> For the complete documentation index, see [llms.txt](https://developer.celigo.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.celigo.com/cli/using-the-cli/skills.md). # AI assistant skills Give your AI coding assistant grounded knowledge of integrator.io. Skills are domain-specific guides an assistant loads on demand. Ask Claude Code, Cursor, or Windsurf to "build a Shopify to NetSuite flow" or "debug this stuck job," and the assistant reads the relevant skill's workflow guidance and field schemas instead of guessing. ## Installing skills Skills live in the public `celigo/ai` repository, and the CLI installs them through the official `skills` CLI. Install them yourself with `celigo skills install`, or let the CLI install them in the background. ### `celigo skills install` ```bash celigo skills install # detect your agents, prompt for a selection celigo skills install --global --all --yes # every skill, every detected agent, no prompts celigo skills install --list # show the catalog without installing celigo skills install --skill building-flows --skill writing-sql celigo skills install --agent claude-code celigo skills install --copy # copy files instead of creating symlinks ``` | Flag | Purpose | | ------------------------- | ------------------------------------------------------------------------------------------------------- | | `-g, --global` | Install for the current user rather than the current project. | | `-a, --agent ` | Install for specific agents only. Repeatable. | | `-s, --skill ` | Install specific skills only. Repeatable. | | `-l, --list` | List the available Celigo skills and exit without installing. | | `--copy` | Copy the skill files instead of creating symlinks. Use this when your tooling does not follow symlinks. | | `-y, --yes` | Skip the installer's confirmation prompts. | | `--all` | Install every skill for every detected agent. | ### `celigo skills list` ```bash celigo skills list # everything the skills CLI has installed celigo skills list --global # globally installed only celigo skills list --agent cursor ``` ### `celigo skills update` ```bash celigo skills update # update every installed Celigo skill celigo skills update building-flows # update named skills celigo skills update --global # globally installed only celigo skills update --project # project-installed only celigo skills update --all-installed # include skills that did not come from Celigo ``` `--all-installed` updates every skill the skills CLI manages, including skills from other publishers. Without it, `update` touches Celigo skills only. ### Background installation Any `celigo` command can install skills in the background so an agent driving the CLI has them without a manual step. The check runs at most once every 24 hours and never blocks the command that triggered it. With no exclusions set, it installs the same skills as `celigo skills install --global --all --yes`. Before installing anything, the background process reads the current commit of the public `celigo/ai` repository. It compares that commit against the one it last installed. Matching commits mean your skills are already current, so it installs nothing and prints nothing. Reading the remote commit needs `git` and network access; without either, it installs without the comparison. When it does install, it prints one line on stderr naming the opt-outs. The background install is skipped in these cases: * The command is `celigo skills …` or `celigo config …`, so an explicit install or opt-out is never raced. * The CLI detects a CI environment. * The last check was less than 24 hours ago. * The `celigo/ai` commit already installed has not changed, and neither has your exclusion list. ## Opting out Two settings turn the background install off, and one narrows it: ```bash # One run, or one shell session export CELIGO_NO_SKILLS_INSTALL=1 # Persistent, machine-wide celigo config set skills_auto_install false # Keep the background install, but never install these celigo config set skills_auto_install_exclude writing-sql,writing-handlebars celigo config set skills_auto_install_exclude "" # clear the list ``` `skills_auto_install` and `skills_auto_install_exclude` are machine-wide, not per profile — one CLI installation serves every profile. See [Configuration reference](/cli/getting-started/configuration.md). ### Excluding individual skills `skills_auto_install_exclude` is the durable way to keep a skill off your machine. Deleting the skill's files is not durable on its own. The background install cannot tell a deliberate deletion from a half-finished one. It restores the skill the next time `celigo/ai` changes. Name the skill in the setting, delete its files once, and it stays gone. The setting narrows the background install, not the CLI: * A non-empty list makes the background install request every other skill by name, rather than all of them. Its stderr notice reports what it skipped. * Naming the rest requires the skill list from `celigo/ai`. An unreadable list, or one that excludes every skill, means the background install skips that run. It retries the next day. * Changing the list takes effect at the next daily check, even when `celigo/ai` has not moved. * An explicit `celigo skills install` ignores the setting. It governs the background install, not what you install on purpose. `--all` still means all. ## Where skills are installed The skills CLI writes into whichever agent directories it detects: | Assistant | Global install path | Local (per-project) path | | ----------- | ----------------------------- | ----------------------------- | | Claude Code | `~/.claude/skills/` | `/.claude/skills/` | | Cursor | `~/.cursor/skills/` | `/.cursor/skills/` | | Windsurf | `~/.codeium/windsurf/skills/` | `/.windsurf/skills/` | Each entry is named for the skill itself, for example `building-flows`. > **Upgrading from celigo-cli 2026.6.1 or earlier.** Those releases installed skills through an npm `postinstall` hook, under names prefixed `npm-celigo-cli-`. That hook is gone. The prefixed directories are left in place and are not updated, so delete them once `celigo skills list` shows the current skills. ## How they work Each skill directory contains: * **`SKILL.md`** — a workflow guide the assistant reads when the skill triggers. It describes the task scope, the build order, common pitfalls, and concrete examples. * **`references/`** — OpenAPI-derived field schemas in YAML for the resources the skill touches, so the assistant writes JSON that validates against integrator.io. The assistant selects one or more skills based on your question, loads each `SKILL.md`, and uses the schemas to produce valid configuration. Asking to set up an HTTP export with a delta cursor pulls in `configuring-exports` and `writing-handlebars`. ## What ships **Orientation** `celigo skills install --list` prints the current catalog. The skills below are what `celigo/ai` publishes today. **Orientation and administration** * `getting-started` — core concepts, build order, and which skill to use for each task. Start here when a task is unclear or you're new to Celigo. * `troubleshooting-flows` — diagnose flow failures: total failures, partial errors, stuck jobs, empty runs, performance issues. * `managing-users` — invite users, update permissions, configure access levels, enforce MFA/SSO, disable accounts. * `managing-integrations` — organize, clone, promote, and version integrations, including Integration Lifecycle Management revisions and snapshots. * `managing-api-tokens` — create, scope, rotate, revoke, and delete API tokens and personal access tokens. * `managing-stacks` — decide whether you need a stack, choose between `server` and `lambda`, and point a hook at one. * `managing-on-premise-agents` — connect to systems behind a firewall, install and pair an agent, rotate its token. * `using-marketplace-templates` — find, install, and reuse Marketplace templates and Integration Apps. **Build** * `building-flows` — pipelines that move data from source to destination on a schedule or in response to events. Covers scheduling, chaining, error management, and abstract/instance templating. * `building-apis` — custom HTTP endpoints that let external systems push or query data synchronously through Celigo. * `building-tools` — reusable building blocks that encapsulate lookups, imports, transforms, and branching behind input/output contracts. * `building-mcp-servers` — MCP endpoints that expose Tools and builder-mode APIs to external AI agents and MCP clients. * `building-b2b` — B2B Manager EDI integrations: trading partner onboarding, EDI profiles, file definitions, X12/EDIFACT flow patterns. **Configure** * `configuring-connections` — credentials and configuration objects that authenticate to external systems. Auth methods, OAuth, iClients. * `configuring-exports` — the data source step: choose adaptor type, set up delta/incremental syncs, webhooks, file transfers, lookups. * `configuring-imports` — the destination step: choose adaptor type, mappings, lookups, upsert logic, AI agent and file imports. * `configuring-lookup-caches` — in-memory key-value stores for fast lookups, dedup, cross-reference resolution, state tracking. * `configuring-ai-agents` — LLM-powered flow steps that classify, extract, validate, or generate data. OpenAI, Gemini, BYOK. * `configuring-guardrails` — safety and compliance checks: PII detection, content moderation, AI-based evaluation rules. * `configuring-filters` — filter rules on exports, imports, and flow branches that control which records continue. **Write** * `writing-mappings` — field mappings and transforms: Mapper 2.0 (imports), Transformation 2.0 (exports), lookups, response mapping, Mapper 1.0. * `writing-scripts` — Celigo JavaScript hook scripts: `preSavePage`, `preMap`, `postMap`, `postSubmit`, `postResponseMap`, filter, transform, branching, `handleRequest`. * `writing-handlebars` — Handlebars template expressions for dynamic values in mappings, HTTP bodies, SQL queries, URIs, filters. * `writing-sql` — SQL for RDBMS exports and imports across Snowflake, Postgres, MySQL, SQL Server, Oracle, BigQuery, Redshift. ## Seeing what's installed ```bash celigo skills list celigo skills list --global ``` ## Schema source of truth Each skill's `references/schemas/` holds field schemas derived from the OpenAPI specs behind the API reference. Skills are published from the public `celigo/ai` repository, so `celigo skills update` picks up schema changes without a CLI upgrade. What your assistant reads in a skill reflects the current API. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://developer.celigo.com/cli/using-the-cli/skills.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.