一键在 Manus 中运行任何 Skill

$pwd:

llm-integration

Name: Llm Integration
Author: rapidaai

// Add or modify LLM/integration providers in integration-api with caller factory wiring, unified provider routing, streaming behavior, and metric/audit compatibility.

在 Manus 中运行

$ git log --oneline --stat

stars:652

forks:99

updated:2026年3月23日 05:06

文件资源管理器

4 个文件

SKILL.md

readonly

name	llm-integration
description	Add or modify LLM/integration providers in integration-api with caller factory wiring, unified provider routing, streaming behavior, and metric/audit compatibility.

LLM Integration Skill

Mission

Add provider callers that support chat/stream/verify (and optional embedding/reranking) with consistent metrics and unified routing.

Inputs expected from user

Provider capabilities required: chat, stream, verify, embeddings, reranking.
Auth style and endpoint shape.
Any model parameter or tool-calling constraints.

If user does not answer:

Implement chat + stream + verify first.
Add embeddings/reranking only when provider supports them.

Hard boundaries

In scope:

api/integration-api/internal/caller/<provider>/...
api/integration-api/internal/caller/caller.go
api/integration-api/internal/type/callers.go when interface compatibility changes are required
api/integration-api/api/unified_provider.go
pkg/clients/integration/integration_client.go if routing/client behavior needs updates
provider UI model metadata in ui/src/providers/<provider>/...

Out of scope:

assistant-api telephony/STT/TTS/EOS/VAD internals

Implementation workflow

Create provider caller package with llm.go, verify-credential.go, and optional embedding/reranking files.
Register provider in caller.go factory methods.
Ensure unified gRPC route usage supports provider name casing/validation.
Emit metrics via MetricBuilder semantics (TIME_TAKEN, STATUS, request ID).
Add tests for chat success/failure, streaming, verify credential, optional embedding/reranking.
Update UI provider catalogs (text-models.json / models.json) as needed.

Validation commands

go test ./api/integration-api/internal/caller/...
go test ./api/integration-api/api/...
go test ./pkg/clients/integration/...
./.claude/skills/llm-integration/scripts/validate.sh --check-diff --provider <provider>

related-skills.json

同仓库

noise-reduction-integration.md

from "rapidaai/voice-ai"

Add or modify noise-reduction providers in assistant-api with denoiser factory wiring, packet safety, and UI option compatibility.

2026-03-23652

noise-reduction-integration.md

from "rapidaai/voice-ai"

Add or modify microphone noise-reduction providers in assistant-api with denoiser factory wiring, packet safety, and option/UI compatibility.

2026-03-23652

end-of-speech-integration.md

from "rapidaai/voice-ai"

Add or modify end-of-speech integrations in assistant-api with strict separation from VAD internals. Use for transcript/audio/history-aware turn-finalization logic, provider wiring, and EOS UI config.

2026-03-23652

local-setup-and-run.md

from "rapidaai/voice-ai"

Explain and validate local setup paths for this repo with Docker and without Docker. Use when developers need exact prerequisites, startup commands, health checks, and troubleshooting steps.

2026-03-23652

stt-integration.md

from "rapidaai/voice-ai"

Add or modify speech-to-text providers in assistant-api with transport-aware ingestion (WS/SDK/HTTP), transcript packet correctness, and UI/provider wiring.

2026-03-23652

system-understanding.md

from "rapidaai/voice-ai"

Build a code-grounded implementation plan before coding. Use to trace packet flow, factory boundaries, provider config loading, and exact file-level change scope for a requested integration.

2026-03-23652

package.json

"author": "rapidaai"

"repository": "rapidaai/voice-ai"

打开 GitHub 仓库查看创作者相关仓库

$ install --global

$ download --local

在 Manus 中运行

$ useful --forSOC

软件开发工程师计算机与数学类职业15-1252L4

name	llm-integration
description	Add or modify LLM/integration providers in integration-api with caller factory wiring, unified provider routing, streaming behavior, and metric/audit compatibility.

LLM Integration Skill

Mission

Add provider callers that support chat/stream/verify (and optional embedding/reranking) with consistent metrics and unified routing.

Inputs expected from user

Provider capabilities required: chat, stream, verify, embeddings, reranking.
Auth style and endpoint shape.
Any model parameter or tool-calling constraints.

If user does not answer:

Implement chat + stream + verify first.
Add embeddings/reranking only when provider supports them.

Hard boundaries

In scope:

api/integration-api/internal/caller/<provider>/...
api/integration-api/internal/caller/caller.go
api/integration-api/internal/type/callers.go when interface compatibility changes are required
api/integration-api/api/unified_provider.go
pkg/clients/integration/integration_client.go if routing/client behavior needs updates
provider UI model metadata in ui/src/providers/<provider>/...

Out of scope:

assistant-api telephony/STT/TTS/EOS/VAD internals

Implementation workflow

Create provider caller package with llm.go, verify-credential.go, and optional embedding/reranking files.
Register provider in caller.go factory methods.
Ensure unified gRPC route usage supports provider name casing/validation.
Emit metrics via MetricBuilder semantics (TIME_TAKEN, STATUS, request ID).
Add tests for chat success/failure, streaming, verify credential, optional embedding/reranking.
Update UI provider catalogs (text-models.json / models.json) as needed.

Validation commands

go test ./api/integration-api/internal/caller/...
go test ./api/integration-api/api/...
go test ./pkg/clients/integration/...
./.claude/skills/llm-integration/scripts/validate.sh --check-diff --provider <provider>

llm-integration

LLM Integration Skill

Mission

Inputs expected from user

Hard boundaries

Implementation workflow

Validation commands

同仓库更多 Skills

同仓库更多 Skills

LLM Integration Skill

Mission

Inputs expected from user

Hard boundaries

Implementation workflow

Validation commands