New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Neocarta Add Connector CLI Command

by neo4j-labs in neo4j-labs/neocarta

Scaffold, wire, and verify a neocarta CLI command that wraps a source/format connector (the neocarta <source <verb integration that follows building the library connector).

Apache-2.0Auto-check passedAI & LLM Engineering

Install Neocarta Add Connector CLI Command

skills CLI
$ npx skills add neo4j-labs/neocarta --skill neocarta-add-connector-cli-command -a claude-code

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

GitHub CLI
$ gh skill install neo4j-labs/neocarta neocarta-add-connector-cli-command --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/neo4j-labs/neocarta.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/neocarta-add-connector-cli-command .claude/skills/neocarta-add-connector-cli-command && 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/

Facts

Skill name
neocarta-add-connector-cli-command
GitHub stars
147
Token cost
~1.7k tokens
SKILL.md length
637 words
Files
3 (incl. scripts)
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Scaffold, wire, and verify a neocarta CLI command that wraps a source/format connector (the neocarta <source <verb integration that follows building the library connector).

  • Works in 7 steps: list to confirm the connector exists and… → scaffold (add --connector-pkg /… → Fill the TODOs in… → …
  • Asked to add/expose/wire a connector into the CLI
  • SKILL.md covers Scope, Prerequisites, Run (agent path) — the driver and Test, plus 2 more sections
  • Runs Python scripts from its folder; calls uv and make

What it does

Neocarta Add Connector CLI Command is an agent skill from neo4j-labs/neocarta. Scaffold, wire, and verify a neocarta CLI command that wraps a source/format connector (the neocarta <source <verb integration that follows building the library connector). Use when asked to add/expose/wire a connector into the CLI, add a neocarta <source subcommand, or check a connector command against the CLI contract. Connectors only — enrichment/embedding and MCP-tool CLI commands are separate skills.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `connector-cli-command-contract.md` and `scripts/driver.py`).

It sits in AI & LLM Engineering, covering Embeddings and MCP servers. The repository describes itself as: Library built for generating semantic layer graphs for query routing, query generation and data discovery. The licence is Apache-2.0.

When your agent uses it

  • Asked to add/expose/wire a connector into the CLI
  • Add a neocarta <source subcommand
  • Check a connector command against the CLI contract

Example prompts

  • “/neocarta-add-connector-cli-command”

Requirements

  • Python 3
  • Docker

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. list to confirm the connector exists and has no CLI command yet.
  2. scaffold (add --connector-pkg / --connector-class / repeated
  3. Fill the TODOs in neocarta/_cli/commands/.py: the connector's real
  4. Promote the --source input to a CLISettings field + an ENV_VARS entry in
  5. Flesh out the unit test for connector-specific behaviour beyond the skeleton.
  6. verify until green.
  7. Run the full CLI suite + ruff, update CHANGELOG.md.

What it can do on your machine

Read from SKILL.md and the folder at commit ba6bf79. 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 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv
    • make

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    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

Neocarta Add Connector CLI Command loads about 1.7k tokens when it runs. Until then it costs about 113 tokens; SKILL.md has 637 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~113
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from neo4j-labs/neocarta at commit ba6bf79, republished under its Apache-2.0 licence (© neo4j-labs). 637 words, ~1,725 tokens.

Download SKILL.mdSave it as .claude/skills/neocarta-add-connector-cli-command/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
neocarta-add-connector-cli-command
description
Scaffold, wire, and verify a neocarta CLI command that wraps a source/format connector (the `neocarta <source> <verb>` integration that follows building the library connector). Use when asked to add/expose/wire a connector into the CLI, add a `neocarta <source>` subcommand, or check a connector command against the CLI contract. Connectors only — enrichment/embedding and MCP-tool CLI commands are separate skills.

Wire an existing source/format connector into the neocarta CLI as a neocarta <source> <verb> command. This file is the operational loop; the full prose standard lives in connector-cli-command-contract.md (read it before designing a command — it's self-contained). Drive the whole loop with the driver: .claude/skills/neocarta-add-connector-cli-command/scripts/driver.py, run through uv.

All paths below are relative to the repo root.

Scope

  • Connectors only. This is for source/format connector commands. The CLI will also grow enrichment/embedding commands and MCP-tool commands — those are separate skills, not this one.
  • Follow-up PR, not the connector itself. The library connector under neocarta/connectors/ is built and verified by the neocarta-add-source-connector skill, which defers CLI wiring to here. Build the connector first; this skill wraps it.

Prerequisites

The managed environment, with the CLI extras and dev groups installed:

bash
uv sync --all-groups --all-extras

(click/rich/pydantic-settings are the cli extra, not a dependency group, so plain uv sync --all-groups will not install the CLI — use --all-extras too.)

Run (agent path) — the driver

bash
# Gap map: every connector and whether it already has a CLI command:
uv run .claude/skills/neocarta-add-connector-cli-command/scripts/driver.py list

# Scaffold a command module + unit test and wire it into main.py.
# <source> is the CLI group name (== command-module stem). By default the
# connector package is the same name and the first exported *Connector is used:
uv run .claude/skills/neocarta-add-connector-cli-command/scripts/driver.py scaffold databricks

# Point at a specific package / class, and/or give multiple verbs:
uv run .claude/skills/neocarta-add-connector-cli-command/scripts/driver.py \
  scaffold bigquery --connector-pkg bigquery --connector-class BigQuerySchemaConnector \
  --verb schema --verb logs

# Verify a command against the contract (import, registration, agent-context,
# --help, ruff, and its unit test):
uv run .claude/skills/neocarta-add-connector-cli-command/scripts/driver.py verify databricks

scaffold writes a conformant skeleton — neocarta/_cli/commands/<source>.py (group + one ingest-shaped command per verb, with the dry-run / JSON / error plumbing already correct) and tests/unit/_cli/test_<source>.py — and wires the import + cli.add_command into main.py alphabetically (idempotent). The skeleton's --help and --dry-run work and the generated test passes as-is once the wrapped connector class is importable. You then fill the TODOs for the connector's real constructor and ingest() signature.

verify imports the module, checks the group is registered on cli, confirms it appears in neocarta agent-context, runs --help for each verb, runs ruff check on the module, and runs the unit test. It exits non-zero on any failure.

Typical workflow
  1. list to confirm the connector exists and has no CLI command yet.
  2. scaffold <source> (add --connector-pkg / --connector-class / repeated --verb as needed).
  3. Fill the TODOs in neocarta/_cli/commands/<source>.py: the connector's real constructor args and ingest() (or export()) call, and the success/dry-run payload fields.
  4. Promote the --source input to a CLISettings field + an ENV_VARS entry in neocarta/_cli/config.py (see contract §6), and resolve from settings instead of os.environ.
  5. Flesh out the unit test for connector-specific behaviour beyond the skeleton.
  6. verify <source> until green.
  7. Run the full CLI suite + ruff, update CHANGELOG.md.

Test

bash
make test-cli           # CLI unit tests — NOTE: make test-unit ignores tests/unit/_cli
make fmt && make lint   # ruff format + lint (select = ["ALL"]) — must be clean before PR
make test-it            # integration: real ingest into a Neo4j testcontainer (Docker)
Show full SKILL.md (284 more words)Show less

Gotchas

  • make test-unit does not run the CLI tests. They live under tests/unit/_cli which that target ignores; use make test-cli (the driver's verify runs the single new test file directly).
  • CLI deps are an extra, not a group. uv sync --all-groups alone omits click/rich; the CLI then fails to import. Sync with --all-extras.
  • The scaffold reads its input from os.environ, deliberately. That keeps the generated command + test self-contained and green before you touch config.py. Promote it to a CLISettings field (step 4) for the real PR — the house pattern resolves inputs from settings, not os.environ.
  • agent-context is generated, never hand-edited. It introspects the live command tree; a registered command with its ENV_VARS entry shows up automatically. If it's missing, the command isn't registered in main.py.
  • Multiple connector classes / non-ingest shapes need hand-editing. The scaffold emits one ingest-shaped command per --verb. A schema/logs split (like bigquery) or an export verb (like osi) starts from the scaffold, then adapt against bigquery.py / osi.py.
  • Don't unwrap the Neo4j password into a named local. Use the _common.py helpers (_require_neo4j_settings, _neo4j_driver) as-is; they keep the secret off CodeQL's logging-sink radar.

Troubleshooting

  • verify FAIL: cannot import neocarta.connectors.<pkg> — the library connector isn't built/installed yet, or --connector-pkg is wrong. Build the connector first (the neocarta-add-source-connector skill).
  • verify FAIL: <source> is not registered in main.py — re-run scaffold (the wiring step is idempotent) or add the import + cli.add_command(<source>) by hand, alphabetically.
  • verify FAIL: ruff — run make fmt then uv run ruff check neocarta/_cli/commands/<source>.py; the generated skeleton is clean, so a failure is in a TODO you filled.
  • scaffold WARN: exports no *Connector — the package has no connector class in __all__ yet (e.g. databricks, collibra are work-in-progress). Pass --connector-class explicitly or finish the library connector first.

© neo4j-labs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in .claude/skills/neocarta-add-connector-cli-command of neo4j-labs/neocarta.

  • SKILL.md
  • connector-cli-command-contract.md
  • scripts/driver.py

Open the folder on GitHubat commit ba6bf79

Compare with similar skills

Neocarta Add Connector CLI Command 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.

Neocarta Add Connector CLI Command compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Neocarta Add Connector CLI Command this skillneo4j-labs/neocarta147—~1.7kAutomated safety check: PassApache-2.0
Sandbaseiflytek/skillhub5.2k2 repos~2.1kAutomated safety check: PassApache-2.0
Siyuan MCP Visual Assetsyangtaihong59/siyuan-plugins-mcp-sisyphus116—~1.1kAutomated safety check: PassMIT
Cookbook Aimldatabricks-solutions/databricks-apps-cookbook183—~1.7kAutomated safety check: PassCustom licence
Civitaiartokun/comfyui-mcp803—~1.1kAutomated safety check: PassMIT
Review Logging Patternsactivepieces/activepieces25k—~8.2kAutomated safety check: PassMIT

Similar skills

  • Sandbase

    iflytek/skillhub

    Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval.

    5.2k GitHub starsUsed in 2 repos~2.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Siyuan MCP Visual Assets

    yangtaihong59/siyuan-plugins-mcp-sisyphus

    MCP playbook for semantic SVG charts and figures, approved asset upload, and verified SiYuan block embedding.

    116 GitHub stars~1.1k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

  • Cookbook Aiml

    databricks-solutions/databricks-apps-cookbook

    Invoke ML models, run vector search, and connect to MCP servers from Databricks Apps.

    183 GitHub stars~1.7k tokensUpdated 6 days ago
    AI & LLM EngineeringAuto-check passed

  • Civitai

    artokun/comfyui-mcp

    Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally.

    803 GitHub stars~1.1k tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check passed

  • Review Logging Patterns

    activepieces/activepieces

    Review code for logging patterns and suggest evlog adoption.

    25k GitHub stars~8.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Configuring Agent Brain

    SpillwaveSolutions/agent-brain

    Installation and configuration skill for Agent Brain document search system.

    119 GitHub stars~7k tokensUpdated 21 days ago
    AI & LLM EngineeringAuto-check: notes

More from neo4j-labs/neocarta

  • Neocarta Add Source Connector

    neo4j-labs/neocarta

    Scaffold, build, and verify a neocarta source or format connector against the connector contract.

    147 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Neocarta Add Connector CLI Command

What does Neocarta Add Connector CLI Command do?

Scaffold, wire, and verify a neocarta CLI command that wraps a source/format connector (the neocarta <source <verb integration that follows building the library connector). Neocarta Add Connector CLI Command is an agent skill from neo4j-labs/neocarta. Scaffold, wire, and verify a neocarta CLI command that wraps a source/format connector (the neocarta <source <verb integration that follows building the library connector).

When should I use Neocarta Add Connector CLI Command?

Neocarta Add Connector CLI Command fits situations like: asked to add/expose/wire a connector into the CLI; add a neocarta <source subcommand; check a connector command against the CLI contract.

How do I install Neocarta Add Connector CLI Command in Claude Code?

Run `npx skills add neo4j-labs/neocarta --skill neocarta-add-connector-cli-command -a claude-code`. Or copy the skill folder (.claude/skills/neocarta-add-connector-cli-command in neo4j-labs/neocarta) into .claude/skills/neocarta-add-connector-cli-command in your project. Claude Code loads it when a task matches its description.

How do I install Neocarta Add Connector CLI Command in Codex?

Run `npx skills add neo4j-labs/neocarta --skill neocarta-add-connector-cli-command -a codex`. Or copy the skill folder (.claude/skills/neocarta-add-connector-cli-command in neo4j-labs/neocarta) into .agents/skills/neocarta-add-connector-cli-command in your project. Codex loads it when a task matches its description.

Can I use Neocarta Add Connector CLI Command 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 neo4j-labs/neocarta --skill neocarta-add-connector-cli-command -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/neocarta-add-connector-cli-command, .gemini/skills/neocarta-add-connector-cli-command, .github/skills/neocarta-add-connector-cli-command and .opencode/skills/neocarta-add-connector-cli-command in your project.

What does Neocarta Add Connector CLI Command need to run?

Going by SKILL.md and its folder, Neocarta Add Connector CLI Command needs Python for the scripts in its folder and the command-line tools its instructions call (uv and make). Our summary lists: Python 3; Docker.

Does Neocarta Add Connector CLI Command access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Neocarta Add Connector CLI Command 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Neocarta Add Connector CLI Command use?

Neocarta Add Connector CLI Command 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 Neocarta Add Connector CLI Command use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 Neocarta Add Connector CLI Command?

Skills that share tags, products or a category with Neocarta Add Connector CLI Command: Sandbase (iflytek/skillhub, 5.2k stars), Siyuan MCP Visual Assets (yangtaihong59/siyuan-plugins-mcp-sisyphus, 116 stars), Cookbook Aiml (databricks-solutions/databricks-apps-cookbook, 183 stars) and Civitai (artokun/comfyui-mcp, 803 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Neocarta Add Connector CLI Command?

neo4j-labs (a GitHub organization) maintains it in neo4j-labs/neocarta, which has 147 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 9, 2026.

Source: neo4j-labs/neocarta on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.