Official agent skill

Build Connector

by elastic in elastic/kibana

End-to-end orchestrator that creates a new connector from scratch, reviews the code, activates it in Kibana, tests it via an Agent Builder agent, iterates until quality is met, and delivers a…

OfficialCustom licenceAuto-check: notesAI & LLM Engineering

Install Build Connector

skills CLI
$ npx skills add elastic/kibana --skill build-connector -a claude-code

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

GitHub CLI
$ gh skill install elastic/kibana build-connector --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/elastic/kibana.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/platform/packages/shared/kbn-connector-specs/.claude/skills/build-connector .claude/skills/build-connector && 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
build-connector
GitHub stars
21k
Token cost
~4.7k tokens
SKILL.md length
2,633 words
Files
1
Skills in repo
40
Repo updated
First seen
Licence
Custom licence

At a glance

End-to-end orchestrator that creates a new connector from scratch, reviews the code, activates it in Kibana, tests it via an Agent Builder agent, iterates until quality is met, and delivers a…

  • Works in 12 steps: Create the connector code — "Generate… → Code review — "Review generated… → Edit based on review — "Fix issues found… → …
  • Implement a complete connector
  • SKILL.md covers Prerequisites, Step 0: Create the Task List, Task 1: Create the Connector… and Task 2: Code Review, plus 11 more sections
  • Calls gh and git

What it does

Build Connector is an agent skill from elastic/kibana, published by the product's own GitHub organization. End-to-end orchestrator that creates a new connector from scratch, reviews the code, activates it in Kibana, tests it via an Agent Builder agent, iterates until quality is met, and delivers a polished result. Use when asked to build, develop, or implement a complete connector.

Its SKILL.md is about 4.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Building AI agents and End-to-end testing. It works with Elasticsearch. The repository describes itself as: Your window into all of your data.

When your agent uses it

  • Implement a complete connector
  • Tasks that involve Building AI agents
  • Tasks that involve End-to-end testing

Example prompts

  • “/build-connector”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Read, Glob, Grep, Write, Edit, Skill

Workflow steps

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

  1. Create the connector code — "Generate connector spec, types, and documentation for $ARGUMENTS"
  2. Code review — "Review generated connector files for correctness and completeness"
  3. Edit based on review — "Fix issues found during code review"
  4. Wait for Kibana — "Ask user to start Elasticsearch and Kibana"
  5. Activate the connector — "Create a connector instance in running Kibana"
  6. Create a test agent — "Create an Agent Builder agent wired to the new connector tools"
  7. Chat test — "Send a test message to the agent and observe tool calls"
  8. Verify tool call quality — "Analyze chat results for successful tool executions"
  9. Iterate on quality — "Fix code issues and re-test until quality bar is met"
  10. Final code review — "Final review of all generated files and documentation"
  11. Final chat test — "Final end-to-end conversation to confirm everything works"
  12. Compile the PR validation table — "Build the ## Validated action-by-action table for the PR description"

What it can do on your machine

Read from SKILL.md and the folder at commit 452e025. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Glob
    • Grep
    • Write
    • Edit
    • Skill

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use gh and git, 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

Build Connector loads about 4.7k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 2,633 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~4.7k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Glob, Grep, Write, Edit, Skill

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,633 words (~4,728 tokens).

“This skill orchestrates the full lifecycle of building a new connector for $ARGUMENTS. It chains together multiple skills and performs code review and quality verification between each stage.”

— opening of SKILL.md by elastic, Custom licence
name
build-connector
allowed-tools
Bash, Read, Glob, Grep, Write, Edit, Skill
argument-hint
3rd-party-service-name

Read the full SKILL.md on GitHub

Files

Just SKILL.md in src/platform/packages/shared/kbn-connector-specs/.claude/skills/build-connector of elastic/kibana.

Open the folder on GitHubat commit 452e025

Compare with similar skills

Build Connector 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.

Build Connector compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Build Connector this skillelastic/kibana21k—~4.7kAutomated safety check: NotesCustom licence
Schema Coverageelastic/terraform-provider-elasticstack210—~1.4kAutomated safety check: PassApache-2.0
Kibana Agent Builderelastic/agent-skills592—~3.4kAutomated safety check: PassApache-2.0
Agentsop Test Fix Loopagentsope/SkillAlchemy466—~7.2kAutomated safety check: PassMIT
Google Agents CLI Adk Codepifferologo/cloud-agents-cli1291 repos~768Automated safety check: PassApache-2.0
Create Taskmelandlabs/openloomi1k—~4.6kAutomated safety check: PassApache-2.0

Similar skills

  • Schema Coverage

    elastic/terraform-provider-elasticstack

    Official

    Analyzes a Terraform resource schema and compares it to attributes used in the acceptance test suite (configs + assertions).

    210 GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Kibana Agent Builder

    elastic/agent-skills

    Official

    Create and manage Kibana Agent Builder agents and custom tools.

    592 GitHub stars~3.4k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Agentsop Test Fix Loop

    agentsope/SkillAlchemy

    Decision protocol for wiring a verify-then-fix loop around a code-editing LLM agent.

    466 GitHub stars~7.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Google Agents CLI Adk Code

    pifferologo/cloud-agents-cli

    This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management", or needs ADK (Agent…

    129 GitHub starsUsed in 1 repo~768 tokens
    AI & LLM EngineeringAuto-check passed
  • Create Task

    melandlabs/openloomi

    Create an end-to-end Continual Learning Bench task. An agent skill from melandlabs/openloomi.

    1k GitHub stars~4.6k tokensUpdated 15 days ago
    Testing & QAAuto-check passed
  • Create Agent Pack

    coda/packs-sdk

    Create, build, validate, and upload a Packs SDK agent (pack.ts using sdk.newAgent()) to your Coda/Superhuman account, including registering an API token, wiring up tools…

    112 GitHub stars~2.2k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from elastic/kibana

All 40 skills in this repo
  • Official

    Migrate Kibana Cypress E2E tests (.cy.ts) to Scout (Playwright).

    21k GitHub stars~3.8k tokensUpdated today
    Auto-check passed
  • Activate Connector

    elastic/kibana

    Official

    Creates a connector instance in a running Kibana. An agent skill from elastic/kibana.

    21k GitHub stars~1.9k tokensUpdated today
    Auto-check: notes
  • Codeql

    elastic/kibana

    Official

    Work with CodeQL in Kibana — write, test, and debug custom queries locally, fetch scan results from GitHub, and validate inline suppression comments.

    21k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Debug Oas

    elastic/kibana

    Official

    A skill your agent uses when debugging OpenAPI (OAS) issues for a specific API area in Kibana by scoping validation output with one or more --path filters, then separating structural invalid-OAS…

    21k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Evals Write Spec

    elastic/kibana

    Official

    Write LLM evaluation spec files with datasets, tasks, and evaluators using the @kbn/evals Playwright fixture.

    21k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Kbn GitHub

    elastic/kibana

    Official

    GitHub interactions via gh CLI for the Kibana repo. An agent skill from elastic/kibana.

    21k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Works with

Questions about Build Connector

What does Build Connector do?

End-to-end orchestrator that creates a new connector from scratch, reviews the code, activates it in Kibana, tests it via an Agent Builder agent, iterates until quality is met, and delivers a…. Build Connector is an agent skill from elastic/kibana, published by the product's own GitHub organization. End-to-end orchestrator that creates a new connector from scratch, reviews the code, activates it in Kibana, tests it via an Agent Builder agent, iterates until quality is met, and delivers a polished result.

When should I use Build Connector?

Build Connector fits situations like: implement a complete connector; tasks that involve Building AI agents; tasks that involve End-to-end testing.

How do I install Build Connector in Claude Code?

Run `npx skills add elastic/kibana --skill build-connector -a claude-code`. Or copy the skill folder (src/platform/packages/shared/kbn-connector-specs/.claude/skills/build-connector in elastic/kibana) into .claude/skills/build-connector in your project. Claude Code loads it when a task matches its description.

How do I install Build Connector in Codex?

Run `npx skills add elastic/kibana --skill build-connector -a codex`. Or copy the skill folder (src/platform/packages/shared/kbn-connector-specs/.claude/skills/build-connector in elastic/kibana) into .agents/skills/build-connector in your project. Codex loads it when a task matches its description.

Can I use Build Connector 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 elastic/kibana --skill build-connector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/build-connector, .gemini/skills/build-connector, .github/skills/build-connector and .opencode/skills/build-connector in your project.

What does Build Connector need to run?

Going by SKILL.md and its folder, Build Connector needs the command-line tools its instructions call (gh and git). Its frontmatter pre-approves these tools: Bash, Read, Glob, Grep, Write, Edit, Skill.

Does Build Connector access the network?

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

Is Build Connector safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Build Connector use?

Build Connector has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Build Connector use?

About 4.7k tokens (SKILL.md is roughly 19k 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 Build Connector?

Skills that share tags, products or a category with Build Connector: Schema Coverage (elastic/terraform-provider-elasticstack, 210 stars), Kibana Agent Builder (elastic/agent-skills, 592 stars), Agentsop Test Fix Loop (agentsope/SkillAlchemy, 466 stars) and Google Agents CLI Adk Code (pifferologo/cloud-agents-cli, 129 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Build Connector?

elastic (a GitHub organization, an official publisher) maintains it in elastic/kibana, which has 21,307 GitHub stars. The repository holds 40 skills in this directory. The repository was last updated on October 9, 2026.

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