swamp

Operate the swamp CLI to manage models, workflows, data, vaults, and extensions.

2|Updated Oct 16, 2021
One-click install
npx skills add https://github.com/pattobrien/dotfiles --skill swamp-pattobrien
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: swamp
Source: https://github.com/pattobrien/dotfiles/tree/main/claude/skills/swamp
Command: npx skills add https://github.com/pattobrien/dotfiles --skill swamp-pattobrien

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Working with the swamp CLI involves many subcommands across models, workflows, data, vaults, reports, extensions, and access control, and guessing flags or bypassing the CLI leads to errors and stale state. This Skill routes each user intent to the correct operational guide so swamp commands are executed accurately and safely. ## Core Features & Use Cases - Intent Routing: A routing table maps user goals (models, workflows, data, vaults, reports, repos, extensions, publishing, issues, serve, troubleshooting) to the right reference guide. - Command Reference: Quick-reference tables cover creating and running models, validating and resuming workflows, querying data with CEL expressions, storing vault secrets, and managing grants. - Safe Execution Workflow: Enforces validate-before-run and inspect-before-destroy rules, plus a four-tier troubleshooting process for diagnosing failures. - Use Case: A user asks to run a workflow with inputs; the Skill loads the workflow guide, validates the DAG with swamp workflow validate, then executes swamp workflow run <name> --input key=value. ## Quick Start Ask the assistant to create and run a swamp workflow, query model data, or diagnose a failing swamp command.

Frequently Asked Questions about swamp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create and run a swamp workflow?▼

Run `swamp workflow create <name> --json` to generate a scaffold with an assigned ID, edit the YAML at the returned path, then validate with `swamp workflow validate <name>` before executing `swamp workflow run <name>`. Never write workflow YAML from scratch or modify the id field.

How do I query swamp model data with CEL expressions?▼

Use `swamp data query '<CEL predicate>'` for general queries over artifact metadata and content, with optional `--select` projections. Shortcuts like `swamp data get <model> <name>` and `swamp data list <model>` map to equivalent queries for common cases.

When should I use a swamp model versus a workflow?▼

Use a model when you need a 1:1 representation of an external resource with typed methods like create, sync, or destroy. Use a workflow when you need to orchestrate multiple model methods in a DAG with dependencies, conditions, and parallelism.

How do I store and read secrets in swamp vaults?▼

Create a vault with `swamp vault create <type> <name> --json`, then store secrets with `swamp vault put <vault> KEY` (prompts for the value) or read them with `swamp vault read-secret <vault> <key> --force --json`. Models reference secrets via vault.get() expressions.

Why is my swamp extension not loading?▼

Run `swamp doctor extensions --json` to diagnose loading failures and check stderr for `swamp-warning:` lines. Common causes include missing exports, stale bundle caches (delete `.swamp/<type>-bundles/` and retry), or outdated extensions reported by `swamp extension outdated`.

When should I not use this swamp skill?▼

Do not use it for getting started or onboarding (use swamp-getting-started), pull requests, git operations, worktree management, cron or agent scheduling, or general coding tasks unrelated to swamp commands.