LandonSchropp
UserMy personal toolkit for working with AI agents
Categories
Indexed Skills (47)
generate
Use when the user wants to run one or more generators from `@landonschropp/generate` (initialize, prettier, only-allow, eslint, typescript, vitest, bun-test, husky).
stacked-pull-requests
Use when working with a stack of GitHub pull requests — creating branches, keeping the stack in sync, or merging in order. Covers Git Town setup, PR targeting, rebasing, and landing the stack.
project-conventions
Use when setting up a new personal project, or when deciding which root file a piece of documentation, configuration, environment variable, or agent instruction belongs in. Covers the standard root files and what each one owns. Does not cover source code layout.
bash-script
Use when writing a Bash script. Covers the template, conventions, and required patterns.
npm-publish
Use when publishing or releasing a new version of an npm/pnpm/yarn/bun package to the registry. Covers package-manager detection, semver bump selection, tagging, pushing, scoped-package access, authentication, and one-time passwords (OTP).
coach
Use when a writer wants to improve a draft through guided questioning and revision rather than a direct rewrite
bun-script
Use when writing a TypeScript script with Bun. Covers the template, conventions, and required patterns.
ruby-script
Use when writing a Ruby script. Covers the template, conventions, and required patterns.
script
Use when creating a new command-line script or standalone executable from scratch. Covers language selection and defers to a language-specific skill for conventions and templates.
react-component
Use when writing or editing a React component. Covers preferred patterns for functional components, prop types, and styling.
outline
Use when content or notes need organizing into a structured, hierarchical outline
title
Use when a piece of content needs title or headline options
unscramble
Use when fragmented, dictated, or stream-of-consciousness notes need reorganizing into coherent prose without adding new ideas
close-orc-session
Use when closing an orc session. Merges the session's completed, reviewed branch into the default branch, confirms origin is in sync, then deletes the orc worktree and tmux session.
plan
Use when explicitly instructed to create an plan (feature, bug fix, or refactor). Not for automatic use—only when directly requested.
interactive-review
Use when a skill needs the user to interactively review code changes in revdiff mid-workflow — working changes, staged changes, or a specific commit — then read their annotations back. Takes a review mode.
concise-response
Invoke when the agent's conversational replies have gotten too long or wordy and the user wants shorter answers for the rest of the conversation.
draft
Use when an outline or bullet points need expanding into a fully developed document with complete paragraphs
format
Use when a document needs the writer's structural and formatting conventions applied
streamline
Use when content is verbose, repetitive, or padded and needs tightening while preserving meaning
voice
Use when a draft needs the writer's voice and style principles applied
sync-repositories
Syncs a subset of the user's local tracked repositories.
interactive-command
Runs an interactive command in a separate window and waits for it to close. Invoked only when another skill explicitly calls for it, never on its own.
herdr
Use when a skill needs to open a project as a new herdr workspace via herdr-project, or close a herdr tab it no longer needs. Covers herdr-project create's --worktree and --prompt flags, and finding a tab by label to close it.
keep-going
Invoke after the agent has stopped, whether the user interrupted it or it paused on its own, to have it resume and stop asking for permission it doesn't need for the rest of the conversation.
close-workspace
Use when closing a herdr workspace or worktree. Merges the workspace's completed, reviewed branch into the default branch, confirms origin is in sync, then removes the worktree and closes the workspace.
write-skill
Use when creating, editing, evaluating, testing, or verifying ANY skill or skill-related file (SKILL.md, skill resources, skill scripts, or skill assets). If you're asked to evaluate or test a skill's effectiveness, use this skill.
git-atomic-commit
Use when splitting a working tree into atomic commits, or when changes need to be distributed across new commits and/or edits to prior commits on the branch. Especially relevant when changes within a single file belong in different commits.
git-edit-commit
Use when needing to fixup, squash, drop, reword, reorder, or edit commits in a branch's history. Handles the non-interactive approach agents need since `git rebase -i` requires a TTY.
git-merge-into-main
Use when a finished, reviewed branch is committed and needs to be merged into the default branch in a repo that integrates directly to `main` (not via pull request).
daily-note
Use when the user mentions a daily note, asks to add a task to today's daily todos, or reads or writes any file under ~/Notes/Daily Notes/. Covers location, section structure, and what each section is used for.
plan-morning
Use when the user says "plan my morning" or wants to fill out morning journaling (Gratitude, Better Day, Daily Affirmation) and personal/work tasks for today's daily note.
testing-bun
Use when writing or modifying tests in a Bun project
comments-and-documentation
Use when writing or editing a code comment or a documentation block, and when reviewing the comments and documentation in a diff before presenting it. Decides what stays in the source, what moves to reference documentation, and what gets deleted.
schedule
Use when creating or editing a macOS LaunchAgent for a recurring or scheduled script. Covers plist structure, PATH resolution, multiple trigger times, the reload workflow, and which behaviors launchd already handles so they don't need to be rebuilt.
git-commit
Use when creating Git commits.
interactive-edit
Use when a skill needs the user to interactively edit a file in Neovim mid-workflow, then read their changes back. Takes a window name and the file to edit.
interactive-ui
Contains interactive interaction scripts. Use when another skill explicitly instructs invoking this one. Do not invoke on your own initiative.
identify-skill-gaps
Use when analyzing Claude Code conversation logs to find patterns in repeated user instructions that could become skills. Ask for date range first.
neovim
Use when interacting with the user's local Neovim instance. Requires a running Neovim instance with a socket at `.agents/neovim.sock`.
merge-pull-request
Use when merging a single GitHub pull request. Handles pre-flight checks, waits for CI, and executes the merge with the repo's default method or merge queue.
note
Use when working with files in ~/Notes (Landon's Obsidian vault). Covers vault structure (PARA), file naming, frontmatter, icons, templates, kanban boards, and the obsidian CLI.
testing-ink
Use when writing or modifying tests for Ink (terminal UI) components.
testing-react
Use when writing or modifying tests for React hooks.
testing-typescript
Use when writing tests for TypeScript or JavaScript code in frameworks such as Jest, Vitest, Bun, etc.
pre-review
Use when a commit's changes are finished and about to be presented for review. Runs the checks that catch the objections the user would otherwise raise, before they spend time reviewing.
project
Use when reading or writing files under ~/Notes/Projects/, starting a new project, or archiving a finished one. Covers folder layout, the board file, supporting notes, and the project lifecycle across Future/, Projects/, and Archive/.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.