一键在 Manus 中运行任何 Skill

run

星标3

分支1

更新时间2026年7月10日 23:25

This skill should be used when the user asks to "run NeuralVault", "start the app", "start the API", "start the frontend", "launch the stack", "sign in locally", or wants to see a change working end-to-end in the running application. Provides NeuralVault's actual local launch sequence (Docker infra + Go API + Next.js frontend), overriding generic app-launch guidance.

安装

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。

在 Manus 中运行

来源

jpgomesr

jpgomesr/neuralvault

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Running NeuralVault locally

NeuralVault runs as Docker Compose infrastructure plus two host processes (the Go API and the Next.js frontend). Start them in this order.

1. Infrastructure

Check whether Postgres, Qdrant, Ollama, MinIO, and Keycloak are already up:

docker compose ps

If not running:

docker compose up -d          # or: make up

Keycloak takes a few seconds to import the neuralvault dev realm — wait for it to report healthy before signing in later.

2. Embedding model

Confirm the embedding model is pulled (one-time, ~270MB):

ollama pull nomic-embed-text

3. Database migrations

Migrations are never run automatically by the server — run them explicitly:

make migrate-up

4. API

cd api && go run ./cmd/server        # or: make run

Listens on http://localhost:8080. Confirm it's healthy:

curl http://localhost:8080/health

5. Frontend

cd web && npm install && npm run dev   # npm install only needed on first run

Serves http://localhost:3000.

6. Sign in

Navigate to http://localhost:3000 — this redirects to Keycloak OIDC. Use the seeded dev user:

Username	Password
`dev`	`dev`

Known limitation

The nv CLI (make run-cli) does not work against a default local setup — it has no OIDC login flow yet (SPEC-011). Drive the app through the API directly (curl, an HTTP client) or the frontend instead of the CLI until that's implemented.

Troubleshooting

Ollama unreachable: ollama serve, then retry
Login fails: Keycloak realm import may still be in progress — docker compose logs keycloak
Migrations fail: Postgres may not be ready yet — docker compose up -d postgres, wait, retry make migrate-up
Port conflict: ports in use are 3000 (web), 8080 (api), 5432 (postgres), 6333 (qdrant), 9000/9001 (minio), 8081 (keycloak), 11434 (ollama)

Full walkthrough with explanations: getting-started.md.

同仓库更多 Skills

同仓库

retrieval

jpgomesr/neuralvault

This skill should be used when modifying api/internal/retrieval/ (query, streaming answers, chunk hydration), or when asked "how does retrieval work", "why re-filter after Qdrant already filtered", "add a new caller of loadChunks", "why does Retrieve query Postgres full-text too". Documents four non-obvious invariants in the retrieval pipeline that look redundant or arbitrary but aren't.

2026-07-133

auth

jpgomesr/neuralvault

This skill should be used when modifying api/internal/auth/ (login, session, RequireUser middleware), or when asked "how does login work here", "how are sessions handled", "add a protected route". Documents the three login surfaces and the custom session scheme, since neither is a standard JWT/OIDC-library setup.

2026-07-103

code-review

jpgomesr/neuralvault

This skill should be used automatically before finishing a nontrivial NeuralVault diff, or when asked to "review this", "check this against conventions", "does this follow the codebase style" — without requiring the explicit /review command. Checks a diff against NeuralVault's own layering and terminology rules.

2026-07-103

go-feature-domain

jpgomesr/neuralvault

This skill should be used when adding or modifying a feature domain under api/internal/ (auth, health, retrieval, sources, workspaces, or a new one), or when asked "how do I add a new endpoint/domain", "where does this logic go", "how are Go tests structured here". Documents the three-file domain layout, its justified exceptions, and the testing conventions.

2026-07-103

go-provider-interface

jpgomesr/neuralvault

This skill should be used when adding a new backend to embedding, llm, vectorstorage, objectstorage, or storage (e.g. "add an OpenAI provider", "add a new LLM backend", "swap the vector database"), or when asked how NeuralVault's pluggable-provider pattern works. Documents the interface-package shape, the fail-fast startup convention, and two known exceptions that look like bugs but aren't.

2026-07-103

ollama

jpgomesr/neuralvault

This skill should be used when modifying api/internal/embedding/ollama/ or api/internal/llm/ollama/, or when asked "why did the server fail to start over Ollama", "how does streaming work here", "add timeout handling to the LLM client". Documents the fail-fast model check and why the LLM client has no HTTP timeout.

2026-07-103

name	run
description	This skill should be used when the user asks to "run NeuralVault", "start the app", "start the API", "start the frontend", "launch the stack", "sign in locally", or wants to see a change working end-to-end in the running application. Provides NeuralVault's actual local launch sequence (Docker infra + Go API + Next.js frontend), overriding generic app-launch guidance.

Running NeuralVault locally

NeuralVault runs as Docker Compose infrastructure plus two host processes (the Go API and the Next.js frontend). Start them in this order.

1. Infrastructure

Check whether Postgres, Qdrant, Ollama, MinIO, and Keycloak are already up:

docker compose ps

If not running:

docker compose up -d          # or: make up

Keycloak takes a few seconds to import the neuralvault dev realm — wait for it to report healthy before signing in later.

2. Embedding model

Confirm the embedding model is pulled (one-time, ~270MB):

ollama pull nomic-embed-text

3. Database migrations

Migrations are never run automatically by the server — run them explicitly:

make migrate-up

4. API

cd api && go run ./cmd/server        # or: make run

Listens on http://localhost:8080. Confirm it's healthy:

curl http://localhost:8080/health

5. Frontend

cd web && npm install && npm run dev   # npm install only needed on first run

Serves http://localhost:3000.

6. Sign in

Navigate to http://localhost:3000 — this redirects to Keycloak OIDC. Use the seeded dev user:

Username	Password
`dev`	`dev`

Known limitation

Troubleshooting

Ollama unreachable: ollama serve, then retry
Login fails: Keycloak realm import may still be in progress — docker compose logs keycloak
Migrations fail: Postgres may not be ready yet — docker compose up -d postgres, wait, retry make migrate-up
Port conflict: ports in use are 3000 (web), 8080 (api), 5432 (postgres), 6333 (qdrant), 9000/9001 (minio), 8081 (keycloak), 11434 (ollama)

Full walkthrough with explanations: getting-started.md.