Agent Stuff

Personal agent skills and subagents I use with Claude and Cursor. Some are highly specific to my own setup (like my Obsidian vault).

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

Using these

Copy whatever looks useful into your own skills directory.

There are a couple of ways to do that, depending on your setup:

• Using an app like Claude? Every general-purpose skill is also packaged as a ready-made .zip in zips/ that you can download and drag straight into Claude.ai > Customize > Skills. Updates are manual: re-download the zip and drop in the new version.
• Working in a coding agent or CLI (Claude Code, Codex, Cursor, Hermes…)? Install with the skills CLI — it also makes updating a one-liner:

bunx skills add nweii/agent-stuff

# or
npx skills add nweii/agent-stuff

Install a specific skill:

bunx skills add nweii/agent-stuff --skill [skill-name]

Updating skills:

bunx skills update

To update a specific skill, run skills add again with the same skill.

Internal skills

Skills under the Internal heading in the catalog below have metadata.internal: true set — they're personal workflows tied to my own setup (vault paths, tools, naming conventions). They're excluded from the zips/ mirror.

Install it as-is — when the skill's assumptions already match your setup

Some of them don't hardcode anything of mine — they assume a convention (a related property, a daily/weekly note hierarchy) or a tool (Granola MCP, gh) and otherwise work anywhere. If nothing in the SKILL.md names a folder or template you don't have, just install it:

bunx skills add nweii/agent-stuff --skill [skill-name]

Two CLI behaviors to know about:

• bunx skills add nweii/agent-stuff (no --skill flag) skips internal skills — naming one is what opts it in.
• bunx skills update silently skips internal skills (you'll see "Failed to update" with no detail). To refresh one after a repo change, re-run add with --skill — it overwrites in place.

For a one-off run, or just to read one first, bunx skills use nweii/agent-stuff -s [skill-name] prints it as a ready-to-paste prompt without installing anything.

Tailor a copy — when it carries folder conventions you don't share

For the ones carrying my folder structure and template names throughout, have your agent read mine and write you your own version instead of installing and then editing:

Read skills/[skill-name]/SKILL.md from the github.com/nweii/agent-stuff repo —
use a local checkout if there's one on this machine, otherwise fetch it. It's
one of that repo's internal skills, written for someone else's setup, so some
of the folder paths, tools, and naming conventions in it won't match mine.
List what you'd need to substitute, ask me about anything you can't infer from
my environment, then write the tailored version into my skills directory under
a name of my choosing, with a `metadata.credit` line in its frontmatter noting
what it was adapted from. Leave everything that isn't setup-specific alone.
Don't install the original.

Giving your copy its own name keeps a later add or update from overwriting it.

---

Catalog

Auto-generated by scripts/update-catalog.py

Skills

• archive-conversation — Create analytical archival summaries of AI conversations, capturing intellectual journeys, key insights, and technical logs. Use when archiving, saving, or documenting a chat session.
• audit-transcription — Flag and propose corrections for likely mistranscriptions in auto-transcribed meeting notes or audio transcripts. Use when the user says 'audit this transcript', 'fix the transcription', 'find mistranscriptions', or shares a noisy Granola/Whisper output and asks for cleanup.
• bb-agent-coordination — Use alongside bb-cli when coordinating work across bb threads: delegation, ownership, environment boundaries, steering, reports, review, reconciliation, or handoff. bb-cli owns commands; this skill owns collaboration.
• build-lab — Set up a durable /lab section in a website: a sidebar shell over design experiments, a tested registry, and the host agents-file conventions that make future lab authoring work.
• commit — Create well-formatted commits with conventional commit messages. Use when user asks to commit, wants to commit changes, or needs help with commit messages.
• drafting-writing — Writing-partner processes that draw out the user's own writing through questioning: guided drafting sessions, fragment mining, shaping raw material into a piece, and phrase tightening. Use for help discovering, developing, and structuring writing (notes, essays, messages, etc).
• enrich-from-transcript — Enrich an existing meeting/interview note from its transcript, or scaffold one when only a transcript exists. Captures granular narrative, exact phrases, mechanics, casual context, and implicit signals. Run on thin auto-summary notes or transcripts that warrant close reading.
• extract-flow-scenario — Use when extracting an actual workflow, user journey, or operational scenario from a conversation into a sequence of actors, state changes, and pain points.
• file-naming — 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 filenames.
• herdr-agent-coordination — Use alongside the managed herdr skill whenever recognized agents communicate through Herdr: peer tasks, reports, questions, corrections, return paths, origin checks, or stalled delivery. This skill owns the peer protocol; herdr owns runtime control.
• obsidian-clis — Use when operating Obsidian from the terminal: notes, search, properties, links, tasks, Bases, or plugin development. Uses the app CLI, with notesmd-cli as a headless fallback.
• obsidian-publish-customize — Use when theming or scripting an Obsidian Publish site through publish.css or publish.js, including client-side workarounds. Excludes ordinary Publish usage, desktop themes, and plugins.
• obsidian-templater — Help with templates/snippets for the Obsidian Templater plugin. Use to help generate Obsidian templates from natural language, understand and debug existing tp.* snippets, and adapt vault notes and workflows to Templater when users mention Templater, tp.*, templater syntax.
• obsidian-web-clipper — Use when creating, importing, or debugging Obsidian Web Clipper templates: JSON, variables, filters, selectors, interpreter prompts, and URL or schema triggers. Does not handle general scraping.
• quantify-impact — Surface measurable metrics and outcomes from a description of work via structured conversation. Use when the user says 'help me quantify this', 'what numbers can I attach to X', or is drafting a resume bullet, case study, or impact statement that needs concrete scale.
• raycast-extensions — Build Raycast extensions — commands, List/Form/Grid views, hooks like useFetch, AI integration, manifest. Use when the user says 'raycast extension', 'add a raycast command', or is working in a project with @raycast/api and a Raycast manifest.
• react-useeffect — React useEffect best practices. Use when writing Effects, derived values, or data fetching. Teaches when NOT to use Effects and better alternatives like useMemo or key props.
• semantic-compression — Compress wordy language or loosely expressed thinking into a smaller, sharper form without flattening its meaning. Use when revising an explanation, phrase, sentence, paragraph, concept, label, or coined term whose nuance, implication, or texture must survive the edit.
• set-note-description — Use when writing a note's description property for recall or retrieval. Summarizes a note's own content; parent-period synthesis belongs to periodic-rollup or the environment's specific rollup workflow.
• software-test-quality — Review software test suites and choose test levels. Use when auditing unit, integration, component, or end-to-end tests; assessing assertions, fixtures, mocks, coverage, or flakiness; or deciding which test level best protects a behavior or risk.
• spec-shaping — Shape product ideas into actionable specs and sprint plans. Use when interviewing about a product plan, breaking specs into sprints, or turning vague ideas into well-scoped work.
• suggest-lucide-icons — Pick Lucide icons for a concept, UI placement, or vault note. Searches the full Lucide catalog for real, verified icon names. Use when the user says 'what icon for X', 'suggest a Lucide icon', 'pick an icon', or needs an icon for note frontmatter, a button, or a section header.
• teach-me — Use when the user asks to learn a concept or understand completed work through stepwise tutoring, checks for understanding, or a saved walkthrough or learning record.
• things-app — Read, capture, schedule, and update tasks and projects in Things 3. Prefer the things CLI whenever there's command-line access to Things; otherwise use a connected Things MCP for headless or remote environments (full read + write, any device), the things:/// URL scheme (any device with Things, write-only), or email-to-Things for unattended capture. Use to add todos, build a project, show Today/Inbox, find tagged tasks, or schedule from desktop, phone, or a serverless routine.
• tirith-config — Operate a tirith setup — the terminal command analyzer guarding against homograph URLs, ANSI injection, and pipe-to-shell exploits. Use when editing ~/.config/tirith/policy.yaml, debugging a blocked command, choosing between allowlist / tirith run / TIRITH=0 bypass, or verifying with tirith doctor.
• transcribe-audio — Transcribe audio or video to text with a locally-run speech-to-text model. Use when the user wants a transcript or captions from a recording, wants to run speech-to-text locally instead of a cloud service, or wants to set up or switch their local transcription model.
• update-changelog — Add or revise a project's Keep-a-Changelog-format changelog, including version bumps and change-type groupings. Use when the user says 'update the changelog', 'log this change', or 'bump the changelog' for a project or plugin.
• use-tailwind-v4 — Tailwind CSS v4 syntax and v3→v4 migration reference. Use when the user mentions 'Tailwind v4', 'upgrade Tailwind', @theme, @utility, or @import 'tailwindcss', or is working in a project whose config indicates v4.
• validating-startup-ideas — Find and validate startup ideas by mining user complaints, crafting premises, and navigating the idea maze. Use when discovering product opportunities, validating ideas, shaping solutions, researching user pain points, or exploring what to build.
• visual-keywords — Generate keyword strings for images, screenshots, or visual references — optimized for fuzzy search, not alt text or prose. Use when the user says 'keywords for this image', 'tag this for search', 'visual keywords', or wants searchable labels on an Eagle asset.

Internal

Personal workflows tied to my own setup (vault paths, tools, naming conventions). Installable, but expect to adapt SKILL.md to your own folders and conventions before they're useful.

• archive-to-brain — Save an archival summary of an AI conversation to Nathan's Obsidian vault, using the Thinking note template and vault folder conventions to capture intellectual journeys, key insights, and technical logs. Use when archiving a chat session to the vault.
• clip-skills — Save bunx skills terminal output (a manifest from skills add/use <repo> -l) as a Repos note in the Brain vault under 03-Records/Snippets/Repos/. Use when the user pastes a skills listing and wants it captured. Triggers: '/clip-skills', 'save these skills', 'make a note for this skill repo'.
• code-to-pantry — Use when looking up reusable components in Nathan's pantry, bringing one into a project, or saving a code technique to the pantry for reuse.
• create-topic-note — Create a topic note grouping related notes under a common theme, with automatic backlinking to source notes. Triggers: 'group these under a topic', 'create topic note for [[A]], [[B]], [[C]]'.
• nweii-skills — Use when creating, editing, migrating, installing, or publishing skills in Nathan's environment. Routes source ownership, public/private placement, authoring conventions, install mechanics, and release boundaries.
• obsidian-granola — Sync meetings from Granola to Obsidian — pulls notes and transcripts and imports them as formatted meeting/transcript notes. Use when the user says "sync my last granola meeting", "note for my last meeting", or asks to pull in a Granola transcript.
• obsidian-log-commits — Fetches today's GitHub commits across personal and org repos, filters noise, and appends a summary as bullets into the ## Log section of today's daily note. Use when asked to log what was worked on today, check today's commits, or update the daily note with dev activity.
• people-notes — Use for person-centered work in Nathan's Brain vault: prepare context from a profile and linked records, create a canonical person note, or reconcile an existing one.
• periodic-rollup — Use when synthesizing child periodic-note descriptions into a parent week, quarter, or year, or compiling project/topic history. Prefer a vault-specific rollup workflow when the environment provides one.
• save-napkin-note — Turn raw capture material into a properly structured Brain vault note (template, frontmatter, folder, links), or integrate a fragment into an existing note after confirmation. Use when filing a quick capture — triggers: 'save this as a note', 'file this', 'napkin note', 'process this dump'.
• save-term — Use when saving an encountered term or a concept coined in conversation as a Brain Term note, with its source quote or a brief gloss.
• vault-recipes — Search, read, filter, combine, adapt, and save recipes in the Brain vault collection. Use whenever cooking and the collection are relevant — 'what should I make', 'recipes with miso', 'save this one' all imply it.

Agents

Claude Code subagents — copy the *.md into your own agents directory (not installed by bunx skills). See agents/.

• vault-reader — Read-only Obsidian vault exploration. Use proactively when searching notes, understanding vault structure, finding connections, or gathering context from a vault.
• vault-writer — Create and edit notes in an Obsidian vault. Use when the user wants to write, update, or organize notes. Follows vault conventions for metadata, linking, and structure.