Product & Planning

jayden-dang Bundle

Use when a design, planning, or implementation question turns on external facts — how a library or API actually behaves, what a standard, spec, or RFC says, platform limits, version differences — rather than opinion, or when the user asks to look into or investigate such a fact and write it up with citations. Do not use when "looks" means visual or UI variants or screen mockups — that is run-spike, not a cited note; or for investigating a paper plus experimental variants, training runs, or candidate ranking.

jayden-dang Bundle

Use when a mid-execution discovery invalidates an already-approved plan — "the plan is wrong," a re-plan is needed, scope changed mid-flight, or a divergence surfaces during build-in-waves or test-first that the current task can't absorb. Produces a blast-radius classification of the lowest invalidated artifact plus a re-entry decision or change proposal, never a silent rewrite. Not for a post-ship in-scope tweak (amend-feature), broken code against a still-valid spec (root-cause), or the mechanical reconciliation that runs after the decision (realign-spec).

jayden-dang Bundle

Use when a design question needs a runnable answer — the user wants to run-spike, spike, or mock up a state model or piece of logic to feel out whether it holds up, or to see what a screen could look like, before committing to a real implementation.

sky-cube Skill

撰写产品需求文档的标准结构与规范。当用户故事与验收标准明确后,需要输出正式 PRD 文档时使用。

sky-cube Skill

使用 Figma MCP 工具生成/落地设计稿的规范。当需要在 Figma 中从线框、PRD 或截图生成设计稿时使用。

halojerry Bundle

飞书 OKR：管理目标与关键结果。查看和编辑 OKR 周期、目标、关键结果、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。不负责：待办任务管理（lark-task）、日程/会议安排（lark-calendar）、绩效评估

halojerry Bundle

以顶刊/顶会审稿人标准严格判断 idea 是否真有突破，还是常规组合、套壳、概念堆叠、缺乏理论深度或实验支撑。当用户问"这个 idea 行不行/够不够创新/帮我挑刺"，或 m03 产出 idea 后必须使用。先盲后明立标准、八维度加权打分、五视角对抗、反谄媚硬协议，给判决 + Revision Roadmap，引导回 m03。

full-stack-skills Bundle

From PRD interface/screen descriptions, output ASCII UI (for PRD supplement), Stitch-executable prompt (for stitch-skills), and Pencil-executable plan (for pencil-skills). Does not call Stitch or Pencil MCP.

ariadoss Skill

Lightweight web fuzzing via ffuf — directory discovery, parameter testing, subdomain enumeration.

ariadoss Skill

Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate in a week", "rapid prototype", "test with users", "de-risk before building", "GV sprint", "prototype testing", or "design workshop". Also trigger when a team needs to make a critical product decision quickly, resolve stakeholder disagreements, or test risky ideas before investing in development. Covers mapping, sketching, deciding, prototyping, and testing. For ongoing experimentation, see lean-startup. For customer job analysis, see jobs-to-be-done.

ariadoss Skill

When the user wants to create, audit, or optimize sitemap.xml. Also use when the user mentions "sitemap," "sitemap.xml," "sitemap index," "lastmod," "changefreq," "priority," "URL discovery," "URL discovery for search engines," "single source of truth," "URL config," "unify sitemap IndexNow," or "reduce duplicate maintenance." For IndexNow, use indexnow.

mn755 Skill

Coordinate brand-guideline, internal-communications, announcement, and stakeholder-message work through Mission Control with tone, audience, and evidence constraints.

arasz Bundle

Use when the user wants to start, continue, or finish a backlog task — "/task <id>", "start task X", "work on the next task", "finish this task". Runs it end-to-end as a token-tracked unit of work with low/high effort, plan packaging with mandatory integration package, MoE panels for high-effort, and automated task-ID derivation ({repo-alias}-{key}). Delegates planning/review to high-reasoning models and implementation to persona-routed agents. Project specifics from .ai-badger/config.json; source-control and PR behaviour from config-gated extensions.

arasz Bundle

Use when a repository should be set up with ai-badger — "welcome-ai-badger", "scaffold this project", "add agent instructions here", "onboard this repo" — whether it is new or already has agent files. Detects stacks, writes .ai-badger/, and generates each configured agent's discovery file.

arjun988 Bundle

Art direction for open world and sandbox games in Blender with biome landmarks, traversable scale, and discovery props.

hack23 Skill

Comprehensive guide for MCP (Model Context Protocol) server setup, transport protocols, configuration validation, lifecycle management, tool discovery, and error handling patterns

hack23 Skill

Product management patterns including roadmap planning, feature prioritization, user feedback, and agile practices

ortus-boxlang Skill

Use this skill when designing or debugging Application.bx behavior: app discovery and nesting, multi-application isolation, lifecycle events, pseudo-constructor settings, session management, mappings/javaSettings resolution, and app-scoped schedulers/watchers via this.schedulers and this.watchers.

zebbern Bundle

Perform web fuzzing for content discovery, parameter enumeration, and virtual host detection using ffuf. Use when directory or file discovery is needed, when fuzzing parameters for hidden endpoints, when enumerating virtual hosts, or when brute-forcing authentication.

zebbern Bundle

Discover hidden HTTP parameters in web applications that could reveal hidden functionality or vulnerabilities. Use when testing APIs, when looking for hidden parameters like admin or debug, or when the user mentions parameter discovery.

zebbern Bundle

Discovers URLs, endpoints, and paths from web applications using katana, gospider, and gau. Use when needing to enumerate application endpoints, find hidden paths, gather historical URLs, or map web application structure during reconnaissance.

jayden-dang Bundle

Produces a path-verified learning tour and local ledger. Run with /tour-system.

jayden-dang Bundle

Use when discovery is complete and a tier-1 or tier-2 change needs its requirements written — the user stories and EARS acceptance criteria in requirements.md that every later task, test, and commit cites by ID. After frame-change, before any design or code.

jayden-dang Bundle

Turns a short, unclear ask into one paste-ready prompt block — targets, boundaries, evidence, open questions, and a done signal — for a fresh session to pick up. Run it with /forge-prompt.

jayden-dang Bundle

Use at the very start of the idea-to-ship chain — when the user wants to add, build, or change a feature, behavior, or component, or to start a new project, and the asked-for behavior has no spec yet. Produces an agreed shape and a spoken ceremony tier. Triggers on "let's add…", "can we build…", "I'm thinking about…", "we should support…" before implementation has begun.

jayden-dang Bundle

Use when a domain term needs defining, a glossary term is being used inconsistently or fuzzily, a hard-to-reverse decision needs an ADR, or existing ADRs need auditing, pruning, or archiving — produces glossary updates and a classified docs/adr tree (keep, archive, or drop a dead rejection). Also runs as a side-effect sub-skill when an interview or design skill calls for glossary and ADR upkeep.

jayden-dang Bundle

Use when a project's milestones need planning, sequencing, replanning, or ANY edit to an existing roadmap — produces or revises docs/roadmap/INDEX.md, the milestone intent registry carrying stable MILE-N and ROAD-N IDs that later feature specs bind to. Triggers on "plan the milestones", "build a roadmap", "what order should we build this in", "break this project into milestones", a frame-change that decomposed work into independent sub-features, and equally on any edit to a roadmap that already exists — "update the roadmap", "drop this item", "we're not doing X anymore", "reorder the milestones", "move sharing ahead of search", "reword this outcome", "commit to the next milestone", "this milestone shipped", or any request touching docs/roadmap/INDEX.md. Not for one feature's requirements (specify-behavior), and not for reporting where the plan currently stands (refresh-roadmap-status).

jayden-dang Bundle

Builds deep foundational knowledge of any codebase or technical subject — dual-axis curriculum, slow and deep — without shipping a product decision. Run with /deepen-codebase.

jayden-dang Bundle

Works a design or framing problem to closure with multi-round breakdown, foundation-to-feature teaching, disk artifacts, and a carry-back brief for the main window — without enacting the decision. Run with /work-the-problem.

jayden-dang Bundle

Use when a project needs a light roadmap — updates the project note with 3–7 milestones and atomic actions only on the current milestone.

jayden-dang Bundle

Use to interview or grill the user before building an underspecified plan, design, or feature idea, including when another skill calls for an interview. Produces a confirmed close package of decisions, constraints, success, boundaries, and spine touch — plus owned unknowns, accepted risks, and operability when the production-coverage gate is on.

jayden-dang Bundle

Companion beside a technical discussion — in the user's language or English — that builds a mental model you can reason with, takes a stance, and produces a paste-back reply. Run with /interpret-session.

jayden-dang Bundle

Reports where a multi-milestone plan actually stands and what to do next, derived fresh from the roadmap, the specs, and git — never from a stored status file. Run it with /refresh-roadmap-status.

poorvith-mp Bundle

Submit to startup, SaaS, AI and MCP directories for backlinks and discovery, tracked. Use when listing products on SaaSHub, AlternativeTo, or free directories.

markbaindesign Skill

Manage project todos from Claude's output. Use when the user says "create tasks", "add to todo", "update the todo list", "push to asana", "what's next", or "add these to the backlog". Writes prioritised tasks to TODO.md in the current project and optionally syncs to Asana. Also use to read and report what's next when the user asks.

thiennc-tesoglobal Bundle

Build direct Bluetooth Low Energy central or peripheral workflows with Core Bluetooth, including GATT discovery, state restoration, MTU sizing, and background modes. Use for BLE scanning, peripheral connection, characteristic reads/writes/notifications, or peripheral advertisement.