johnlindquist

@johnlindquist source repo

55 skills
0 followers
10 hours ago last updated

▌
Toolsmith · johnlindquist
Analyze the local Toolsmith corpus of Codex tool calls, identify tool optimization opportunities and blindspots, propose new tools or skills, and suggest focused AGENTS.md/software-engineering improvements based on observed agent behavior.

0
installs
▌
Fusion · johnlindquist
Use when the user asks Codex to consult, run, or reason with the local fusion, fusion-med, or fusion-high CLI for multi-provider feedback, architecture review, planning, critique, or synthesis. Use the local CLI directly, verify providers first, and run the full configured panel to terminal provider states by default, with quota/rate-limit failures treated as non-blocking for that run.

0
installs
▌
Gemini Design · johnlindquist bundle
Generate layout and design mockups using Gemini CLI with project design context from .impeccable.md. Creates variations as new routes/pages/components with easy preview and comparison. Use when asked to mock up designs, generate layout variations, or get Gemini design ideas.

0
installs
▌
Mdflow · johnlindquist
Build and maintain a project's ./flows directory, the agent roster. Each flow is one markdown file that runs as an AI agent (frontmatter + prompt body) on claude, codex, pi, cursor-agent, copilot, agy, or any CLI engine, with colocated behavioral evals. Use when the user asks to "create a flow", "add an agent to this repo", "set up ./flows", "make a markdown agent", or wants repeatable AI tasks with evals.

0
installs
▌
Align · johnlindquist bundle
Turn a task prompt into a prompt-align brief page — reading, scope, done-means, and autonomy as editable sentences with ghost alternatives and AI steering — wait for the human's saved brief, then implement to completion from the persisted result. Trigger: /align <task>.

0
installs
▌
Publish Skill · johnlindquist
Publish a skill to GitHub for discovery via `npx skills`. Use when asked to "publish skill", "share skill", "make skill discoverable", or "upload skill to GitHub".

0
installs
▌
Agent Recall · johnlindquist bundle
Search past agent conversations across Claude Code, Codex, Grok, Kimi, and pi, and read shared curated memory. Use when the user references past work ("we discussed/decided/fixed this before", "last time", a familiar error) or when starting a substantive task in this project.

0
installs
▌
Agent Recall Save · johnlindquist bundle
Stage explicit memory text or accept the most recently suggested Agent Recall memory candidate or candidates for human approval. Use when the user asks to save or remember text with Agent Recall, says to accept/save the memory candidate(s), or invokes agent-recall-save with or without an explicit payload.

0
installs
▌
Oracle · johnlindquist
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

0
installs
▌
Oracle Packx · johnlindquist bundle
Bundle optimized code context with packx then send it to Oracle's MCP consult tool for GPT-5.4 Pro analysis. Use when the user wants to ask oracle about code with smart filtering, or run "packx oracle", "oracle with packx", or "bundle and ask oracle".

0
installs
▌
Oracle Thread Packx · johnlindquist
Use packx plus Oracle's MCP consult tool to run iterative GPT-5.4 Pro code reviews in the same ChatGPT browser conversation. Use when the user wants "ask oracle again", "iterate with oracle", "continue the oracle thread", or repeated packx-backed reviews that should preserve prior ChatGPT thread context.

0
installs
▌
New Agent · johnlindquist
Create mdflow-backed agent files for Script Kit. Compatibility path — prefer creating skills (SKILL.md under a plugin's skills/ directory) for new reusable AI work.

0
installs
▌
New Script · johnlindquist
Create or update TypeScript scripts for Script Kit. Use when the user wants to write a new script, edit an existing script, or understand Script Kit's SDK and metadata system.

0
installs
▌
Start Chat · johnlindquist
Start and manage Agent Chat conversations from scripts, including typed context parts, streaming status, and chat lifecycle operations.

0
installs
▌
Add Actions · johnlindquist
Add Actions Menu commands to scripts and scriptlet bundles with setActions() and companion .actions.md files.

0
installs
▌
Manage Notes · johnlindquist
Manage the Notes window — creating, searching, editing, and automating notes via the SDK and automation protocol.

0
installs
▌
Troubleshoot · johnlindquist
Diagnose and fix common Script Kit issues. Use when the user reports bugs, crashes, missing features, or unexpected behavior in Script Kit GPUI.

0
installs
▌
Configure MCP · johnlindquist
Configure external MCP servers for scripts and Agent Chat. Use when the user wants to add, remove, enable, disable, or inspect MCP servers in Script Kit.

0
installs
▌
New Scriptlet · johnlindquist
Create or update scriptlet bundles for text expansions, snippets, shell commands, and lightweight helpers in a single markdown file.

0
installs
▌
Update Config · johnlindquist bundle
Update Script Kit configuration files — hotkeys, theme, layout, dictation, Claude Code, and workspace settings.

0
installs
▌
Script Kit Devtools · johnlindquist bundle
Agent-facing DevTools for Script Kit GPUI: use protocol, MCP, and CLI primitives to inspect, control, measure, debug, benchmark, and prove real app UI behavior from bug reports without defaulting to prewritten agentic-testing recipes.

0
installs
▌
Agy Script Kit Devtools · johnlindquist
Use the local agy CLI as a fast Script Kit GPUI app inspector by prompting it to drive existing script-kit-devtools primitives, capture logs, and produce a compact investigation result from a user bug report or inspection prompt.

0
installs
▌
Uxspec · johnlindquist bundle
Walk through building a UXSpec (.uxspec.json) file — gathering requirements, making design decisions about layout/typography/color/motion/accessibility, designing the state machine, defining visuals, then compiling and verifying the output.

0
installs
▌
Wire · johnlindquist
Connect the spec to behavior — wire up $context, $events, actions, effects, guards, and element bindings

0
installs
▌
Gather · johnlindquist
Collect design context, audience, intent, and requirements before writing any UXSpec JSON

0
installs
▌
Harden · johnlindquist
Strengthen a UXSpec against real-world conditions — overflow, missing data, network failures, and accessibility

0
installs
▌
Review · johnlindquist
Run a systematic quality audit on a completed UXSpec — design intent, consistency, accessibility, and state coverage

0
installs
▌
States · johnlindquist
Design the $machine section — map happy paths, error paths, and all state types into a complete behavioral skeleton

0
installs
▌
Tokens · johnlindquist
Define $tokens for color, typography, spacing, and timing that give a spec its visual identity

0
installs
▌
Animate · johnlindquist
Add purposeful motion to a UXSpec — $animations, onEnter choreography, and timing tokens

0
installs
▌
Clarify · johnlindquist
Improve every piece of text in a UXSpec — descriptions, labels, error messages, empty states, and loading copy

0
installs
▌
Extract · johnlindquist
Identify repeated patterns and consolidate them into $elements and shared tokens for systematic reuse

0
installs
▌
Visuals · johnlindquist
Write $visual blocks that define layout, elements, descriptions, and test hooks for each state

0
installs
▌
Badger Deploy · johnlindquist
Deployment workflows, file management, and project organization for Universe 2025 (Tufty) Badge. Use when deploying apps to MonaOS, managing files on device, syncing projects, organizing code, or setting up deployment pipelines.

1
install
▌
Badger Diagnostics · johnlindquist
System diagnostics, verification, and troubleshooting for Badger 2350. Use when checking firmware version, verifying installations, diagnosing hardware issues, troubleshooting errors, or performing system health checks on Badger 2350.

1
install
▌
DB · johnlindquist
Database operations for SQLite, PostgreSQL, and MySQL. Use for queries, schema inspection, migrations, and AI-assisted query generation.

1
install
▌
Tmux · johnlindquist
Manage tmux sessions for background processes. Use to run long-running commands, manage multiple terminals, and capture output from background processes.

1
install
▌
Beads · johnlindquist
Track tasks and issues using the bd CLI. Use for task management, sprint planning, dependency tracking, and project organization. Replaces TodoWrite.

1
install
▌
Debug · johnlindquist
Unified debugging workflow enforcing root cause protocol. Investigate → Understand → Reason → Fix. Use when debugging bugs, errors, or unexpected behavior.

1
install
▌
Chrome · johnlindquist
Browser automation using Puppeteer or Playwright. Use for web testing, screenshots, form filling, and automated browser interactions.

1
install
▌
Design · johnlindquist
Design system and token management. Use for managing design tokens, colors, typography, and maintaining design consistency.

1
install
▌
Gemini · johnlindquist
Use Gemini AI for research, analysis, summarization, web search, and complex reasoning. Use when you need AI-powered research, code analysis, content summarization, or web search with synthesis.

1
install
▌
Linear · johnlindquist
Manage Linear issues and workflows. Use for viewing, creating, and updating Linear issues, and integrating with development workflow.

1
install
▌
Council · johnlindquist
Query multiple AI agents in parallel for diverse perspectives. Use when you want multiple viewpoints on a question, to compare approaches, or to find consensus among AI models.

1
install
▌
Diagram · johnlindquist bundle
Use this skill whenever a "diagram" is mentioned. Maintain and synchronize Unified Impact Diagrams following Diagram Driven Development (DDD) methodology. Create, update, and manage diagrams that connect user value to technical implementation.

1
install
▌
Pipeline · johnlindquist
Chain multiple operations together in pipelines. Use for multi-step workflows, combining research with analysis, and complex automated tasks.

1
install
▌
Refactor · johnlindquist
Code refactoring with AI assistance. Use for modernizing code, converting JavaScript to TypeScript, class to hooks conversions, and systematic renaming.

1
install
▌
Research · johnlindquist
Comprehensive research combining web search and AI synthesis. Use for deep research on topics, comparing technologies, investigating libraries, and finding GitHub issues related to problems.

1
install
▌
Workflow · johnlindquist
Manage GitHub Actions workflows using gh CLI. Use to check CI status, view run logs, analyze failures, and rerun workflows.

1
install
▌
Worktree · johnlindquist
Manage git worktrees for parallel development. Use to work on multiple branches simultaneously without stashing or switching contexts.

1
install
▌
Changelog · johnlindquist
Generate and manage changelogs from git history. Use for release notes, tracking breaking changes, and maintaining project history.

1
install
▌
Agent Mail · johnlindquist
Inter-agent communication for multi-agent workflows. Use when multiple agents need to coordinate, share information, or reserve resources.

1
install
▌
Brainstorm · johnlindquist
Generate ideas and explore possibilities with AI. Use for creative problem solving, generating alternatives, and expanding on concepts.

1
install
▌
Skill Creator · johnlindquist
Create new Agent Skills for Claude Code. Use when user wants to create a skill, add a new capability, document a CLI workflow, or asks how skills work.

1
install
▌
Raycast Extension · johnlindquist
Build Raycast extensions with React and TypeScript. Use when the user asks to create a Raycast extension, command, or tool.

1
install

55 published skills