claude

aichemist

Custom agents and skills for AI-assisted development

1 on GitHubby Anders Bo Rasmussenv3.11.0MITupdated 5 days ago
/

Plugin aichemist from marketplace aichemist in Anras573/AIchemist. Commands read from the repo's manifest — 4 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (22)

  • beads

    This skill should be used when the user asks to "track tasks with beads", "use bd", "add a beads task", "show ready tasks", "claim a task", "list bd tasks", "create a bd issue", "show my tasks", "what's ready to work on", "update task status", or mentions beads task IDs like "bd-a1b2". Provides bead

  • brainstorming

    Use this BEFORE any creative work — creating features, building components, adding functionality, or modifying existing behavior. Explores user intent, requirements, and design through structured dialogue before any implementation begins. Trigger phrases: "I want to build", "let's add", "how should

  • calendar

    This skill should be used when the user asks about "my calendar", "what's on my schedule", "what meetings do I have", "what's today's agenda", "what's coming up this week", "next meeting", "prepare me for my next meeting", "meeting prep", "brief me on", "briefing for", or asks about specific calenda

  • capture

    This skill should be used when the user asks to "capture this", "save this to obsidian", "add to obsidian", "quick capture", "capture to vault", "capture this thought", "capture this insight", "capture this code", "save this insight", "jot this down", or wants to save a thought, snippet, or note to

  • code-review

    This skill should be used when the user asks to "review my code", "do a code review", "review this PR", "review this pull request", "check my changes", "review changes against main", "review against develop", "post review comments", "review and comment on PR", "code review with Jira context", "revie

  • daily-note

    This skill should be used when the user asks to "show my daily note", "open daily note", "check daily note", "create daily note", "create today's note", "view today's note", "add to daily note", "append to daily note", "what's in my daily note", or wants to interact with today's (or a specific date'

  • danish-writing

    Use this whenever text must be written, translated, or polished in Danish, including emails, messages, documentation, posts, and replies. It makes the agent compose directly in Danish and then check the result against a list of common English-to-Danish translation tells. Exact trigger phrases: "writ

  • dotnet-dev

    Personal C#/.NET conventions to apply when writing, generating, reviewing, or scaffolding .NET code — derived from the user's DnDSessionPlanner project (ASP.NET Core minimal APIs, vertical-slice architecture, EF Core with the specification pattern, xunit + Moq). Trigger on "write this in C#", "write

  • hotspot

    Trigger this skill when the user asks about code complexity, refactoring candidates, or risk areas. Exact trigger phrases: "/hotspot", "should I refactor this", "is this a hotspot", "hotspot analysis", "complexity risk", "churn analysis", "is this worth refactoring", "what's the riskiest file", "cyc

  • jira

    This skill should be used when the user asks to "search Jira tickets", "get ticket details", "check ticket status", "find my tickets", "what am I working on", "create a Jira issue", "update a ticket", "add a comment to ticket", "transition ticket status", "move ticket to done", or mentions Jira issu

  • markitdown

    This skill should be used when the user asks to "convert this URL to markdown", "fetch page as markdown", "get this page as markdown", "convert this webpage", "summarize this URL", "turn this page into markdown", "fetch and convert", "convert this file to markdown", "convert this PDF to markdown", "

  • mempalace

    Use this skill to interact with the MemPalace memory system. Activates when the user says "remember this", "store in memory", "what do you know about X", "search memory", "forget this", or "clear memory". Also auto-triggers to store and retrieve context during tasks — see Auto-Trigger Behavior below

  • mermaid

    This skill should be used when the user asks to "create a diagram", "draw a flowchart", "sequence diagram", "architecture diagram", "visualise this", "add a mermaid diagram", "diagram this flow", "draw a class diagram", "ER diagram", "state machine diagram", "C4 diagram", or any request to visually

  • obsidian

    Use for general Obsidian vault management: tasks ("list my tasks", "mark task done", "show incomplete tasks"), tags ("list tags", "find notes tagged #auth"), properties/frontmatter ("set status to done", "read the status property"), file operations ("move this note", "rename this file", "delete this

  • owasp-top-10

    Trigger this skill when the user asks about the OWASP Top 10, wants a security review scoped to it, or asks whether code is compliant with it. Exact trigger phrases: "OWASP top 10", "owasp top ten", "check against owasp top 10", "review for owasp vulnerabilities", "what's the current owasp top 10",

  • playwright

    Use this skill for browser automation, web testing, and UI interaction tasks. Prefer this over Playwright MCP — it uses the token-efficient playwright-cli instead of loading large MCP tool schemas and accessibility trees into context. Trigger phrases: "test this page", "automate the browser", "take

  • postgresql

    This skill should be used when the user asks to "query postgres", "run SQL", "check database", "show tables", "describe table", "query database", "execute SQL query", "list tables", "show indexes", "database schema", or mentions PostgreSQL/Postgres operations. Provides PostgreSQL database querying w

  • pr-review-loop-copilot

    Copilot-compatible PR review loop for processing GitHub Copilot review comments in manual ticks. Fetches unresolved Copilot threads, clusters and fixes issues with confidence-based gating, replies and resolves threads, then extracts lessons into CLAUDE.md and REVIEW_LESSONS.md. Invoke with /pr-revie

  • pr-review-loop

    Autonomously drives the GitHub Copilot PR review loop. Polls for unresolved review threads, classifies and fixes them with confidence-based gating, replies and resolves threads on GitHub, then extracts lessons into CLAUDE.md and personal memory. Invoke with /pr-review-loop from a repo root on a feat

  • research

    This skill should be used when the user asks to "research in vault", "search my notes", "search obsidian", "find in obsidian", "look up notes", "find notes about", "what do I have on", "search my vault for", or wants to search their Obsidian vault for relevant context, past knowledge, or notes on a

  • ticket-flow

    This skill should be used when the user wants to work on a Jira ticket end-to-end. Trigger phrases: "work on ticket", "start ticket", "implement ticket", "pick up PROJ-123", "let's do PROJ-123", "work on [issue key]", or any mention of a Jira issue key alongside intent to implement. Guides you throu

  • tool-preferences

    Guidance for selecting between equivalent tools when multiple options exist. Inject this skill into agents that may interact with GitHub, git, or other systems where both CLI tools and MCP servers are available. This skill ensures consistent, efficient tool selection across all agents.

Subagents (7)

  • code-explorer-agent

    Codebase exploration specialist for mapping patterns and architecture before implementation. Use this agent when you need to understand an area of the codebase before making changes — finding similar features, tracing data flow, or identifying extension points. <example> Context: Starting a new tick

  • code-review-agent

    Expert code reviewer providing thorough, constructive feedback on code quality, security, and best practices. Use this agent PROACTIVELY when the user asks for feedback on code, wants a second opinion, or when reviewing changes before committing. <example> Context: User has written code and wants fe

  • ddd-agent

    Domain-Driven Design expert for strategic modeling guidance, tactical pattern review, and design discussions. Use this agent PROACTIVELY when you encounter domain modeling questions, aggregate design, or code that deals with entities, value objects, and bounded contexts. <example> Context: User is d

  • dotnet-agent

    Expert .NET software engineer for building, debugging, and optimizing .NET applications. Use this agent PROACTIVELY when working with C#, F#, .NET projects, or when the user needs help with async patterns, SOLID principles, testing, or .NET-specific APIs. <example> Context: User is working on a C# f

  • hotspot-agent

    Hotspot analysis agent that identifies high-risk files by combining cyclomatic complexity with git churn. Use this agent when you need to assess the complexity risk of a set of files — typically as part of a code review to provide risk context on changed files. <example> Context: Code review skill h

  • simplify-agent

    Expert code simplifier that refines recently modified code for clarity, consistency, and maintainability while preserving exact functionality. Use this agent PROACTIVELY when the user asks to simplify, tighten, or clean up code, or when a code-writing task produces a diff worth reviewing for clarity

  • typescript-react-agent

    Expert full-stack TypeScript developer specializing in React, Next.js, Node.js, and modern frontend/backend patterns. Use this agent PROACTIVELY when working with TypeScript, JavaScript, React components, Next.js apps, or Node.js backends. <example> Context: User is working on a React component or f

MCP servers (2)

  • mempalace

    runs: uvx --from mempalace python -m mempalace.mcp_server

  • markitdown

    runs: docker run --rm -i mcp/markitdown@sha256:1cef3bf502503310ed0884441874ccf6cdaac20136dc1179797fa048269dc4cb

Hooks (5)

  • Stop

    "${CLAUDE_PLUGIN_ROOT}/tools/notify.sh" 'Claude Code' 'Awaiting your input'

  • Stop

    command -v mempalace >/dev/null 2>&1 || exit 0; tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/mp-stop-XXXXXX") || exit 0; trap 'rm -rf "$tmpdir" 2>/dev/null' EXIT HUP INT TERM; cat > "$tmpdir/session.jsonl" &&

  • PreCompact

    command -v mempalace >/dev/null 2>&1 || exit 0; tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/mp-compact-XXXXXX") || exit 0; trap 'rm -rf "$tmpdir" 2>/dev/null' EXIT HUP INT TERM; cat > "$tmpdir/session.jsonl"

  • PreCompact

    "${CLAUDE_PLUGIN_ROOT}/tools/skill-suggester.sh" 2>/dev/null; exit 0

  • SessionEnd

    "${CLAUDE_PLUGIN_ROOT}/tools/skill-suggester.sh" 2>/dev/null; exit 0

View source on GitHub

More from Anras573/AIchemist

All 5 plugins →

Claude Code mod: shows your in-progress and ready beads tasks in a band above the prompt, read through the beads skill's tools/beads-db.sh

1

Claude Code mod: shows your next meeting (Microsoft 365 or iCloud/CalDAV) in the status line, via the calendar skill's tools/calendar.sh

1

Claude Code mod: a read-only pane showing what the pr-review-loop skill works on (Copilot review state, CI, unresolved threads)

1

Claude Code mod: shows the open items (## Next) from the Remember plugin's /remember handoff note in a band above the prompt

1

Similar plugins

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

nextlevelbuilder/ui-ux-pro-max-skill 148,759

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Statically analyze a local JS/Electron app you're authorized to study, with file+line evidence, and build an original reimplementation of what you find. Experimental. Phase 1: JS/Electron static analysis. Phase 2: native ELF/PE/Mach-O container inspection. Phase 3: .NET assembly metadata. Phase 4: EVM bytecode inventory. Phase 5: CUDA fatbin, cubin and PTX inventory. Parses, never executes. Dynamic analysis is a future phase, not yet implemented.

1 skill · 1 command · 1 agent

ruvnet/ruflo 81,589

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

headroomlabs-ai/headroom 79,508

expo

claude

Official Expo skills for building, deploying, upgrading, and debugging React Native apps with Expo. Covers UI development with Expo Router, SwiftUI and Jetpack Compose components, Tailwind CSS setup, API routes, data fetching, CI/CD workflows, App Store and Play Store deployment, SDK upgrades, DOM components, and dev client distribution.

23 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

Maintain aichemist?

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.

claude & codex plugins5 plugins