipped.
✅ Config and variation are created.
🔴 The SDK will return
enabled=Falseuntil you flip targeting on. The fallthrough is currently pointing at an auto-generated disabled variation, not at the{variationKey}you just created.Next step — run
/launchdarkly-configs-targetingwith these inputs:
- Project key:
{projectKey}- Config key:
{configKey}- Environment key: the env whose SDK key is in your
.env(usuallytestorproduction)- Fallthrough variation:
{variationKey}(the one this skill just created)Verify after targeting is flipped by:
- Opening the config in the LD UI, switching to the correct environment, and confirming "Default rule serves:
{variationName}" is shown with targeting On.- Running a quick test:
ai_config = ai_client.{completion|agent}_config(...)and assertingai_config.enabled is True.
Direct shortcut if the user wants to flip targeting without invoking the sibling skill
launchdarkly-configs-targeting is the canonical path — it handles percentage rollouts, targeted rules, and individual targets. For the simplest case ("promote the new variation to fallthrough in one environment"), call update-agent-config with resource: "targeting" and a fallthrough after the user agrees:
{
"projectKey": "{projectKey}",
"configKey": "{configKey}",
"resource": "targeting",
"env": "{envKey}",
"fallthrough": {"variationKey": "{variationKey}"},
"confirm": true
}Then call get-agent-configs with configKey, section: "targeting", and env to confirm the default rule serves that variation.
If the response has requiresApproval: true, the environment needs an approved change and nothing was changed: ask the user who should review it, then submit the returned instructions with create-agent-config-approval, with a description of the change and at least one reviewer, as in Step 5 of launchdarkly-configs-targeting.
Do not use turnTargetingOn — that semantic-patch instruction does not work for configs. Setting the fallthrough is what makes the config serve the new variation.
modelConfigKey Format
Required for models to display in the UI. Format: {Provider}.{model-id}
OpenAI.gpt-4oOpenAI.gpt-4o-miniAnthropic.claude-sonnet-4-5Anthropic.claude-3-5-sonnet
create-agent-config validates this format and rejects invalid values.
Edge Cases
| Situation | Action |
| Config already exists | Ask if user wants to update instead |
| Variation shows "NO MODEL" | Use update-agent-config with resource: "variation" to set modelConfigKey |
| Need to attach tools | Create tools first (launchdarkly-tools skill), then update the variation |
What NOT to Do
- Don't create configs without understanding the use case
- Don't skip the two-step process (config then variation)
- Don't try to attach tools during initial creation -- update the variation afterward
- Don't forget modelConfigKey (models won't show in the UI)
- Don't omit
modelNamefrom the initial variation call. It is required at create time; setting it via a follow-up PATCH is a workaround for a bug, not the intended flow. The PATCH field is alsomodelName, notname. - Don't drop to raw
curl+jqfor verification. Useget-agent-configs(MCP) — it returns a typed object and avoids brittlejqfilters that break on response-shape variation. - Don't consider the workflow complete until the user has been told to run
launchdarkly-configs-targeting. A created variation that isn't promoted to fallthrough returnsenabled=Falseto every consumer.
More resources
To learn more about creating a config in the LaunchDarkly UI, read Create configs
To learn more about configuring the SDK, read:
- .NET AI SDK reference
- Go AI SDK reference
- Node.js (server-side) SDK AI reference
- Python AI SDK reference
- Ruby AI SDK reference
Related Skills
launchdarkly-tools-- Create tools before attachinglaunchdarkly-configs-variations-- Add more variations for experimentationlaunchdarkly-configs-update-- Modify configs based on learnings
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

