Prioritize provider integration skills

This commit is contained in:
hwhung
2026-05-06 21:40:19 +08:00
parent f947c69062
commit f075cddc4e
+15 -7
View File
@@ -1,6 +1,14 @@
Clone and run https://git.komnenos.me/springfw/random-proxy-simple in ./random-proxy-simple. First action: load/use only these two provider-specific skills by exact name:
- ai-integrations-openai
- ai-integrations-anthropic
Goal: get the app running once, with Replit AI Integrations wired, on port 3000. Do not load the generic integrations skill and do not search for integrations before loading
those two skills.
Then clone and run https://git.komnenos.me/springfw/random-proxy-simple in ./random-proxy-simple.
Goal: get the app running once on port 3000 with OpenAI and Anthropic provider integration
variables available.
Bearer token for this deployment: DEPLOYMENT_GENERATED_PROXY_TOKEN Bearer token for this deployment: DEPLOYMENT_GENERATED_PROXY_TOKEN
@@ -25,15 +33,15 @@ Do not:
Steps: Steps:
1. Clone into ./random-proxy-simple. 1. Confirm only these provider-specific skills were loaded/used:
2. Immediately load/use only these provider-specific Replit AI Integration skills:
- ai-integrations-openai - ai-integrations-openai
- ai-integrations-anthropic - ai-integrations-anthropic
Do not search for them. Do not load the generic integrations skill first. Do not search for them. Do not load the generic integrations skill.
3. Ensure those two skills make these variables available, then use the variable names exactly 2. Clone into ./random-proxy-simple.
3. Ensure the two provider-specific skills make these variables available, then use the variable names exactly
as written in the workflow command: as written in the workflow command:
- AI_INTEGRATIONS_OPENAI_BASE_URL - AI_INTEGRATIONS_OPENAI_BASE_URL
- AI_INTEGRATIONS_OPENAI_API_KEY - AI_INTEGRATIONS_OPENAI_API_KEY