cross-model-handoff
claudePassphrase-based session handoff: write one note before /clear or a tool switch, resume by name in Claude Code, Codex, Gemini CLI, Antigravity, Cursor or any AGENTS.md-aware tool.
3 skills · hooks
One thin router chooses among fourteen product specialists (brain, biz, brand, UI, dev, test, debug, a11y, secure, verify, ship and more) and gates release behind verification.
Plugin superforge-skills from marketplace takaoumehara in takaoumehara/skills. Commands read from the repo's manifest — 1 month ago.
superforge-a11yAudit and fix accessibility against WCAG 2.2, ARIA, Apple, and Material guidance — a seven-pass run (automated, keyboard, screen reader, zoom and reflow, colour, motion and time, forms and errors) that produces a criterion-by-criterion verdict instead of a scanner dump. Covers Web, iOS, and Android,
superforge-bizDecide whether a market is worth entering, then architect the business model on top of it. Opens with a GO/NO-GO gate: TAM/SAM/SOM computed both ways, confidence tiers on every input, and the reverse calculation asking how many customers this needs and whether you can reach that many. Then monetizat
superforge-brainRun the BreakBias engine — an exhaustive, machine-checkable idea sweep — or, when the stakes don't call for it, a lighter classic method (SCAMPER, Six Hats, Crazy 8s, How Might We). For a full sweep: decompose the problem across five lenses, name the hidden bias on every element, ban the obvious thr
superforge-brandDefine brand identity systems (naming, tone, visual tokens, VVA Matrix coordinates) and produce AI-generated visual and motion assets through prompt engineering for generate_image, Kie.ai, and Higgsfield — with the generation cost, the consistency recipe that makes a twelfth image match the first, a
superforge-debugRoot-cause-first debugging with FailForward learning memory, which recalls past failures before diagnosing and records new ones after, in a committed docs/failforward.md that survives the session. Forbids trial-and-error patching and dummy fallbacks that mask symptoms. Covers the bugs the protocol c
superforge-devBuild multi-component features by decomposing the work and dispatching subagents, assigning a model tier per subtask. Splits work into tasks with one outcome, a proof line, and a listed set of files — so parallel safety is decidable rather than hoped for — and proposes Subagents versus Agent Teams v
superforge-handoffWrite the session state to a structured capsule in .handoff/ so any AI model or tool (Claude Code, Codex, Gemini CLI, Antigravity, Cursor) can resume the work with zero context loss. Use before clearing a long thread or switching tools. Also packages work for an async cloud agent such as Devin — dec
superforge-roastDeliver an unsparing, compliment-free critique of a design, PRD, plan, architecture, copy, or UI to expose flaws before they ship. Strips AI politeness and names the weakest point first. Use when the user says "roast", "be brutal", "tear this apart", "what's wrong with", "honest feedback", "critique
superforge-scrollBuild a scroll-scrubbed cinematic landing page where scroll drives a camera continuously through a generated world, with no cuts between scenes. Plans the camera before generating anything — floor plan or world map, room adjacency, a shot list with camera position, heading, lens and eye height per l
superforge-secureSecurity review for products built by small teams — seven passes (secrets, authentication, authorization, input handling, data at rest and in transit, dependencies, exposed surface) producing a finding-by-finding ledger instead of a scanner dump. Ranks by what an attacker actually gets, not by a gen
superforge-shipDecide whether a product may be released, a different question from whether it works. Runs the release gate: which legal obligations the product's own data handling triggered and where a lawyer becomes mandatory, what will actually get it rejected from the App Store or Google Play, the measurement t
superforge-testDecide what earns a test, then drive implementation through Red-Green-Refactor TDD across Web (Jest, Vitest, Playwright), iOS (Swift Testing, XCTest), and Android (JUnit, Compose Test), verifying each red and green state by actually running the suite. Covers test granularity (unit / integration / E2
superforge-uiDesign and build interfaces across Web, iOS (SwiftUI), and Android (Jetpack Compose), covering layout, visual hierarchy, typography, responsive behaviour, state specification, and micro-interactions. Opens by sourcing the visual direction from references or a design made in another tool, and extract
superforge-verifyGate that blocks any completion claim until there is empirical runtime evidence — the test suite actually run, both mobile and desktop viewports checked, and native iOS or Android simulator runs confirmed. Grades every piece of evidence (reproducible / observed / derived / asserted) and forbids a re
superforgeUse when starting a substantial product or feature phase, choosing the next specialist across strategy, design, engineering, verification, security, or release. Skip bounded follow-up edits. author: Takao Umehara version: "5.1
Passphrase-based session handoff: write one note before /clear or a tool switch, resume by name in Claude Code, Codex, Gemini CLI, Antigravity, Cursor or any AGENTS.md-aware tool.
3 skills · hooks
Three design skills for work built on human movement, cameras and sensors: a director that first decides experience vs. training tool, plus specialists for installations and movement-learning systems.
3 skills
Design and build games a first-time player understands with no manual: intuition design and diagnosis, one-tap game feel, Web Audio, camera/body input, calm puzzles, multiplayer sync.
2 skills
Take a messy git working tree back to clean (untrack build output, complete .gitignore, sort changes into commit / stash / discard) without leaking a secret or losing uncommitted work.
1 skill
Pair phones and screens by QR, PIN or broadcast and stream realtime input over Firebase, PartyKit, WebRTC or BroadcastChannel. Ships with the snap-pair-core npm package.
1 skill
MetaHarness integration — surfaces score/genome/mint/mcp-scan/threat-model via skills; pairs with @metaharness/router (ADR-148/149) for cost-optimal model routing; honors ADR-150 optional-augmentation constraint
13 skills · 1 command · 1 agent · hooks
Official Expo skills for building, deploying, upgrading, and debugging React Native apps with Expo. Covers UI development with Expo Router, SwiftUI and Jetpack Compose components, Tailwind CSS setup, API routes, data fetching, CI/CD workflows, App Store and Play Store deployment, SDK upgrades, DOM components, and dev client distribution.
23 skills · 1 MCP server
Portable operating method: session lifecycle agents, pre-ship code review, deploy with live verification and state doc update, and production log health check
5 agents
33 C-level advisory skills (install the separate companion c-level-agents plugin for the persona layer): virtual board of directors (CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO) plus General Counsel, CDO, CAIO, CCO, and VP of Engineering (DORA delivery throughput analyzer, engineering hiring funnel calculator with conversion + pipeline gap, eng team structure designer with squad/tribe + manager-trigger), executive mentor, founder coach, orchestration (Chief of Staff, board meetings, decision logger), strategic capabilities (board deck builder, scenario war room, competitive intel, M&A playbook), culture frameworks. The 13 cs-* persona agents + 21 /c-level-agents:* slash commands (founder-mode router, office-hours intake, multi-role boardroom, strategic sprint pipeline, cross-model consensus, cooldown freeze) ship in the companion c-level-agents plugin.
34 skills · hooks
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Includes LaTeX templates, citation verification, reviewer guidelines, publication-quality figure generation, systems paper structural blueprints, and conference presentation slides.
98 skills
dontbesilent 商业工具箱的技能调度台,根据当前问题和反馈选择下一步,在对话中直接执行、澄清、组合或对照尝试 Skill。用户不知道从哪里开始、需要调整处理方法、第一次使用 dbskill、输入三位编号或查询隐藏款目录时使用;仅需推荐或可复制提示词时按请求交付。
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.