Product & Planning

hermai-ai Bundle

REQUIRED when the user names a website and wants data from it, such as prices on allbirds.com, flights on kayak, or listings from zillow, or wants to add a new site to the Hermai registry. Supports self execution from open source schemas and hosted execution through Hermai Cloud. Covers discovery, session capture, schema authoring, push, and production fetch checks. SKIP when the task has no specific website or the user explicitly wants raw HTML of a one time page.

heyparsadev Bundle

This skill should be used when a founder wants to validate, pressure-test, or kill a startup/product idea before building it — sharpening a hunch into a testable hypothesis, red-teaming it, sizing the market, mapping competitors, designing and synthesizing customer-discovery interviews, and deciding whether the evidence justifies an MVP. Triggers on "validate my idea", "is this worth building", "should I build this", "test my hypothesis", "problem-solution fit", "customer discovery", "I have a startup idea", "poke holes in this idea", "ایده‌ام رو بررسی کن", "این ایده ارزش ساختن داره؟", "اعتبارسنجی ایده", "فرضیه‌سازی", "فرضیه‌ام رو تست کن", "مصاحبه با مشتری طراحی کن", "ایده استارتاپی دارم", "بسازم یا نه". Implements Chapter 3 (Idea Stage) of The Founder's Playbook. Do NOT use for MVP scoping, launch, or scaling work — use founder-playbook:stage-map to route those.

litecore-ai Skill

Develop production-compatible DDD vertical slices, either as one bounded ad-hoc change or by continuously executing an approved roadmap selector. Use for implementation, TDD, roadmap execution/resume, exact-range review, or explicit cancellation without disconnected stubs.

litecore-ai Bundle

Initialize or evolve a project’s DDD architecture, product brief, executable vertical-slice roadmap, and approved behavior contracts. Use for DDD adoption, architecture boundaries, roadmap planning, replanning, feature specification, contract review, or spec binding.

loong Skill

Add or update Go concurrency exercises in this workshop without committing solutions. Use when maintaining the repo, adding a challenge, changing tests or mocks, or updating agent discovery files (AGENTS.md, llms.txt, exercises.json, skills).

jeffy-peng Skill

起草或润色可直接发送的职场即时消息和邮件。用户明确要求“怎么说、怎么发、润色、改写、写消息、写邮件”，或提供职场素材并表明要发给某人时使用；仅展示背景、讨论沟通策略、撰写 PRD、报告或长篇文档时不使用。

fasalzein Skill

Slice a PRD or plan into independently-grabbable vertical slices — tracer bullets, each with acceptance criteria — for an implementing agent to pick up. Use when the user wants to turn a PRD or plan into implementation tickets, or plan delivery work.

floracat526 Bundle

Use this skill to draft, complete, review, or improve PRDs for AI or large-model products. Trigger whenever the user mentions AI product PRD, large model requirements, prompt design, model selection, evaluation set, model rollout, AI capability boundaries, data flywheel, AI product launch plan, or asks a product manager to turn an idea into an AI product requirements document.

flowglad Bundle

Help the user define a multi-milestone workstream for a larger project through clarifying questions, risk identification, milestone design, and dependency sequencing. Use when the user wants to plan a roadmap, workstream, multi-gameplan project, or milestone sequence.

fokkyp Skill

协助产品经理生成专业的产品需求文档(PRD)，通过交互式问答收集信息，进行竞品研究，迭代优化各模块内容，最终输出结构化的PRD文档。

frankxai Skill

Use when orchestrating multiple coding agent CLIs (Claude Code, Codex, OpenCode, Grok CLI, Antigravity). Discovery, comparison, structured prompting, and multi-agent handoff patterns. Portable free pack — no host-specific secrets.

gandli Bundle

Build search queries for network asset discovery platforms (space测绘). Use when users want to find network assets, discover attack surfaces, investigate vulnerabilities (CVE), or search for specific services/servers/websites. Triggers on: 空间测绘, FOFA, 鹰图, ZoomEye, Shodan, CVE, 漏洞, asset discovery, network search, or similar queries.

modiqo Skill

Autonomous adapter creation agent. Takes a request like "connect to Stripe" and runs the full discovery, analysis, research, auth, scoping, creation, and verification pipeline using rote CLI commands.

moonbitlang Bundle

Route implementation, design, review, diagnosis, and testing work on the Moon CLI and MoonBuild to canonical glossary, ADR, design, behavioral-reference, and testing documents. Use when work touches crates/moon, crates/moonbuild-rupes-recta, crates/moonbuild, crates/moonbuild-debug, crates/mooncake, crates/moonutil, xtask, or docs for moon commands, package discovery, dependency resolution, workspaces, build planning and lowering, targets and toolchains, native builds, command output, caching, moon run, moon test, moonx, or runwasm. Do not use for crates/moonrun runtime internals.

morpho-org Bundle

Build or review Morpho Earn integrations that deposit into and exit from Morpho Vault V2. Use for Vault V2 discovery, data, APY and rewards, positions, deposit or withdrawal transactions, illiquid exits, UI copy, QA, and pre-launch review. Treat Vault V1 only as migration or compatibility context.

morpho-org Bundle

Build or review Morpho borrowing integrations for Blue variable-rate markets, Midnight fixed-rate fixed-term markets, or both. Use for market discovery, collateralized borrow and repayment transactions, position risk, rates, liquidity, refinancing, Midnight quotes and maturities, UI copy, QA, and pre-launch review. Identify the product before loading implementation guidance.

motiondivision Bundle

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

mrlesk Bundle

Technical project management for Backlog.md workstreams using coordinated sub-agents. Use only when the user explicitly asks Codex to take over one or more existing Backlog.md tasks (for example: "act as TPM", "coordinate these tasks", "delegate to sub-agents"). Orchestrate planning, implementation, and finalization; manage dependencies and overlapping code areas; review and approve sub-agent plans before implementation.

narumiruna Bundle

Create, name, rename, revise, or review agent skills for clear triggers, safe workflows, strong checks, lean content, and easy discovery, and score or numerically compare skills only when the user explicitly asks.

oukeming64-tech Bundle

Keep repository documentation aligned with code, configuration, asset, API, release, workflow, or product changes. Use whenever Codex modifies a repo that has docs-as-contract expectations, when a user says docs must stay in sync, before finalizing a feature/fix, or when reviewing a diff for stale README, roadmap, specs, changelog, agent instructions, or handoff notes.

owasp Bundle

Perform Rapid Developer-driven Threat Modeling (RaD-TM) on a software feature — a lightweight, six-stage method that turns a feature description, user story, design doc, API spec, or source/infrastructure code into a complete threat model: data-flow model, trust boundaries, a threat list, control mapping, severity evaluation, and a ready-to-file security backlog. Use this skill whenever the user wants to threat model a feature or system, run a security design review, identify security threats and controls, find attack surface or trust boundaries, build or update a threat model, or generate security backlog items for something they are designing or building — even if they never say "RaD-TM", "STRIDE", or "threat model" by name, and even if they just describe a feature and ask "what could go wrong here, security-wise?". Especially relevant for shift-left, feature-level reviews. Threat identification is grounded in expert-curated Threat Templates so output stays consistent and the model never invents threats.

pedroknigge Bundle

v1.0.1. Fixture Agent Skill with a runnable script and no tests. Use to validate native Antigravity (agy) skill discovery.

tingwei628twdev Skill

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out, 幫我規劃功能, 寫需求文件, 規劃這個專案, 建立 PRD.

tingwei628twdev Skill

使用 Ralph 自動化 agent loop 模式來實作功能、建構專案或執行多步驟開發任務。當使用者說「用 ralph 實作」、「幫我建一個 ralph loop」、「自動跑 claude code 完成任務」、「建立 PRD 讓 agent 自動做」、「我想用 ralph 模式」、「設定 ralph 跑這個專案」時，一定要使用此 skill。也適用於任何需要把大型任務拆成多個 user stories、讓 Claude Code 或 Amp 反覆迭代執行直到完成的場景。即使使用者只說「幫我自動實作這個功能」或「讓 AI 自己把這個做完」，也應該觸發此 skill。

tosin2013 Bundle

Determine whether an AI coding agent is authorized to create, change, maintain, or retire something in this repository, and when it must stop. Use before implementing a feature, refactoring, upgrading a dependency, deleting code, acting on a TODO or discovery, or when asked whether work is authorized, in scope, or complete.

varnan-tech Bundle

Query Google Trends data via SerpApi for search trend analysis, keyword discovery, topic comparison, and geographic interest patterns. Use when users need trending keyword data, want to compare search terms, or need Google Trends insights for content planning.

vava-nessa Skill

Find New Providers — Discovery Skill

homayoun-asghari Skill

Turn a raw idea in IDEA.md into a PRD, an architecture, a verify script, CI, and a Kanban of vertical slices. Asks at most five questions first. Run this once, at the start of a project.

hubwu42 Skill

一句话说明这个 skill 做什么、Claude/agent 何时该用它（discovery 阶段只读这两行，务必精准）。

infragate Bundle

Capify an existing project. Scans the repo for already-installed MCP servers, skills, rules, hooks, sub-agents, and plugins (across .claude, .cursor, .codex, .gemini, etc.), consolidates them into shared top-level directories (skills/, rules/, hooks/), and synthesizes a sound capabilities.yaml from the inventory. Use whenever the user says "bootstrap capa", "capify this project", "onboard capa onto an existing repo", "inventory my agent setup", or asks how to turn an ad-hoc Claude/Cursor/Codex configuration into a capabilities file. Use even when the user only mentions one provider — discovery should still sweep all of them.

marko-js Bundle

Build the monthly Marko newsletter for the website from the marko-js "Roadmap" project board. Use when asked to write, draft, or update the newsletter for a given month (e.g. "write the July newsletter", "draft this month's newsletter").

marko-js Bundle

Reconcile the marko-js "Roadmap" project board against the pull requests actually merged in a month, and fill in the items and fields that are missing. Use before writing a newsletter, or when asked to check, audit, or catch up the project board for a month.

martynjsimpson Bundle

Explains and enforces the project-agnostic Request -> Work item -> Active release -> Done work-management model, including the manifest schema at docs/work/project.yml, the exact file formats for requests.md / backlog.yml / active-release.md, all valid statuses, and the configuration-resolution protocol every command follows. Use when someone asks how the work management model works, what a status means, whether something is blocked or deferred, what fields a request or work item takes, how to configure project.yml, what belongs in the manifest versus a command, or when validating that requests.md and backlog.yml conform to the model. Also use before hand-editing any of the work files, so the edit matches the required structure rather than drifting from it.

martynjsimpson Skill

Quickly capture a bug, feature idea, improvement, annoyance, tech-debt item, or security concern into the project's requests.md intake file, without starting a planning session. Use when someone says "note this down", "log this", "capture this", "add this to the backlog", "remember this for later", "I noticed a bug", "I had an idea", "can you add a request for", "flag this for later", or otherwise mentions something in passing that they want recorded rather than fixed now. Also use proactively at the end of a session when a real defect or improvement was noticed but deliberately left unfixed. Works on any project set up with the work-management model; discovers the project from its manifest rather than assuming a location. Do NOT use for refining requests, proposing release scope, or closing out a release — those are the /work-plan command.

maxanatsko Skill

Use when: copying, cloning, duplicating, or bulk-copying Power BI Dataflow Gen1 artifacts between workspaces while preserving Gen1. Uses Azure CLI, PowerShell, and the Power BI REST export/import APIs. Covers Gen1 discovery, exclusions, target conflict checks, export cleanup, multipart model.json upload, import polling, and Gen1 verification. Do not use for Gen1-to-Gen2 migration or saveAsNativeArtifact. Triggers: copy Gen1 dataflow, clone Gen1 dataflow, move Gen1 dataflow between workspaces, export import dataflow JSON, Dataflow Gen1 copy with az cli.

media-io Bundle

Generate images and videos through the currently installed Media.io CLI. Use for text-to-image, image-to-image, text-to-video, image-to-video, reference-to-video and published workflows. Select the model from the bundled static catalog (`references/model-catalog.md`), which is generated from the production registry; only fall back to `mediaio model list` on the triggers listed in the discovery guardrail. Copy every `job_type` byte for byte — some contain a literal space, and display names often do not match the identifier. Effects may be used only when their parameters have been independently verified because the current CLI exposes `effect list` but not `effect get`. Always confirm the parameter schema with `model get` before submission. Submitting spends the user's credits, but the CLI stays quiet about the amount unless asked; surface the cost with `--show-credit`, and get an explicit approval first, only when the user is cost-sensitive or has raised credits, price or balance. When the balance runs short,