setup
/setup
Use once per repository before relying on the other wraith skills, or when the user asks to configure wraith. Records the project's commands, GCP projects, dbt targets and conventions in an AGENTS.md wraith block that every wraith skill reads, and recommends vendor companions.
- Author
- wraith-proxy ↗
- Repository
- wraith-skills ↗
- Licence
- MIT
- Last repository change
- 13.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 1
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- SKILL.md zawiera komentarze HTML (1). Nie widać ich w podglądzie Markdown, a model je czyta.
What it does and when to use it
Use once per repository before relying on the other wraith skills, or when the user asks to configure wraith. Records the project's commands, GCP projects, dbt targets and conventions in an AGENTS.md wraith block that every wraith skill reads, and recommends vendor companions.
Original author description
Use once per repository before relying on the other wraith skills, or when the user asks to configure wraith. Records the project's commands, GCP projects, dbt targets and conventions in an AGENTS.md wraith block that every wraith skill reads, and recommends vendor companions.
How it works
- Process
SKILL.md preview
--- name: setup description: "Use once per repository before relying on the other wraith skills, or when the user asks to configure wraith. Records the project's commands, GCP projects, dbt targets and conventions in an AGENTS.md wraith block that every wraith skill reads, and recommends vendor companions." license: MIT metadata: source: MP@d1478fc:skills/engineering/setup-matt-pocock-skills/SKILL.md --- # Setup Scaffold the per-repo configuration that the other wraith skills read. This is a prompt-driven skill, not a deterministic script. Explore, present what you found, confirm with the user, then write. ## Process ### 1. Detect Look at the current repo. Read whatever exists; don't assume: - `dbt_project.yml` - `*.tf` - `Dockerfile` - `pyproject.toml` - `.github/workflows/` - YAML files with `apiVersion: v3` (ODCS contracts) - ontology YAML - existing `AGENTS.md` and `CLAUDE.md` ### 2. Ask Summarise what is present and what is missing. For each missing key, ask one question at a time, proposing the detected value. Lead with the recommended answer so the user can accept it in a word. ### 3. Write Show the user a draft, let them edit, then write or update this block in `AGENTS.md` (creating `AGENTS.md` if needed). The values below are examples: ```markdown ## wraith <!-- Read by the wraith plugin. Edit freely. --> - artifacts_dir: docs/wraith - glossary: GLOSSARY.md - gcp_project_dev: example-project-dev - gcp_project_prod: example-project-prod - region: europe-west2 - bigquery_location: europe-west2 - dbt_project_dir: dbt - dbt_target_dev: dev - dbt_target_prod: prod - dev_max_bytes_billed: 10000000000 - contracts_dir: contracts - ontology_file: ontology/ontology.yaml - context_dir: context - deploy_method: terraform - terraform_dir: infra ``` ### 4. CLAUDE.md If `CLAUDE.md` is missing, create it containing `@AGENTS.md`. If it exists without that import, append the line `@AGENTS.md`. ### 5. Companions Recommend missing companions. Never install anything yourself. For each one, recommend the companion and tell the user to install it with the commands in the wraith README's Companions section, after skimming its SKILL.md first: - `dbt_project.yml` present and no `using-dbt-for-analytics-engineering` skill listed: dbt Labs' dbt plugin. - `*.tf` files present and no `terraform-style-guide` skill listed: HashiCorp's terraform plugin. - BigQuery in use (`dbt-bigquery`, `google-cloud-bigquery` or `bq` in the repo) and no `bigquery-basics` skill listed: Google's BigQuery skills. - A Cloud Run service or job defined and no `cloud-run-basics` skill listed: Google's `cloud-run-basics`. - For general workflow (designs, plans, test-first work, debugging, code review, handoffs), mention obra/superpowers and mattpocock/skills as optional. wraith skills work without them. ### 6. Issue trackers Do not create issue-tracker files.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · wraith-proxy/wraith-skills | 100 | MIT |
| HwangSlater/harness-fit | 100 | MIT |
| nesquikm/dev-process-toolkit | 100 | MIT |
| userKael/rastro | 100 | MIT |
| als-apg/osprey | 100 | BSD-3-Clause |
| dedujeong/gemba | 100 | Apache-2.0 |
| eigenwise/eigenwise-toolshed | 100 | MIT |
| awrshift/agent-memory-kit | 100 | MIT |
| lifecycle-innovations-limited/claude-ops | 100 | MIT |
Database snapshot: 13.11.2026 · package version ad4a728394a5 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90using-wraith
Use when the user asks what wraith does or which wraith skill or agent fits a data or GCP task. Lists the wraith skills and agents and the rules they share. - 90suggesting-dbt-bouncer-checks
Analyzes a dbt project and suggests dbt-bouncer checks that already pass (for existing projects) or a sensible starter config (for greenfield projects). Use when adding dbt-bouncer to a project, creating or extending a dbt-bouncer.yml config, or enforcing dbt conventions with dbt-bouncer. - 95dbt-projects-snowflake-setup
Step-by-step setup guide for dbt Projects on Snowflake including prerequisites, external access integration, Git API integration, event table configuration, and automated scheduling. Use this skill when setting up dbt Projects on Snowflake for the first time or troubleshooting setup issues. - 100running-dbt-commands
Formats and executes dbt CLI commands, selects the correct dbt executable, and structures command parameters. Use when running models, tests, builds, compiles, or show queries via dbt CLI. Use when unsure which dbt executable to use or how to format command parameters. - 95dbt-bigquery
Expert guidance for creating, modifying, and optimizing dbt pipelines for BigQuery. Use this skill whenever user asks for generating or modifying a dbt model or project. Activate this skill when the user - Creates, modifies, or troubleshoots **dbt models or pipelines** - Needs… - 100dbt-projects-on-snowflake
Deploying, managing, executing, and monitoring dbt projects natively within Snowflake using dbt PROJECT objects and event tables. Use this skill when you want to set up dbt development workspaces, deploy projects to Snowflake, schedule automated runs, monitor execution with…