Agent Starter
Declarative agent config for Claude Code, Codex, and Cursor: an agent.json manifest for skills, MCP servers, and stack profiles, synced to each agent's native config, plus 29 hand-maintained skills.
Cleanup Dedupe
Detect duplicated code blocks and refactor to DRY where it reduces complexity. Runs jscpd (multi-language), filters by signal-to-noise, and auto-extracts only token-identical blocks ≥30 LOC. Use when the user asks to deduplicate, DRY up, find copy-paste, or consolidate repeated logic. Example queries — \"DRY this up\", \"find copy-paste in the codebase\", \"consolidate repeated logic\", \"where a…
Cleanup Cycles
Detect and untangle circular dependencies. Runs madge/skott (TS), pycycle (Py), or compiler-only checks (Go/Rust). Auto-fixes leaf-extractable cycles; reports core cycles for human review. Use when the user asks to find circular imports, fix dependency cycles, or untangle module graph. Example queries — \"find circular imports\", \"fix dependency cycles\", \"untangle our module graph\", \"why is…
Cleanup Legacy
Find and remove deprecated, legacy, and fallback code paths with zero callers. Verifies callers via repo grep + LSP before deletion. Removes unreachable fallback branches. Use when the user asks to remove deprecated code, clean up legacy paths, drop fallbacks, or simplify code branches. Example queries — \"remove the deprecated API\", \"drop the v1 fallback\", \"this code is marked legacy, kill i…
Hig Doctor Audit
HIG Doctor audit workflow for scanning app projects against Apple Human Interface Guidelines. Use when the user asks for a HIG audit, Apple UI compliance scan, accessibility/design lint, HIG Doctor, severity report, CI gate, or wants to verify SwiftUI, UIKit, React, Next.js, Vue, Svelte, Angular, React Native, Flutter, Compose, Android XML, CSS, or HTML against Apple HIG rules.
Hig Foundations
>-
Copywriting Frameworks
Direct-response copywriting workflow for drafting, rewriting, critiquing, and explaining persuasive copy. Use when Claude needs to work on headlines, hooks, ads, landing pages, emails, sales pages, CTAs, founder stories, lead magnets, social or video scripts, offer pages, copy critiques, copywork, swipe-file analysis, AIDA, curiosity gaps, open loops, objection handling, proof-first ads, or story…
Hig Project Context
>-
Hig Components Controls
>-
Goms Klm Analysis
GOMS and Keystroke-Level Model analysis for decomposing UI workflows into goals, operators, methods, selections, and expert-user execution estimates. Use when the user asks to compare task flows, count interaction cost, reduce clicks or keystrokes, evaluate command/menu/navigation choices, model expert performance, or redesign a workflow using GOMS, KLM, CMN-GOMS, or cognitive walkthrough style r…
Cleanup Slop
Strip AI slop, narration comments, restated-code comments, in-motion notes, and stub markers. Preserves comments that explain WHY (workarounds, invariants, surprising behavior). Comment-only changes — never touches code logic. Use when the user asks to remove AI slop, clean up comments, strip narration, or remove unhelpful comments. Example queries — \"remove the AI slop\", \"strip the narration…
Hig Components Search
>-
Hig Patterns
>-
Cleanup Defensive
Remove pointless try/catch blocks and defensive guards that hide errors or add no value. Preserves catches at true system boundaries (HTTP handlers, CLI entry, message consumers). Use when the user asks to remove try/catch, fix error hiding, clean up defensive code, or stop swallowing errors. Example queries — \"remove pointless try/catch\", \"we're swallowing errors\", \"stop hiding bugs in catc…
Hig Platforms
>-
Hig Components Status
>-
Hig Inputs
>-
Hig Components Content
>-
Cleanup Types
Find duplicated or fragmented type/interface definitions across files and consolidate to a shared types module. TypeScript-first; also handles Python dataclasses/TypedDicts and Go structs. Use when the user asks to consolidate types, find duplicate interfaces, or organize type definitions. Example queries — \"consolidate our types\", \"find duplicate interfaces\", \"this same type is defined in t…
Toon Formatter
Guidance on when and how to use TOON (Token-Oriented Object Notation) — a compact JSON alternative that typically cuts input tokens 30-50% on tabular data. Use when the user is about to paste or serialize a large JSON array into a prompt, has a payload with ≥5 uniform objects, or is optimizing an LLM pipeline for cost/context. Knows the format shapes (tabular `[N]{a,b}:` rows, inline `[N]: ...`,…
Cleanup Unused
Detect and delete unused code, exports, files, and dependencies. Runs knip/vulture/staticcheck/cargo-machete appropriate to the language, writes a critical assessment, and auto-applies HIGH-confidence deletions. Use when the user asks to remove dead code, find unused exports, clean up dependencies, or run dead-code analysis. Example queries — \"find dead code\", \"what's unused in this repo\", \"…
Hig Components System
>-
Cleanup All
Run all 8 cleanup skills in sequence: unused → cycles → dedupe → types → weak-types → defensive → legacy → slop. Each step verifies before the next runs; halts on first failure. Produces one consolidated report. Use when the user asks to clean up the whole codebase, run all cleanup skills, do a full code-quality pass, or sweep the repo. Example queries — \"clean up the whole codebase\", \"run a f…
Cleanup Weak Types
Replace weak types (any, unknown, interface{}, untyped Python) with strong, inferable types. Researches actual usage to determine the correct type, runs typecheck after each change, reverts individual changes that fail. Use when the user asks to remove any/unknown, strengthen typing, fix weak types, or make code more type-safe. Example queries — \"remove all the `any` types\", \"strengthen our ty…
Hig Components Layout
>-
Hig Technologies
>-
Hig Components Menus
>-
Hig Components Dialogs
>-
Human Processor Model
Human Processor Model workflow for estimating interaction time, cognitive load, motor/perceptual bottlenecks, and memory risk in product flows. Use when the user asks to evaluate usability, estimate task completion time without a study, compare UI alternatives by interaction cost, audit working-memory burden, or apply Card-Moran-Newell style MHP reasoning to a prototype, design, app, or workflow.
Docpull
Convert the public web into AI-ready Markdown with a local Python CLI/SDK/MCP crawler.
Finish Setup
Finish provisioning a freshly scaffolded SaaS project using the MCP servers wired by agent.json (Neon, Stripe, Resend, PostHog, GitHub). Verifies env vars, creates Stripe products matching the billing plans, checks database migrations, walks email-domain DNS, and confirms analytics. Use when the user says \"finish setup\", \"provision the project\", \"set up stripe/the database\", or after scaffo…