wraith-proxy/wraith-skills
Agents don't hesitate before prod. wraith is the ghost that does. Skills and agents for data and infrastructure engineering on GCP: dbt, BigQuery, Cloud Run, Terraform, ODCS data contracts and ontologies.
field: Data & analyticsCloud & infrastructure workflow: Data / ETLPlanning & specsCI/CD & deployPR / code reviewTesting & TDD runs claude in CI
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit wraith-proxy/wraith-skills/.claude ./rig-wraith-skills # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit wraith-proxy/wraith-skills/skills/bigquery .claude/skills/bigquery $ npx degit wraith-proxy/wraith-skills/skills/brainstorming .claude/skills/brainstorming $ npx degit wraith-proxy/wraith-skills/skills/careful .claude/skills/careful $ npx degit wraith-proxy/wraith-skills/skills/cloud-run .claude/skills/cloud-run $ npx degit wraith-proxy/wraith-skills/skills/context-layer .claude/skills/context-layer $ npx degit wraith-proxy/wraith-skills/skills/dbt-bigquery .claude/skills/dbt-bigquery $ npx degit wraith-proxy/wraith-skills/skills/deploy .claude/skills/deploy $ npx degit wraith-proxy/wraith-skills/skills/grilling .claude/skills/grilling $ npx degit wraith-proxy/wraith-skills/skills/handoff .claude/skills/handoff $ npx degit wraith-proxy/wraith-skills/skills/knowledge-base .claude/skills/knowledge-base $ npx degit wraith-proxy/wraith-skills/skills/odcs-contracts .claude/skills/odcs-contracts $ npx degit wraith-proxy/wraith-skills/skills/ontology-modeling .claude/skills/ontology-modeling $ npx degit wraith-proxy/wraith-skills/skills/orchestrating-agents .claude/skills/orchestrating-agents $ npx degit wraith-proxy/wraith-skills/skills/plan-data-review .claude/skills/plan-data-review $ npx degit wraith-proxy/wraith-skills/skills/plan-infra-review .claude/skills/plan-infra-review $ npx degit wraith-proxy/wraith-skills/skills/qa .claude/skills/qa $ npx degit wraith-proxy/wraith-skills/skills/review .claude/skills/review $ npx degit wraith-proxy/wraith-skills/skills/security-audit .claude/skills/security-audit $ npx degit wraith-proxy/wraith-skills/skills/setup .claude/skills/setup $ npx degit wraith-proxy/wraith-skills/skills/ship .claude/skills/ship $ npx degit wraith-proxy/wraith-skills/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit wraith-proxy/wraith-skills/skills/tdd .claude/skills/tdd $ npx degit wraith-proxy/wraith-skills/skills/terraform-gcp .claude/skills/terraform-gcp $ npx degit wraith-proxy/wraith-skills/skills/using-wraith .claude/skills/using-wraith $ npx degit wraith-proxy/wraith-skills/skills/verification-before-completion .claude/skills/verification-before-completion $ npx degit wraith-proxy/wraith-skills/skills/wizard .claude/skills/wizard $ npx degit wraith-proxy/wraith-skills/skills/writing-plans .claude/skills/writing-plans $ npx degit wraith-proxy/wraith-skills/skills/writing-skills .claude/skills/writing-skills
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (28)
bigquerybrainstormingcarefulcloud-runcontext-layerdbt-bigquerydeploygrillinghandoffknowledge-baseodcs-contractsontology-modelingorchestrating-agentsplan-data-reviewplan-infra-reviewqareviewsecurity-auditsetupshipsystematic-debuggingtddterraform-gcpusing-wraithverification-before-completionwizardwriting-planswriting-skills
Similar rigs
simonblauth/claude-config
Claude Code config: user instructions, rules, and skills vendored from other repos under my own names
Fort Knox 1.3k tok · · Q19
pantyuhov9-web/agentic-workflow-template
Second brain + agentic workflow template — PARA knowledge layer + WAT execution layer for Claude Code
Skill Collector 3.7k tok · · Q43
mdiri-ai/SoduWork
The AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted.
Skill Collector 2.5k tok · · Q0
Viqto0r/zames_pro
Terminal coding agent that drives chat.deepseek.com or chat.qwen.ai through Playwright — no API key required. Reads/edits files, runs commands, commits to git.
Pragmatist 11.3k tok · · Q8