Agent Stuff

Personal prompts, skills, and commands I use with Claude and Cursor. Some are highly specific to my own setup (like my Obsidian vault). Sharing publicly in case any of it's useful or interesting to others.

What's here

• Skills — Instructions that Claude/Cursor automatically apply based on context
• Commands — User-invoked slash commands for specific workflows
• Reference — Documentation on Agent Skills, Cursor rules, and how components work together
• Templates — Starting points for creating new skills, commands, and rules

Agent skills format

This repo uses the Claude Agent Skills format. Skills are folders containing a SKILL.md with YAML frontmatter and instructions. The description field tells AI agents when to load and apply the skill.

skill-name/
├── SKILL.md              # Metadata + instructions
├── reference.md          # Optional: detailed docs
└── supporting-file.md    # Optional: additional context

Commands are standalone markdown files with prompts that get invoked via /command-name.

Using these

Copy whatever looks useful into your own .claude/skills/ or .cursor/rules/ directory. Adapt as needed.

Note: Some skills reference personal vault notes not included in this repo.

License

MIT — do whatever you want with it.

---

Catalog

Auto-generated by scripts/update-catalog.py

Skills

dev

• using-heavy-mcps — Use mcporter + jq to reduce token bloat when working with token-heavy MCPs like Sanity and Brain vault. Call MCPs outside chat, filter outputs, and feed compact results back to the model.
• web-interface-guidelines — Best practices for building accessible, fast, and delightful web interfaces. Use when doing frontend/UI development, building web apps, reviewing UI code, or implementing interactive components. Covers interactions, animation, layout, accessibility, performance, and visual design.

personal

• aid-finances — Expert financial advice and guidance. Use when providing financial advice, analyzing investments, planning budgets, discussing market strategies, retirement planning, or any personal finance questions.
• culinary-assistant — Help with cooking, recipes, and kitchen tasks. Use when discussions involve cooking, recipes, ingredients, meal planning, food substitutions, kitchen techniques, or culinary questions. Also handles recipe parsing, improvement from reader comments, format conversion (Mela, Schema.org), and .melarecipe file generation.
• use-brain-vault — Navigate and develop this Obsidian vault—metadata system (categories, types, tags, related), Bases for dynamic dashboards, and periodic notes structure. Use when organizing vault content, configuring Bases, or working with journal notes.

Commands

brain-vault

• archive-conversation — Create archival summaries of AI conversations that capture intellectual journeys, key insights, work session logs, and technical execution. Use when user asks to archive, save, or document a conversation, or when a substantive discussion or work session reaches a natural conclusion worth preserving.
• create-topic-note — Create a Commentary topic note from related notes with automatic backlinking
• find-related — Navigate the vault to find concept notes and records semantically and conceptually related or adjacent to the provided text. Use the tools and skills at your disposal to do so. Present relevant notes with brief explanations of why they're related.
• rollup-periodic-summary — Generate rollup summaries for periodic notes (weekly/quarterly/yearly) by synthesizing child note descriptions
• summarize-to-frontmatter — When asked to generate summaries of markdown content for its YAML frontmatter, follow these instructions.

general

• cleanup-dictation — Process dictated or stream-of-consciousness input into clean formatted output. Used for Superwhisper presets and similar dictation workflows.
• commit — Create well-formatted commits with conventional commit messages and emojis. Follow the Conventional Commits specification. This command helps automate formatting, checks, and clarity.
• create-command — Guide for creating new custom Claude commands with proper structure.
• find-fallacies — Analyze text for logical fallacies. Use when reviewing arguments, debates, articles, or reasoning that may contain flawed logic.
• lookup — Explain the meaning of selected text using surrounding context. Identifies unclear words, phrases, idioms, or colloquialisms and provides concise definitions with cultural context and usage notes. Use with reasoning models for best results.
• rename-files — Analyze file content and propose intelligent renames using context-aware naming conventions. Date-prefixed for transactional/periodic documents, content-first for creative works. Use for organizing files, cleaning up downloads, or standardizing filename conventions.
• spec-interview — Interview me about the plan
• visual-keywords — Generate keyword-rich strings for visual references to optimize for fuzzy search and recall. Focuses on searchability and keyword matching rather than prose or alt text.