Agent skill

Add Python Microservice

TRIGGER when user asks to create a microservice that calls Python, runs ML inference, or uses Python libraries (PyTorch, pandas, sentence-transformers, numpy) for its core compute.

Apache-2.0Auto-check passedBackend & APIs

Install Add Python Microservice

skills CLI

$ npx skills add microbus-io/fabric --skill add-python-microservice -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install microbus-io/fabric add-python-microservice --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/microbus-io/fabric.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/python/add-python-microservice .claude/skills/add-python-microservice && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "add-python-microservice" agent skill from https://github.com/microbus-io/fabric/tree/main/.claude/skills/python/add-python-microservice into .claude/skills/add-python-microservice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-python-microservice", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/microbus-io/fabric/tree/main/.claude/skills/python/add-python-microservice

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add microbus-io/fabric --skill add-python-microservice -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install microbus-io/fabric add-python-microservice --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/microbus-io/fabric.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/python/add-python-microservice .agents/skills/add-python-microservice && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "add-python-microservice" agent skill from https://github.com/microbus-io/fabric/tree/main/.claude/skills/python/add-python-microservice into .agents/skills/add-python-microservice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-python-microservice", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add microbus-io/fabric --skill add-python-microservice -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install microbus-io/fabric add-python-microservice --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/microbus-io/fabric.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/python/add-python-microservice .cursor/skills/add-python-microservice && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "add-python-microservice" agent skill from https://github.com/microbus-io/fabric/tree/main/.claude/skills/python/add-python-microservice into .cursor/skills/add-python-microservice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-python-microservice", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/microbus-io/fabric.git --path .claude/skills/python/add-python-microservice

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add microbus-io/fabric --skill add-python-microservice -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install microbus-io/fabric add-python-microservice --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/microbus-io/fabric.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/python/add-python-microservice .gemini/skills/add-python-microservice && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "add-python-microservice" agent skill from https://github.com/microbus-io/fabric/tree/main/.claude/skills/python/add-python-microservice into .gemini/skills/add-python-microservice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-python-microservice", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install microbus-io/fabric add-python-microservice

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add microbus-io/fabric --skill add-python-microservice -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/microbus-io/fabric.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/python/add-python-microservice .github/skills/add-python-microservice && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "add-python-microservice" agent skill from https://github.com/microbus-io/fabric/tree/main/.claude/skills/python/add-python-microservice into .github/skills/add-python-microservice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-python-microservice", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add microbus-io/fabric --skill add-python-microservice -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install microbus-io/fabric add-python-microservice --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/microbus-io/fabric.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/python/add-python-microservice .opencode/skills/add-python-microservice && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "add-python-microservice" agent skill from https://github.com/microbus-io/fabric/tree/main/.claude/skills/python/add-python-microservice into .opencode/skills/add-python-microservice/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-python-microservice", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: add-python-microservice
GitHub stars: 172
Token cost: ~1.1k tokens
SKILL.md length: 323 words
Files: 4
Skills in repo: 33
Repo updated: Sep 28, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

TRIGGER when user asks to create a microservice that calls Python, runs ML inference, or uses Python libraries (PyTorch, pandas, sentence-transformers, numpy) for its core compute.

Works in 7 steps: Run add-microservice → Add Python Source Files → Add python.go → …
User asks to create a microservice that calls Python
Runs Go and Python scripts from its folder
Runs ML inference

What it does

Add Python Microservice is an agent skill from microbus-io/fabric. TRIGGER when user asks to create a microservice that calls Python, runs ML inference, or uses Python libraries (PyTorch, pandas, sentence-transformers, numpy) for its core compute.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `service.py`).

It sits in Backend & APIs, covering Microservices and DataFrames. It works with Python, NumPy, pandas and PyTorch. The repository describes itself as: Microbus is the only fabric where every agentic workflow runs on a true microservice substrate - giving your workflows security, scale, observability, and prompt-driven authoring. The licence is Apache-2.0.

When your agent uses it

User asks to create a microservice that calls Python
Runs ML inference
Uses Python libraries (PyTorch
Sentence-transformers

Example prompts

“/add-python-microservice”

Requirements

Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

Run add-microservice
Add Python Source Files
Add python.go
Extend the Service Fields
Add MaxWorkers Config
Wire OnStartup and OnShutdown
Housekeeping

What it can do on your machine

Read from SKILL.md and the folder at commit fb98098. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Go and Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Add Python Microservice loads about 1.1k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 323 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~51
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from microbus-io/fabric at commit fb98098, republished under its Apache-2.0 licence (© microbus-io). 323 words, ~1,086 tokens.

Download SKILL.mdSave it as .claude/skills/add-python-microservice/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: add-python-microservice
description: TRIGGER when user asks to create a microservice that calls Python, runs ML inference, or uses Python libraries (PyTorch, pandas, sentence-transformers, numpy) for its core compute.

CRITICAL: Read .claude/rules/python.txt before proceeding.

CRITICAL: Do NOT explore or analyze other microservices unless explicitly instructed to do so.

Workflow

This skill works in two modes:

New microservice: starts at Step 1, runs the standard add-microservice scaffold first.
Extend existing microservice: skips Step 1; the target package already exists and may have business logic. Every subsequent step is additive (it appends, never overwrites).

Copy this checklist and track your progress:

Adding Python support to a microservice:
- [ ] Step 1: Run add-microservice (skip when extending an existing service)
- [ ] Step 2: Add Python source files
- [ ] Step 3: Add python.go
- [ ] Step 4: Extend the Service fields
- [ ] Step 5: Add MaxWorkers config
- [ ] Step 6: Wire OnStartup and OnShutdown
- [ ] Step 7: Housekeeping

Step 1: Run `add-microservice`

Skip this step when extending an existing microservice.

Otherwise, run the add-microservice skill, skipping its housekeeping step (housekeeping runs once at the end of this skill instead). When it finishes, return here. The remaining steps assume myservice/ is the microservice directory.

Step 2: Add Python Source Files

Refuse to overwrite if either file already exists. Copy the template files to the microservice's root:

shell

test -e myservice/service.py        || cp .claude/skills/python/add-python-microservice/service.py myservice/service.py
test -e myservice/requirements.txt  || cp .claude/skills/python/add-python-microservice/requirements.txt myservice/requirements.txt

Step 3: Add `python.go`

Refuse to overwrite if the file already exists:

shell

test -e myservice/python.go || cp .claude/skills/python/add-python-microservice/python.go myservice/python.go

Change package myservice to match the microservice's package name. Leave the rest unchanged.

Step 4: Extend the Service Fields

In service.go, append the venv field to the existing Service struct, preserving any fields already there:

type Service struct {
    *Intermediate // IMPORTANT: Do not remove

    // ...existing fields...
    venv *pyvenv.Venv
}

Add these imports to service.go if they're not already there:

import (
    // ...
    "github.com/microbus-io/fabric/connector"
    "github.com/microbus-io/pyvenv"
)

Step 5: Add `MaxWorkers` Config

Run add-config:

Name: MaxWorkers
Type: int
Validation: int [1,]
Default: match the workload (e.g. 1 for LLM inference, 4 for I/O, 8 for parallel numpy/pandas)
Description: MaxWorkers caps how many calls into the Python venv may run concurrently.

Step 6: Wire `OnStartup` and `OnShutdown`

Add the Python lifecycle wiring to the existing OnStartup and OnShutdown bodies. Do not delete any existing code; append the new lines around it.

In OnStartup, add this block (anywhere in the body, but conventionally at the end so any earlier setup is in place before the venv goroutine launches):

sources, err := readPythonSources()
if err != nil {
    return errors.Trace(err)
}
svc.venv, err = pyvenv.New(pyvenv.Config{
    Sources:          sources,
    Requirements:     parseRequirements(pythonRequirements),
    MaxWorkers:       svc.MaxWorkers(),
    Logger:           svc,
    LivenessCallback: svc.onVenvLiveness,
})
if err != nil {
    return errors.Trace(err)
}
// Start the venv in the background. Auto-start is gated on deployment; in TESTING the
// venv is left dormant (parallels how tickers don't run in TESTING).
if svc.Deployment() != connector.TESTING {
    // Tests opt-in by calling svc.StartPyVenv(ctx)
    svc.Go(ctx, svc.venv.Start)
}

In OnShutdown, add this block (conventionally at the start, so the venv is released before any downstream resources the service shuts down later):

if svc.venv != nil {
    err := svc.venv.Close(ctx)
    if err != nil {
        svc.LogError(ctx, "Closing python venv failed", "error", err)
    }
}

Step 7: Housekeeping

Follow the housekeeping skill.

Files

SKILL.md and 3 other files in .claude/skills/python/add-python-microservice of microbus-io/fabric.

SKILL.md
python.go
requirements.txt
service.py

Open the folder on GitHubat commit fb98098

Compare with similar skills

Add Python Microservice next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Add Python Microservice compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Add Python Microservice this skillmicrobus-io/fabric	172	—	~1.1k	Automated safety check: Pass	Apache-2.0	9 days ago
Python Executorcortega26/chile-hub	113	2 repos	~1.5k	Automated safety check: Pass	MIT	yesterday
Vaex Out-of-Core DataFramesdavila7/claude-code-templates	32k	12 repos	~1.6k	Automated safety check: Pass	MIT	today
Candlestick Pattern SignalsHKUDS/Vibe-Trading	35k	—	~468	Automated safety check: Pass	MIT	yesterday
DaskK-Dense-AI/scientific-agent-skills	48k	1 repos	~4.4k	Automated safety check: Notes	BSD-3-Clause	2 days ago
Ta Libagiprolabs/claude-trading-skills	410	—	~2.4k	Automated safety check: Notes	MIT	1 mo ago

Similar skills

Python Executor
cortega26/chile-hub
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).
113 GitHub starsUsed in 2 repos~1.5k tokens
Data & AnalyticsAuto-check passed
Vaex Out-of-Core DataFrames
davila7/claude-code-templates
Processes tabular datasets too large for RAM with Vaex: lazy DataFrames, fast aggregations, big-data plots and ML pipelines over CSV, HDF5, Arrow and Parquet.
32k GitHub starsUsed in 12 repos~1.6k tokens
Data & AnalyticsAuto-check passed
Candlestick Pattern Signals
HKUDS/Vibe-Trading
Detects 15 classic candlestick patterns with vectorized pandas code and combines bullish and bearish scores into a long, short or flat trading signal.
35k GitHub stars~468 tokensUpdated yesterday
Business, Finance & HRAuto-check passed
Dask
K-Dense-AI/scientific-agent-skills
Scales pandas, NumPy, and custom Python research workflows beyond memory or across clusters with Dask.
48k GitHub starsUsed in 1 repo~4.4k tokens
Data & AnalyticsAuto-check: notes
Ta Lib
agiprolabs/claude-trading-skills
C-optimized technical analysis with 150+ functions and 61 candlestick pattern recognition functions via TA-Lib
410 GitHub stars~2.4k tokensUpdated 1 mo ago
Data & AnalyticsAuto-check: notes
Scikit Learn Machine Learning
jaechang-hits/SciAgent-Skills
Classical ML in Python: classification, regression, clustering, dim reduction, evaluation, tuning, preprocessing pipelines.
370 GitHub starsUsed in 1 repo~4k tokens
Data & AnalyticsAuto-check passed

Questions about Add Python Microservice

What does Add Python Microservice do?

TRIGGER when user asks to create a microservice that calls Python, runs ML inference, or uses Python libraries (PyTorch, pandas, sentence-transformers, numpy) for its core compute. Add Python Microservice is an agent skill from microbus-io/fabric. TRIGGER when user asks to create a microservice that calls Python, runs ML inference, or uses Python libraries (PyTorch, pandas, sentence-transformers, numpy) for its core compute.

When should I use Add Python Microservice?

Add Python Microservice fits situations like: user asks to create a microservice that calls Python; runs ML inference; uses Python libraries (PyTorch; sentence-transformers.

How do I install Add Python Microservice in Claude Code?

Run `npx skills add microbus-io/fabric --skill add-python-microservice -a claude-code`. Or copy the skill folder (.claude/skills/python/add-python-microservice in microbus-io/fabric) into .claude/skills/add-python-microservice in your project. Claude Code loads it when a task matches its description.

How do I install Add Python Microservice in Codex?

Run `npx skills add microbus-io/fabric --skill add-python-microservice -a codex`. Or copy the skill folder (.claude/skills/python/add-python-microservice in microbus-io/fabric) into .agents/skills/add-python-microservice in your project. Codex loads it when a task matches its description.

Can I use Add Python Microservice in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microbus-io/fabric --skill add-python-microservice -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/add-python-microservice, .gemini/skills/add-python-microservice, .github/skills/add-python-microservice and .opencode/skills/add-python-microservice in your project.

What does Add Python Microservice need to run?

Going by SKILL.md and its folder, Add Python Microservice needs Go and Python for the scripts in its folder. Our summary lists: Python 3.

Does Add Python Microservice access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Add Python Microservice safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Add Python Microservice use?

Add Python Microservice is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Add Python Microservice use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Add Python Microservice?

Skills that share tags, products or a category with Add Python Microservice: Python Executor (cortega26/chile-hub, 113 stars), Vaex Out-of-Core DataFrames (davila7/claude-code-templates, 32k stars), Candlestick Pattern Signals (HKUDS/Vibe-Trading, 35k stars) and Dask (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Add Python Microservice?

microbus-io (a GitHub organization) maintains it in microbus-io/fabric, which has 172 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on September 28, 2026.

Source: microbus-io/fabric on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Add Python Microservice

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Workflow

Step 1: Run add-microservice

Step 2: Add Python Source Files

Step 3: Add python.go

Step 4: Extend the Service Fields

Step 5: Add MaxWorkers Config

Step 6: Wire OnStartup and OnShutdown

Step 7: Housekeeping

Files

Compare with similar skills

Similar skills

More from microbus-io/fabric

Related

Questions about Add Python Microservice

Step 1: Run `add-microservice`

Step 3: Add `python.go`

Step 5: Add `MaxWorkers` Config

Step 6: Wire `OnStartup` and `OnShutdown`