← all publishers

MadAppGang

@madappgang source repo

Report this profile Claim this profile

• 207 skills
• 0 followers
• last month last updated

1. ▌
   Tanstack Query 2 · madappgang

   Comprehensive TanStack Query v5 patterns for async state management. Covers breaking changes, query key factories, data transformation, mutations, optimistic updates, authentication, testing with MSW, and anti-patterns. Use for all server state management, data fetching, and cache invalidation tasks.
   9 installs
2. ▌
   Shadcn UI 2 · madappgang

   shadcn/ui component library patterns. Covers CLI usage, installation, component categories, theming with CSS variables, dark mode setup, and integration with React Hook Form + Zod. Use when adding UI components, setting up design systems, or implementing forms with shadcn/ui.
   10 installs
3. ▌
   Tanstack Router 2 · madappgang

   Use when setting up routes, implementing navigation, or configuring route loaders. TanStack Router patterns for type-safe, file-based routing. Covers installation, route configuration, typed params/search, layouts, and navigation.
   9 installs
4. ▌
   Claudish Usage 6 · madappgang

   CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, Gemini, OpenAI, Ollama, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
   9 installs
5. ▌
   Style Format 2 · madappgang

   Style template format specification. Single markdown files that describe artistic direction.
   10 installs
6. ▌
   Transcription 2 · madappgang

   Provides Whisper transcription patterns — model selection, SRT/VTT/JSON, timing sync, diarization. Use when transcribing audio or video, or generating subtitles.
   5 installs
7. ▌
   Ffmpeg Core 2 · madappgang

   Provides FFmpeg patterns — trim, concat, convert, extract, codec selection, filter chains. Use when planning or executing video or audio processing tasks.
   12 installs
8. ▌
   Claudish Integration · madappgang

   Claudish Integration Skill
   7 installs
9. ▌
   Error Recovery 2 · madappgang

   Handle errors, timeouts, and failures in multi-agent workflows. Use when dealing with external model timeouts, API failures, partial success, user cancellation, or graceful degradation. Trigger keywords - "error", "failure", "timeout", "retry", "fallback", "cancelled", "graceful degradation", "recovery", "partial success".
   14 installs
10. ▌
    Claudish Usage 5 · madappgang

    CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
    9 installs
11. ▌
    UI Analyse 2 · madappgang

    Reviews a UI screenshot — usability, WCAG, design-system consistency, design-vs-implementation diff. Prompting patterns, depth tiers and severity guidelines. Analysis only; pair with dev:frontend-implement to apply.
    9 installs
12. ▌
    Context Detection 2 · madappgang bundle

    Detects the project stack from its config files, then names the one or two dev skill files to read for this task — it loads none of them. Use at the start of any coding task, or on an unfamiliar or multi-stack repo.
    8 installs
13. ▌
    Claudish Usage 4 · madappgang

    Runs models through the claudish MCP tools — team, create_session, run_prompt — and resolves model IDs against the live catalog. Use when the user mentions claudish, OpenRouter, or external AI models.
    9 installs
14. ▌
    Plugin Sdk Patterns 2 · madappgang

    Patterns and templates for building Claude Code plugins. Use for plugin development — creating a plugin, skill and agent templates, plugin architecture, or standardizing structure.
    8 installs
15. ▌
    Hooks System 2 · madappgang

    Lifecycle hook patterns — PreToolUse, PostToolUse, UserPromptSubmit, Stop, SubagentStop. Use when configuring hooks, writing validation, auto-format on save, stdin payloads, exit-2 blocking, or debugging a hook.
    10 installs
16. ▌
    UI Style Format 2 · madappgang

    Specifies the UI design style file format and schema for .claude/design-style.md and .claude/design-references/. Use when creating, validating, or parsing project design styles.
    10 installs
17. ▌
    Quality Gates 2 · madappgang

    Implement quality gates, user approval, iteration loops, and test-driven development. Use when validating with users, implementing feedback loops, classifying issue severity, running test-driven loops, or building multi-iteration workflows.
    11 installs
18. ▌
    Investigate 2 · madappgang

    Routes a code investigation to one of four modes — bug, test gap, architecture, implementation — and runs the query sequence that mode needs. Use when asked to investigate, trace, or debug code.
    9 installs
19. ▌
    Design References 2 · madappgang

    Provides design system references — Material 3, Apple HIG, Tailwind UI, Ant Design, Shadcn/ui. Use when reviewing UI against an established design system.
    11 installs
20. ▌
    Brainstorming 2 · madappgang

    Explores solution approaches in parallel across models, scores confidence, validates the chosen plan. Use when planning an approach or asked to brainstorm.
    8 installs
21. ▌
    Testing Strategies 2 · madappgang bundle

    Testing pyramid, AAA structure, test doubles, fixtures, assertions and coverage targets, in any language. Use when writing, reviewing or setting up tests. Do not use for the write-test-first loop — that is test-driven-development.
    5 installs
22. ▌
    Universal Patterns 2 · madappgang

    Code organization, error handling, data flow, naming and anti-patterns in any language. Use while writing or reviewing everyday code. Do not use to choose a system shape or a design pattern — read the architecture skill instead.
    10 installs
23. ▌
    Documentation Standards 2 · madappgang

    15 ranked documentation practices, 7 templates and anti-slop writing rules. Use when writing or reviewing a README, API reference, guide or changelog, even if the user only says "document this".
    12 installs
24. ▌
    Bunjs Production 2 · madappgang

    Provides Bun.js production patterns — Docker, AWS ECS/Fargate, Redis caching, security hardening, CI/CD. Use when deploying or operationalizing a Bun.js service.
    5 installs
25. ▌
    Agent Enforcement 2 · madappgang

    Multi-agent orchestration enforcement for /team command. Validates session directory paths and ensures /team Tasks use a valid agent from the routing whitelist. Use when debugging /team orchestration failures.
    6 installs
26. ▌
    Batching Patterns 2 · madappgang

    Batches related operations into single messages for maximum parallelism. Use when launching multiple agents, reading many files, or removing sequential execution bottlenecks.
    8 installs
27. ▌
    Session Isolation 2 · madappgang

    Use when orchestrating workflows that generate multiple files (designs, reviews, reports) to prevent file collisions across concurrent or sequential sessions with unique session directories.
    9 installs
28. ▌
    Task Orchestration 2 · madappgang

    Track progress in multi-phase workflows with Tasks system. Use when orchestrating 5+ phase commands, managing iteration loops, tracking parallel tasks, or providing real-time progress visibility.
    8 installs
29. ▌
    Bunjs Architecture 2 · madappgang

    Provides Bun.js clean architecture patterns — routes/controllers/services/repositories, camelCase conventions, Prisma schemas. Use when designing layered Bun.js apps or planning structured workflows.
    6 installs
30. ▌
    Browser Debugging 2 · madappgang

    Tests UI in a real browser via Chrome MCP — visual fidelity, console, network. Use when verifying UI, chasing browser bugs, or console errors.
    9 installs
31. ▌
    Performance Tracking 2 · madappgang

    Track agent, skill, and model performance metrics for optimization. Use when measuring agent success rates, tracking model latency, analyzing routing effectiveness, or optimizing cost-per-task.
    9 installs
32. ▌
    Proxy Mode Reference 2 · madappgang

    Reference for running models through the claudish MCP tools — team, create_session, run_prompt. Covers model routing, native Claude slots, require_pattern shape checks, and error handling. Use when working on /team, /delegate, or any claudish call.
    6 installs
33. ▌
    Task External Models 2 · madappgang

    Quick reference for running external models in orchestration. They are invoked via claudish MCP tools (team, create_session), never the CLI. Use when unsure how to specify an external model.
    9 installs
34. ▌
    Worktree Lifecycle 2 · madappgang

    Creates, uses and cleans up git worktrees with safety checks. Use before isolated, risky or parallel feature work, or on mention of worktree, experiment or prototype.
    8 installs
35. ▌
    Multi Model Validation 2 · madappgang

    Runs the same task across multiple AI models in parallel and aggregates verdicts. Use when the user wants a second opinion, multi-expert validation, or consensus from Grok, Gemini, GPT-5, or Kimi.
    9 installs
36. ▌
    Task Complexity Router 2 · madappgang

    Routes tasks to model tiers (haiku/sonnet/opus) by complexity. Use for model selection, complexity routing, picking a tier, or optimizing API cost.
    11 installs
37. ▌
    Model Tracking Protocol 2 · madappgang

    MANDATORY tracking protocol for multi-model validation. Creates structured tracking tables BEFORE launching models, tracks progress during execution, and ensures complete results presentation. Use when running 2+ external AI models in parallel.
    9 installs
38. ▌
    Systematic Debugging 2 · madappgang bundle

    Root-cause debugging — reproduce, localize, explain, verify — with depth routing and a technique catalogue for stack traces, wolf fence and data-flow tracing. Use when anything errors, crashes or misbehaves, even on a bare pasted trace.
    5 installs
39. ▌
    Hierarchical Coordinator 2 · madappgang

    Prevents goal drift in long multi-agent runs by validating outputs against the original objective at checkpoints. Use when orchestrating 3+ agents or multi-phase work.
    8 installs
40. ▌
    Multi Agent Coordination 2 · madappgang

    Coordinate multiple agents in parallel or sequential workflows. Use when running agents simultaneously, delegating to sub-agents, switching between specialized agents, or managing agent selection.
    7 installs
41. ▌
    Test Driven Development 2 · madappgang

    RED-GREEN-REFACTOR: write a failing test, watch it fail, make it pass, refactor. Use before writing any production code or bug fix, or on mention of TDD or test-first, even if the user asked only for the implementation.
    9 installs
42. ▌
    Verification Before Completion 2 · madappgang

    Requires fresh evidence — command output, a test run, a screenshot — before any completion claim. Use when marking work done, saying something is fixed, or before committing, even when the change looks obviously correct.
    8 installs
43. ▌
    Experiment Journal 2 · madappgang bundle

    Write a structured experiment journal article after completing an experiment iteration. Use this skill whenever the user finishes running an experiment, wants to document results, says 'write journal', 'document this experiment', 'save experiment results', 'write up the iteration', or after any experiment run completes. Also trigger when the user asks to compare experiment iterations, summarize findings, or create a report from autotest results.
    7 installs
44. ▌
    Claudish Usage 3 · madappgang

    CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
    10 installs
45. ▌
    Deep Analysis 2 · madappgang

    ⚡ PRIMARY SKILL for: 'how does X work', 'investigate', 'analyze architecture', 'trace flow', 'find implementations'. PREREQUISITE: code-search-selector must validate tool choice. Launches codebase-detective with claudemem INDEXED MEMORY.
    7 installs
46. ▌
    Macos App Testing No Disrupt 2 · madappgang bundle

    Verify, screenshot, AND drive a native macOS app on the same machine the user is actively working on, WITHOUT stealing their mouse, keyboard, or window focus. Use this whenever you need to screenshot, inspect, click through, or confirm the behavior of a running Mac app (Swift/SwiftUI, Electron, AppKit, a dev build, a cloned app) and the user is present at the machine — even if they just say "check that it works", "screenshot the app", "verify the UI", "does the picker show X", "click through the flow", or "test my app". Especially use it the moment driving the GUI with computer-use would yank focus away from the user. Covers focus-free window capture (screencapture -l), focus-free clicking and typing via the Accessibility API (AXPress / set value), read-only window/process/file inspection, and human-handoff only when AX genuinely can't reach a control.
    9 installs
47. ▌
    Release 2 · madappgang bundle

    Release one or more Magus plugins. Infers the version bump from git history, bumps plugin.json and marketplace.json, commits, and after the PR merges tags the merge commit with one explicit ref per tag; CI gates the PR and publishes the dist repos. Use whenever the user says "release setup", "release the dev plugin", "cut a new version of terminal", "bump setup to 1.3", or hands you a batch like "release setup and terminal". Also use to check what a release would contain before committing.
    5 installs
48. ▌
    Skill Authoring 2 · madappgang bundle

    Writes and reviews SKILL.md files for this repo — a description that triggers, a body that fits, and a visibility choice that does not starve a preload consumer. Use when adding, editing or auditing any skill. Not for commands or agents.
    10 installs
49. ▌
    Claudish Usage 2 · madappgang

    CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, Gemini, OpenAI, Ollama, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
    8 installs
50. ▌
    Lsp Hover Testing · madappgang bundle

    Automated LSP hover validation for Dingo transpiler. Use when testing hover functionality, validating position mappings, checking for hover drift, or debugging LSP issues after sourcemap changes.
    10 installs
51. ▌
    Table Print · madappgang

    Render beautiful terminal tables, bar charts, and leaderboards for experiment results using tools/table.ts. Use when the user asks to display data, render a table, show results, create a leaderboard, make a chart, visualize experiment output, or print formatted terminal output. Also use when creating display scripts for any experiment in this repo.
    9 installs
52. ▌
    Skill Authoring · madappgang bundle

    Writes and reviews SKILL.md files for this repo — a description that triggers, a body that fits, and a visibility choice that does not starve a preload consumer. Use when adding, editing or auditing any skill. Not for commands or agents.
    9 installs
53. ▌
    Macos App Testing No Disrupt · madappgang bundle

    Verify, screenshot, AND drive a native macOS app on the same machine the user is actively working on, WITHOUT stealing their mouse, keyboard, or window focus. Use this whenever you need to screenshot, inspect, click through, or confirm the behavior of a running Mac app (Swift/SwiftUI, Electron, AppKit, a dev build, a cloned app) and the user is present at the machine — even if they just say "check that it works", "screenshot the app", "verify the UI", "does the picker show X", "click through the flow", or "test my app". Especially use it the moment driving the GUI with computer-use would yank focus away from the user. Covers focus-free window capture (screencapture -l), focus-free clicking and typing via the Accessibility API (AXPress / set value), read-only window/process/file inspection, and human-handoff only when AX genuinely can't reach a control.
    9 installs
54. ▌
    Pr Comment · madappgang

    Write GitHub PR comments in Jack's voice. Use whenever writing, drafting, or posting PR comments — review feedback, thank-you notes, merge comments, close explanations, or change requests. Also use when the user asks to "comment on PR", "review PR", "thank contributor", "close PR", or "write PR feedback". Always use this skill for ANY PR comment writing, even if the user doesn't explicitly mention it.
    7 installs
55. ▌
    1password Sdk · madappgang bundle

    How to load secrets and environment variables from 1Password programmatically using the official @1password/sdk (JavaScript/TypeScript). Use this skill whenever code needs to read a 1Password secret, resolve an op:// reference, fetch many secrets at once, discover the fields/sections of a 1Password item (e.g. to import API keys), or read a 1Password Environment — even if the user doesn't name the SDK explicitly. Triggers on: "@1password/sdk", "op://", "OP_SERVICE_ACCOUNT_TOKEN", "DesktopAuth", "resolve a secret from 1Password", "1Password service account", "1Password Environments", "fetch API keys from 1Password", or wiring 1Password into a Node/Bun/TypeScript app. Prefer this in-process SDK over shelling out to the `op` CLI unless the task specifically needs the user's interactive `op signin` session.
    7 installs
56. ▌
    Final Cut Pro · madappgang

    Final Cut Pro FCPXML reference — project structure, timelines, clip references, effects, transitions. Use when generating or reading FCP projects.
    13 installs
57. ▌
    Image Providers · madappgang

    Reference for generating images across Google, OpenAI and ByteDance through one CLI. Use when generating or editing images, picking an image model, or resolving image API key and provider errors.
    8 installs
58. ▌
    Release · madappgang bundle

    Release one or more Magus plugins. Infers the version bump from git history, bumps plugin.json and marketplace.json, commits, and after the PR merges tags the merge commit with one explicit ref per tag; CI gates the PR and publishes the dist repos. Use whenever the user says "release kanban", "release the dev plugin", "cut a new version of gtd", "bump kanban to 1.7", or hands you a batch like "release kanban and gtd". Also use to check what a release would contain before committing.
    7 installs
59. ▌
    Bun · madappgang bundle

    Router for the eight Bun/TypeScript skills — setup, HTTP, errors, testing, security, production, performance, TUI. Says which to read for a task, without loading them. Any Bun or TS work.
    12 installs
60. ▌
    Tui · madappgang bundle

    Build, review, or debug OpenTUI terminal UIs — React JSX or core constructs, Yoga flexbox, gradient meters, colour screenshots. Any Bun/TypeScript TUI. Only Bun is tested; Node/Deno at own risk.
    7 installs
61. ▌
    Go Tui · madappgang bundle

    Build, review, or debug Go terminal UIs with the Charm stack — Bubble Tea, Lip Gloss, Bubbles, ntcharts. Use for any Go TUI, dashboard, or full-screen CLI, including colour-accurate screenshots.
    7 installs
62. ▌
    Errors · madappgang bundle

    Error handling and resilience for Bun/TypeScript — operational vs programmer errors, AppError hierarchy, centralized handler, boundary validation, timeout/retry/circuit breaker. Copyable, tested.
    7 installs
63. ▌
    Testing · madappgang bundle

    Write and fix Bun tests — bun:test surface, component tests over HTTP, doubles, coverage gating, flake control. Ships a tested harness, fake upstream and builders. Includes a measured silent-coverage-gate trap.
    4 installs
64. ▌
    Security · madappgang bundle

    Harden or review a Bun/TypeScript service — secrets, password and token handling, SQL injection, authn/authz, rate limiting, CORS and security headers, dependency audit. Ships tested guards with measured Bun crypto behaviour.
    9 installs
65. ▌
    Code Roast · madappgang bundle

    Roasts code with severity-graded sins, cites file and line, offers redemption. Use when the user asks to roast code, find sins, or shame my code.
    8 installs
66. ▌
    Gtd Review · madappgang

    Weekly review automation for GTD workflow. Guides through inbox processing, project review, and next actions.
    8 installs
67. ▌
    Gtd Capture · madappgang

    Proactive capture trigger detection for GTD workflow. Detects "I need to", "we should", "remind me" signals and routes to inbox.
    9 installs
68. ▌
    Production · madappgang bundle

    Ship a Bun service — graceful shutdown ordering, structured logging, liveness vs readiness, multi-stage Docker, signals and PID 1, frozen lockfiles, CI. Ships tested logger, shutdown and health code plus a Dockerfile.
    6 installs
69. ▌
    Compare · madappgang

    Provides the compare.ts CLI invocation pattern, semantic comparison prompt template, severity thresholds, and model selection guide for UI design comparison.
    8 installs
70. ▌
    Architecture · madappgang bundle

    Router for architecture knowledge — 7 architectural styles (layered, hexagonal, clean, modular monolith, microservices, event-driven, CQRS) and the 22 GoF design patterns. Names which file to read; loads none of them.
    10 installs
71. ▌
    Performance · madappgang bundle

    Diagnose and fix Bun/TypeScript performance — event-loop blocking, measured native fast paths, benchmarking that does not lie, streaming, caching, workers, memory. Ships a tested benchmark harness.
    7 installs
72. ▌
    HTTP Service · madappgang bundle

    Build or review a Bun HTTP service — Bun.serve declarative routes, middleware composition, request context, status/ETag/streaming helpers, graceful lifecycle. Ships tested middleware with measured routing gotchas.
    7 installs
73. ▌
    Index Skills · madappgang bundle

    Walks every skill reachable from this project and writes a browsable markdown index, plus a small deterministic index spliced into CLAUDE.md. Explicit invocation only — run /setup:index-skills.
    8 installs
74. ▌
    Project Setup · madappgang bundle

    Start or restructure a Bun/TypeScript project — folder structure by business component, strict tsconfig, typed env config, workspaces and catalogs, bunfig, linting. Ships a tested config parser and measured install-layout facts.
    8 installs
75. ▌
    Core API · madappgang

    Reference for the Browser Use MCP tools — parameters, returns, session lifecycle. Use when navigating, clicking, typing, evaluating JS, or extracting page content.
    11 installs
76. ▌
    Debug UI · madappgang

    Visual UI debugging — screenshot capture and analysis, responsive layout checking at multiple viewport sizes, CSS validation via DOM state, visual regression detection, before/after state comparison.
    5 installs
77. ▌
    Dingo Developer · madappgang

    Generates and reviews Dingo meta-language code with Go boundary handling. Use when the user mentions Dingo, .di files, or Dingo-to-Go transpilation.
    8 installs
78. ▌
    Tdd Workflow · madappgang

    Drives a Red-Green-Refactor state machine for TDD with terminal test watchers. Use when running TDD in watch mode or iterating on failing tests with jest, vitest, cargo watch, or pytest-watch.
    7 installs
79. ▌
    Agent Model · madappgang

    Picks the browser-use agent brain LLM per task. Use when choosing a model for retry_with_browser_use_agent or a cloud session, or the user mentions a cheap, slow, or smart model.
    8 installs
80. ▌
    Madbench Evals · madappgang bundle

    Authors, runs, and debugs madbench evals — bench YAML, checks, red-state testdata, the two controls (check / grade), expectation tuning. Use when writing or reviewing a madbench.yaml or Eval file, choosing checks, or debugging a failing bench.
    5 installs
81. ▌
    Web Scraping · madappgang

    Structured data extraction from web pages — pagination patterns, dynamic SPAs, authenticated scraping, rate limiting, anti-bot handling, JSON/CSV output.
    9 installs
82. ▌
    DB Branching · madappgang

    Branches Neon, Turso, or Supabase per git worktree for isolated schema work. Use when a worktree changes the schema, or on mention of Neon, Turso, Prisma.
    10 installs
83. ▌
    Workspace Setup · madappgang

    Orchestrates tmux workspaces — dashboards, watch/entr monitors, one command on many hosts — on numbered helper slots. Use for a multi-pane dashboard, an ambient monitor, a command across hosts, or a startup script for the user.
    9 installs
84. ▌
    Code Search · madappgang

    Finds code by meaning, structure or exact text, then reads only the spans returned. Use when searching a codebase, locating a symbol, tracing callers, or about to open three or more files.
    6 installs
85. ▌
    Error Recovery · madappgang

    Handle errors, timeouts, and failures in multi-agent workflows. Use when dealing with external model timeouts, API failures, partial success, user cancellation, or graceful degradation.
    9 installs
86. ▌
    Framework Signals · madappgang

    Provides pass/fail/running/idle output markers for 15+ test, build, and deploy tools. Use when monitoring terminal output for jest, vitest, pytest, go test, cargo, webpack, vite, or vercel.
    11 installs
87. ▌
    Deep Analysis · madappgang

    Audits a codebase across seven dimensions, from architecture to code health, scoring each finding with evidence. Use for a full codebase review, tech-debt assessment, or post-incident analysis.
    14 installs
88. ▌
    Hybrid Debugging · madappgang

    Combines Browser Use (DOM, clicks, screenshots) with claude-in-chrome (console, network, JS) for full-spectrum debugging. Use when investigating console errors or network requests.
    14 installs
89. ▌
    Delegate Patterns · madappgang

    Delegating plugin commands and tasks to external models via claudish — capability discovery, pre-flight question gathering, and prompt assembly. Use when routing work to an external model.
    11 installs
90. ▌
    Terminal Interaction · madappgang

    Slot-addressed tool patterns for interactive terminal access. Use when running interactive commands, starting dev servers, watching tests, querying databases, or working beside the user.
    10 installs
91. ▌
    Statusline Customization · madappgang

    Configuration reference and troubleshooting for the statusline plugin — sections, themes, bar widths, and script architecture
    6 installs
92. ▌
    Navigation Patterns · madappgang

    URL navigation, multi-tab orchestration, session creation and management, back/forward navigation, browser profile persistence, session export/import for authentication reuse.
    9 installs
93. ▌
    Frontend Implement · madappgang

    Rewrites generic-looking UI by five anti-generic rules — asymmetry, texture, typography, motion, colour. Use when applying design-review fixes, or UI looks AI-generated.
    7 installs
94. ▌
    Browser Use Integration · madappgang

    Detects the browser-use@magus plugin and captures screenshots of URL-based references. Use when designer agents need browser screenshot capture and claude-in-chrome is unavailable.
    10 installs
95. ▌
    Tui Navigation Patterns · madappgang

    Provides key sequences and navigation patterns for common TUI apps. Use when navigating vim, nano, htop, less, psql, lazygit, k9s, tig, btop, or sending keystrokes to a database shell.
    10 installs
96. ▌
    Design System Guardrails · madappgang bundle

    Enforces single-source-of-truth UI — design tokens for every style value, one component library, variants instead of call-site restyling. Use before writing or reviewing any component, screen, theme or style, even a one-line tweak.
    8 installs
97. ▌
    Experiment Journal · madappgang

    Write a structured experiment journal article after completing an experiment iteration. Use this skill whenever the user finishes running an experiment, wants to document results, says 'write journal', 'document this experiment', 'save experiment results', 'write up the iteration', or after any experiment run completes. Also trigger when the user asks to compare experiment iterations, summarize findings, or create a report from autotest results.
    9 installs
98. ▌
    Agentbench Eval · madappgang

    AgentBench evaluation harness for claudemem. Covers pre-indexed repos, experiment conditions, running benchmarks, analyzing results, and managing index archives. Use when working on eval infrastructure, running experiments, or interpreting benchmark results.
    8 installs
99. ▌
    Tmux Control · madappgang bundle

    Drive tmux from the command line to manage terminal sessions, windows, and panes — split the current pane, run a command in a new pane, capture output, send keystrokes, resize/navigate panes, or spin up a fully isolated background tmux server for sandboxed work. Use this whenever you need to run something in a terminal pane beside your work, watch a long-running process (dev server, build, test watcher, log tail), drive an interactive CLI/REPL, set up a multi-pane layout, or run commands in a tmux server that stays invisible to the user's own `tmux ls`. Trigger on any mention of tmux, splitting/managing panes or windows, "run this in a pane", "watch the output", side-by-side terminals, or background/isolated terminal sessions — even when tmux isn't named explicitly but the task clearly needs terminal-pane control. If the tmux-mcp tools (`open-pane`, `execute-command`, `start-and-watch`, `capture-pane`, …) are available, prefer them for the ordinary "give me a pane and run something in it" case and use this sk
    9 installs
100. ▌
     Developer Detective · madappgang

     ⚡ Implementation analysis skill. Best for: 'how does X work', 'find implementation of', 'trace data flow', 'where is X defined', 'find all usages'. Uses claudemem AST with callers/callees for efficient code tracing.
     2 installs