Name: migrate
Rating: 68.8 (1 reviews)
Author: launchdarkly

migrate

Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic, Bedrock, Gemini, Strands) to a managed config, or stage a full hardcoded-to-LaunchDarkly migration.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, actionable five-stage migration guide with strong workflow checkpoints and clean progressive disclosure into six real reference files. Its main weakness is conciseness: the hand-off discipline and several warnings are restated across Core Principles, Workflow, and What NOT to Do.

Suggestions

Consolidate the hand-off model explanation — it currently appears in Prerequisites, Core Principles (item 5), the Workflow intro, and What NOT to Do; state it once and cross-reference.

Trim overlap between 'Core Principles' and 'What NOT to Do': several items (tracker lifetime, configs-targeting, load_chat_model) are restated verbatim; merge or link rather than repeat.

Move the repeated per-stage 'Delegate:'/'Do not auto-invoke' boilerplate into a single convention note near the Workflow header instead of repeating it after each stage.

Dimension	Reasoning	Score
Conciseness	The body is largely focused on non-obvious API surface, but it carries real redundancy — the hand-off model is re-explained in Prerequisites, Core Principles, and What NOT to Do, and the latter two sections restate Workflow warnings — so it could be tightened without losing clarity.	3 / 5
Actionability	Provides concrete, executable Python and Node code with specific package versions, exact slash-command and MCP-tool names, and before/after snippets; the few gaps are justified delegation to sibling skills rather than missing detail.	4 / 5
Workflow Clarity	Five stages are clearly sequenced with an explicit STOP/confirm-add-fix-stop checkpoint in Step 1, per-stage Verify sub-steps, and validation feedback loops (validate → fix → re-validate) for destructive and batch operations.	5 / 5
Progressive Disclosure	SKILL.md is an overview with six real, clearly signaled one-level-deep reference files (all present in references/) and a terminal References section, making navigation easy; inline detail is justified rather than misfiled.	5 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it states concrete capabilities, enumerates the five stages, and provides explicit, specific 'Use when' trigger guidance tied to real migration intents. It is slightly shy of maximal trigger-term coverage only because a few natural synonyms are missing.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions — "audit the code, wrap the call, move the tools, add tracking, attach evaluators" plus externalizing model/prompt config and moving from direct provider calls — giving comprehensive coverage of the migration stages.	5 / 5
Completeness	Clearly answers both what (five-stage AgentControl migration, stages enumerated) and when ("Use when the user wants to externalize model/prompt configuration, move from direct provider calls ..., or stage a full hardcoded-to-LaunchDarkly migration") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ("externalize model/prompt configuration", "hardcoded-to-LaunchDarkly migration", provider names OpenAI/Anthropic/Bedrock/Gemini/Strands), but a few common phrasings users might say (e.g. "prompt management", "LLM config") are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (hardcoded-LLM-prompt-to-LaunchDarkly AgentControl migration) with distinct, specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (573 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 10 suspicious	Warning

	Total	14 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/agentcontrol/migrate/SKILL.md
Commit: 45fcc25

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.