菜单
Complete guided onboarding to Freeplay — analyzes codebase, migrates prompts, and integrates logging. Use whenever the user says 'onboard to Freeplay', 'set up Freeplay', 'get started with Freeplay', 'integrate Freeplay', or wants end-to-end setup.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | freeplay-onboarding |
| description | Complete guided onboarding to Freeplay — analyzes codebase, migrates prompts, and integrates logging. Use whenever the user says 'onboard to Freeplay', 'set up Freeplay', 'get started with Freeplay', 'integrate Freeplay', or wants end-to-end setup. |
Orchestrate the complete Freeplay onboarding flow with checkpoint-based progression.
This is the meta-skill that orchestrates:
/freeplay-plan - Analyze codebase/prompt-migration - Migrate prompts/record-to-freeplay - Integrate loggingCheck state -> Display progress -> Execute phases (plan -> migrate -> log) with approval gate between each. Progress saved to .freeplay/ after each phase.
Look for .freeplay/ directory and existing state files.
Reference _reference/ui-examples.md for UI formatting examples throughout onboarding. When interacting with Freeplay, prefer using the MCP server tools (mcp__freeplay-mcp-v1__*) first. For endpoints or operations not covered by MCP tools, see _shared/FREEPLAY_API_REFERENCE.md.
State detection:
.freeplay/environment-config.json exists -> Environment configured.freeplay/analysis.json exists -> Phase 1 complete.freeplay/migration-manifest.json exists -> Phase 2 complete.freeplay/integration-report.json exists -> Phase 3 completeIf .freeplay/environment-config.json doesn't exist, follow the configuration workflow in _shared/environment-config.md. This creates the config file with domain, API key, project ID, and URLs, and prompts the user to set environment variables.
Run each phase with approval gates between them:
Execute the /freeplay-plan workflow:
Approval gate: User must approve the analysis before proceeding. Show summary of findings and ask to continue.
Execute the /prompt-migration workflow:
Approval gate: User must confirm prompts look correct in Freeplay before continuing.
Show completion summary:
Phase 2 complete!
Prompts migrated to Freeplay
Deployed to latest environment
Manifest saved to .freeplay/migration-manifest.json
Please verify your prompts in Freeplay, then continue.
Continue to Phase 3 (Integrate Logging)? [y/n]
Use Quick Links from _shared/environment-config.md to show relevant project URLs.
Execute the /record-to-freeplay workflow:
Approval gate: User must confirm traces appear in Freeplay.
If user wants to stop mid-onboarding, show progress saved and explain how to resume.
If user wants to skip a phase, warn about implications (especially for prompt migration) and confirm.
Display completion message with summary of changes, links, files, next steps, and documentation. See _reference/ui-examples.md for detailed format. Use Quick Links from _shared/environment-config.md for project URLs.
Create/update .freeplay/onboarding-status.json tracking all phases. See _reference/report-schemas.md for the schema.
Reads:
.freeplay/environment-config.json - Credentials and URLs.freeplay/analysis.json - Phase 1 status.freeplay/migration-manifest.json - Phase 2 status.freeplay/integration-report.json - Phase 3 status.freeplay/onboarding-status.json - Overall statusCreates/Updates:
.freeplay/onboarding-status.json - Track overall progressIf a phase fails:
.freeplay/logs/If user interrupts:
If state is corrupted:
.freeplay/ enable resumabilityAnalyze a codebase to map its LLM implementation for Freeplay migration. Examines prompts, model configs, tool use, sessions, and agent patterns. Use when user wants to understand their LLM usage, inventory prompts, plan a migration, audit LLM patterns, or before integrating with Freeplay — even if they just say 'analyze my code' or 'what LLM stuff do I have'.
Migrate prompts from code into Freeplay for version control, A/B testing, and centralized management. Use whenever the user wants to move prompts, manage templates, set up prompt management, or mentions 'migrate prompts', 'prompt versioning', 'prompt templates', or wants to organize their prompts.
Integrate Freeplay logging, tracing, and observability into an LLM application. Use whenever the user mentions recording LLM calls, adding observability, capturing traces, logging to Freeplay, monitoring LLM usage, or wants a dashboard — even if they don't say 'Freeplay'. Also use after prompt migration, or for observability-only setups.
Assess the health, completeness, and production readiness of a Freeplay project across the data flywheel. Use when the user asks about project status, wants to know if their project is ready for production, asks what's missing in their Freeplay setup, wants a project health check, or asks "what should I set up next?" Also use when the user is first connecting a project to Freeplay.
Analyze Freeplay test run results to surface insights, evaluation metrics, and test case details. Use when the user wants to review test run performance, compare two test runs, understand evaluation scores, or identify failing test cases. Do NOT use for executing new test runs (use run-test) or managing datasets (use dataset-management).
Create, manage, and curate Freeplay datasets (prompt datasets and agent datasets). Always confirm with the user before any write operations. Use when the user wants to create a new dataset, add test cases, update datasets, manage dataset content, import test data from CSV or JSONL, create golden sets, or build evaluation datasets. Do NOT use for running tests (use run-test) or analyzing test results (use test-run-analysis).