Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

enable-ollama

Estrelas0

Forks0

Atualizado22 de abril de 2026 às 05:58

Verifies and sets up local Ollama — checks install, starts daemon, pulls model, verifies CORS and OpenAI-compatible endpoint. Client-agnostic; use before any skill that needs a working Ollama (e.g. enable-ollama-in-cursor). Use when the user wants Ollama running locally, needs to troubleshoot Ollama, or before configuring any client to use Ollama.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

strativd

strativd/dotfiles

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Administradores de redes e sistemas de computadorInformática e Matemática·SOC 15-1244

Explorador de arquivos

7 arquivos

SKILL.md

readonly

name	enable-ollama
description	Verifies and sets up local Ollama — checks install, starts daemon, pulls model, verifies CORS and OpenAI-compatible endpoint. Client-agnostic; use before any skill that needs a working Ollama (e.g. enable-ollama-in-cursor). Use when the user wants Ollama running locally, needs to troubleshoot Ollama, or before configuring any client to use Ollama.

Enable Ollama

Ensures Ollama is installed, running, has the requested model pulled, CORS is configured, and the OpenAI-compatible /v1 endpoint responds. This skill is client-agnostic — it knows nothing about Cursor, VS Code, or any other consumer.

Defaults

Item	Default	Notes
`OLLAMA_CURSOR_MODEL`	`gemma4:26b`	Override with any `ollama list` name.
`OLLAMA_HOST`	`http://127.0.0.1:11434`	Override if Ollama binds elsewhere.
`OLLAMA_ORIGINS`	`*`	Required for browser/ngrok clients.

Agent workflow (run in order)

1. Quick health check (recommended first)

Runs all checks in sequence:

bash ~/.agents/skills/enable-ollama/scripts/health-check.sh

If this passes, Ollama is ready. Skip to step 5 for endpoint URL.

2. Individual checks (if health check fails)

Each script exits 0 on success, non-zero on failure:

# Check ollama CLI installed
bash ~/.agents/skills/enable-ollama/scripts/check-install.sh

# Check daemon responding
bash ~/.agents/skills/enable-ollama/scripts/check-daemon.sh

# Pull/verify model
bash ~/.agents/skills/enable-ollama/scripts/pull-model.sh

# Check CORS configuration
bash ~/.agents/skills/enable-ollama/scripts/check-cors.sh

3. Fix CORS (if check-cors.sh warns)

export OLLAMA_ORIGINS='*'
# Then restart Ollama from this shell, or on macOS:
launchctl setenv OLLAMA_ORIGINS "*"

4. Re-run health check after fixes

bash ~/.agents/skills/enable-ollama/scripts/health-check.sh

5. Result: endpoint URL

After health check passes, the Ollama OpenAI-compatible endpoint is:

${OLLAMA_HOST:-http://127.0.0.1:11434}/v1

Use this URL in any OpenAI-compatible client (Cursor, Continue, etc.).

Script reference

Script	Purpose	Destructive?
`check-install.sh`	Verify `ollama` CLI exists	No
`check-daemon.sh`	Verify `:11434` responding, auto-start macOS	Yes (start)
`pull-model.sh`	Pull model if missing	Yes (pull)
`check-cors.sh`	Check `OLLAMA_ORIGINS=*`	No
`health-check.sh`	End-to-end check (calls all above)	Yes (daemon+pull)

All scripts are idempotent — safe to run repeatedly.

Mais deste repositório

mesmo repositório

add-agents-file

strativd/dotfiles

Generate an optimized AGENTS.md file after analyzing the directory/codebase for context.

2026-04-220

extract-system-first-spec

strativd/dotfiles

Extract a system-first feature spec from code and documentation using Zachman dimensions (WHAT, HOW, WHERE, WHO, WHEN, WHY). Use when users request structured, implementation-grounded specs, architecture extraction, or system design context from an existing codebase and linked sources.

2026-04-220

prompt-optimizer

strativd/dotfiles

Transform a user's 'basic prompt' into an 'optimized prompt' by applying context engineering -> the right context beats the right prompt.

2026-04-220

coding-guidelines

strativd/dotfiles

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

2026-04-150

investigation-guidelines

strativd/dotfiles

Behavioral guidelines to reduce common LLM investigation mistakes. Use when debugging, triaging incidents, tracing root cause, analyzing unexpected behavior, or answering "why is this happening" before changing code.

2026-04-150

refactor-with-a-kiss

strativd/dotfiles

Refactoring with KISS principles. Rethinks implementations to reach the same outcome with less complexity—prefers straightforward, readable code over clever abstractions. Use when refactoring, reviewing code, the user asks for a simpler approach, or when a solution feels over-engineered relative to the problem.

2026-04-080

name	enable-ollama
description	Verifies and sets up local Ollama — checks install, starts daemon, pulls model, verifies CORS and OpenAI-compatible endpoint. Client-agnostic; use before any skill that needs a working Ollama (e.g. enable-ollama-in-cursor). Use when the user wants Ollama running locally, needs to troubleshoot Ollama, or before configuring any client to use Ollama.

Enable Ollama

Defaults

Item	Default	Notes
`OLLAMA_CURSOR_MODEL`	`gemma4:26b`	Override with any `ollama list` name.
`OLLAMA_HOST`	`http://127.0.0.1:11434`	Override if Ollama binds elsewhere.
`OLLAMA_ORIGINS`	`*`	Required for browser/ngrok clients.

Agent workflow (run in order)

1. Quick health check (recommended first)

Runs all checks in sequence:

bash ~/.agents/skills/enable-ollama/scripts/health-check.sh

If this passes, Ollama is ready. Skip to step 5 for endpoint URL.

2. Individual checks (if health check fails)

Each script exits 0 on success, non-zero on failure:

# Check ollama CLI installed
bash ~/.agents/skills/enable-ollama/scripts/check-install.sh

# Check daemon responding
bash ~/.agents/skills/enable-ollama/scripts/check-daemon.sh

# Pull/verify model
bash ~/.agents/skills/enable-ollama/scripts/pull-model.sh

# Check CORS configuration
bash ~/.agents/skills/enable-ollama/scripts/check-cors.sh

3. Fix CORS (if check-cors.sh warns)

export OLLAMA_ORIGINS='*'
# Then restart Ollama from this shell, or on macOS:
launchctl setenv OLLAMA_ORIGINS "*"

4. Re-run health check after fixes

bash ~/.agents/skills/enable-ollama/scripts/health-check.sh

5. Result: endpoint URL

After health check passes, the Ollama OpenAI-compatible endpoint is:

${OLLAMA_HOST:-http://127.0.0.1:11434}/v1

Use this URL in any OpenAI-compatible client (Cursor, Continue, etc.).

Script reference

Script	Purpose	Destructive?
`check-install.sh`	Verify `ollama` CLI exists	No
`check-daemon.sh`	Verify `:11434` responding, auto-start macOS	Yes (start)
`pull-model.sh`	Pull model if missing	Yes (pull)
`check-cors.sh`	Check `OLLAMA_ORIGINS=*`	No
`health-check.sh`	End-to-end check (calls all above)	Yes (daemon+pull)

All scripts are idempotent — safe to run repeatedly.