By miXshift
MixShift AI skills for Amazon advertising and retail operations. The MixShift warehouse is a MySQL database (legacy schema: dashamazon) covering Sponsored Ads (SP/SB/SD), DSP, Seller Central + Vendor Central ops revenue, orders, inventory, and dimensional catalog. This plugin ships: data-explore (ad-hoc querying + CSV export), PPC optimization skills (daily health checks, bid management, search term negation, harvest, monthly reporting), and onboarding commands (welcome, brand discover/add). Warehouse access is read-only via the bundled harness; credentials read from ~/.mixshift/auth/credentials.json.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Build a Tier 3 brand context directory for a new Amazon PPC account from scratch. Collect account metadata, run structured database queries, synthesize into a typed context.yaml + narrative.md + corpora/, and produce a human-reviewable Brand Context summary. Run before any other skill execution on a new account.
Phase 2 negation review for ASIN targets matched through auto campaigns, category targeting, and other Product Attribute Targeting paths. Pulls ASIN-triggered rows for a configurable window, suppresses ASINs already under manual targeting, evaluates PDP/form-factor overlap, joins lifetime performance by location (campaign + ad group), and separates clean negate candidates from review/watch buckets. Triggers on: 'run asin negation review', 'asin target negations', 'pdp overlap review', 'phase 2 negations', 'asin exact negations'.
Walk the user through one-time MixShift warehouse auth setup. Collects email + MySQL credentials interactively in chat (not via TTY prompts — Claude Code's Bash tool can't drive those), writes them to a temp file, runs the harness's non-interactive `mixshift auth setup --from-file`, and cleans up. Required before any data-touching skill.
Structured competitive analysis framework for market positioning. Produces SWOT analysis, feature comparison matrices, pricing tiers, and market positioning maps. Research-driven assessment of direct competitors and adjacent market players. Triggers on: 'competitor analysis', 'competitive landscape', 'market comparison', 'SWOT', 'who competes with us', 'competitive threat analysis'.
This skill should be used when the user asks to "run daily health check", "check account status", "how is the account", or needs comprehensive daily exception-based analysis of advertising account performance across campaign types, objectives, and item groups. Uses percentile-based confidence intervals to detect spend and ACOS anomalies requiring management attention.
A Claude plugin for MixShift customers — Amazon advertising + retail data exploration and analytical workflows, built by MixShift.
Status: Pre-beta. The data-explore skill (query / sample / export your MixShift warehouse) is the initial launch surface. Analytical skills (daily health checks, bid management, search-term workflows, etc.) are present in the codebase but staged behind vetting and not yet enabled for general customer use.
mixshift-ai is a Claude plugin that lets you talk to your MixShift warehouse from inside Claude — sample tables, export CSVs, run ad-hoc SQL, and (soon) get full analytical reports. The plugin is read-only and routes every query through a bundled CLI that authenticates with your MixShift credentials.
Pick the row that matches your situation:
| Your situation | Use | Doc |
|---|---|---|
| You're a MixShift customer, want to install on your own Cowork seat | Cowork — Personal install | docs/install/cowork-personal.md |
| You're a Cowork org admin, want to deploy to your whole team | Cowork — Organization install | docs/install/cowork-organization.md |
| You use Claude Code (terminal-based) | Claude Code | docs/install/claude-code.md |
| You want the harness CLI directly (without a plugin host) | CLI direct | docs/install/cli-direct.md |
All four paths land at the same place: a working mixshift CLI on your machine, plus the plugin's skills available to Claude. After install, every path goes through the same auth setup.
The most common path:
miXshift/mx-claude-plugin.mixshift-ai.Full step-by-step in the install docs.
mixshift welcome prints it too)Everything else — brand context, run history, output destinations — lives at ~/.mixshift/ on your local machine. The plugin manages it.
A deterministic harness (mixshift CLI, bundled in this repo) handles authentication, pre-fetch, validation, and audit. Claude (the model) only analyzes pre-fetched data and writes recommendations — it never reads SQL files directly, never executes queries, and never pushes to Amazon's APIs. Skills are read-only by default; execution capabilities are opt-in additions that will be staged in later releases. The harness writes all state to ~/.mixshift/ on your machine; the plugin install itself ships no customer data.
~/.mixshift/auth/credentials on your local machine. They never leave your device.docs/privacy.md. The welcome screen shows a short notice on first run.Source-available under PolyForm Perimeter License 1.0.0. See LICENSE.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub mixshift/mx-claude-plugin --plugin mixshift-aiComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).