Trade-offs to check before shipping SQL Server code: 54 cards from the Before You Ship That chart, each with one action and what it costs, what it risks, how fast it works, and when it backfires. Covers new and existing queries, tables, and indexes.
Plugin sqlserver-before-you-ship from marketplace erikdarling in erikdarlingdata/claude-plugins. Commands read from the repo's manifest — yesterday.
before-you-shipTrade-offs to check before shipping SQL Server code, from Erik Darling's "Before you ship that" chart. Use when someone is writing or changing a T-SQL query, designing or altering a table, adding an index or cleaning up existing ones, or asks for a review of T-SQL code or a pull request that touches
Read a SQL Server execution plan and explain what is actually slow, and why. Prevents the standard wrong conclusions: cost percentages read as measurements, operators ranked by cumulative time, estimated rows compared to actual without dividing by executions, and missing-index DDL pasted verbatim.
1 skill
Refuses a subagent spawn that names a pinned model id, and enforces your own per-agent-type model rules.
A band above the prompt listing each question the session is waiting on from you, with the recommended answer, trimmed as each is answered. Adds ask_add, ask_resolve and ask_list tools for the model and an /asks command.
Keeps a registry of interactive sessions so /resume-sessions can list and reopen the ones a crash, reboot or closed terminal interrupted. Windows, PowerShell, WezTerm or Windows Terminal.
A band above the prompt with each running subagent's type, model, effort, steps, context, advisor calls and estimated cost, plus a /fleet pane, /steer, /subagent-cost and a subagent_vitals tool.
Refuses force-pushes, pushes to protected branches, git commands that skip hooks and kills by process name; optionally bans folders, keeps subagents out of shared checkouts and stops whole-file reads of big files.
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
1 command
Professional UI/UX design intelligence for AI coding assistants. Includes searchable databases of styles, colors, typography, charts, and UX guidelines for React, Next.js, Astro, Vue, Nuxt.js, Nuxt UI, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, and Three.js.
7 skills
Self-learning vector database — HNSW, FlashAttention-3, Graph RAG, hybrid search, DiskANN, and Brain AGI
4 skills · 1 command · 1 agent
Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.
1 skill · 7 commands
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.