Check raw SQL against the data team's naming and formatting conventions. Superseded by dbt-helper, which covers the same conventions plus tests and documentation for the models the SQL belongs to.
0 on GitHubby Data Engineeringv1.2.0MITupdated 2 months agodata
/
Plugin sql-lint from marketplace acme in mwblima/ai-marketplace. Commands read from the repo's manifest — 1 month ago.
What it installs
Skills (1)
sql-lint
Check raw SQL against the data team's naming and formatting conventions.
Find and apply the company's operational runbooks during an incident, using the internal runbook MCP server. Use when a service is degraded and you need the documented procedure rather than an improvised one.
Run the repository's own formatter after the assistant edits a file, and only in repositories that already declare one. Use it to keep generated edits consistent with the project's existing formatting rules.
Review a pull request or working-tree diff against the company engineering standards, reporting correctness bugs, missing tests, and security issues with file and line references. Use before requesting human review on any change.
Write and review dbt models following the data team's layering and naming conventions, including tests and documentation for every new model. Use when adding or changing a model in the analytics repository.
Prepare and verify a service deployment: check the release checklist, confirm migrations are backward compatible, and produce the rollout and rollback plan. Use when shipping a backend service to staging or production.
Draft customer-facing incident updates in the company's voice: what is affected, what is being done, and when the next update comes. Use while an incident is open and customers need to be told something.
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
The official CCXT MCP server plus the ccxt-mcp usage skill — market data, balances and opt-in trading across 100+ crypto exchanges and prediction markets, with keys kept local.
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
wshobson/agents 42,461
Maintain SQL Lint?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.