Product & Planning

timzaak Skill

Validate draft PRD, published PRD baseline, and user stories for quality and consistency.

timzaak Skill

After implementation and acceptance, summarize the draft PRD against delivered facts, then revise the existing formal PRD.

fabioc-aloha Skill

Reviews an AI-related decision for stakeholder impact, privacy, responsibility, transparency, contestability, and reversibility.

brennanjcollins Skill

Translate user needs into buyer economics using Brennan Collins' 'Two Languages, One Bridge' methodology — Bridge Madlib story mapping, the 'What Would Get Them Fired?' stakeholder test, and quantified pitch transformation. Catches user-only language, missing buyer economics, and unquantified business impact.

brennanjcollins Bundle

Decode the hidden incentive map of every stakeholder in your room before you walk in. Coach the PM through the three archetypes (Risk Shield, Credit Catcher, Tribal Guardian), the three diagnostic questions (fired/promoted/validated), and the Adversarial Stakeholder Prompt — an AI devil's-advocate workflow that stress-tests your stakeholder read the night before a high-stakes pitch, roadmap review, or alignment meeting. Companion to the meeting before the meeting.

brennanjcollins Skill

Transform competent-but-forgettable pitches into compelling stories that get to 'yes' — using Brennan Collins' 3-Act Structure (Human Stakes → Scale → Solution), stakeholder-specific adaptation via the 'What Would Get Them Fired?' test, and the Bridge Madlib. Catches when PMs lead with logic instead of stakes.

brennanjcollins Skill

Practice high-stakes conversations with realistic pushback before the real thing — simulating board presentations, skip-level meetings, cross-functional negotiations, and more using Brennan Collins' Earned Confidence framework (Competence + Confidence = Influence). Throws curveballs from six stakeholder archetypes, then coaches on confidence signals, warmth-power balance, and recovery.

brennanjcollins Bundle

Coach a PM to respond to stakeholder feature requests using sincere curiosity, deliver a compelling reframe with the Mad Lib template, and position transparent tradeoffs using Stakeholder Judo (Stakeholder Judo) — turning stakeholder tension into strategic partnership.

brennanjcollins Skill

Evaluate a PM's response to a stakeholder request and coach them from order-taker behavior to outcome ownership — with behavioral markers, rewritten responses, and a 24-72 hour investigation plan they can start immediately.

connorgriffin Bundle

Implement a piece of work based on a PRD or set of issues.

connorgriffin Bundle

Adversarially review a plan, work order, spec, or agent brief before anything gets built. Use when the user wants a plan reviewed, stress-tested, audited, or countersigned, says "plan review" or "poke holes in this plan", or wants a pre-build check on an issue/brief/PRD.

connorgriffin Bundle

Use the codebase knowledge graph for structural code queries, trace call paths and dependencies, inspect architecture, assess change impact, or activate the bundled Claude Code discovery hooks.

ilamanov Skill

Runs a project's scheduled health checks in order — syncing the main worktree's main branch with origin, refreshing installed skills, then triaging the Linear backlog to pick and ship a next ticket. Use when the user asks to run the project health check, do the scheduled/periodic project checks, run routine project maintenance, or when this is invoked as a recurring scheduled agent. The Linear team (name or key) to triage is provided when the skill is invoked; an optional date cutoff for ignoring stale tickets may also be provided.

iwanalq Bundle

飞书 OKR：管理目标与关键结果。查看和编辑 OKR 周期、目标（Objective）、关键结果（Key Result）、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。

iwanalq Skill

统一处理网页应用的生成、编辑，以及围绕已生成产物的问答。既负责把自然语言需求端到端转成可运行、可预览、可交付的网页应用产物，也负责在用户追问产物时基于真实产物作答。当用户要生成网站、H5、网页应用、管理后台、数据看板时使用。当用户要编辑已有网页应用、做功能新增、页面调整或 Bug 修复时使用。当用户提供 PRD、文档、截图或素材包并要求产出可预览网页应用时使用。当用户针对已生成的网页应用，要求总结或解读网页内容、查看或分析源码、解释或排查运行报错、查询访问量/用户量/数据报表/发布状态等运营信息时同样使用。

idkwhatimd0ing Bundle

Orchestrate a new project from idea to running scaffold by chaining `domain-to-spec`, `scaffold-frontend`, and optional `scaffold-backend`. Use this skill when the user wants a one-shot setup, full-stack bootstrap, empty-repo starter, or guided path from rough idea to `AGENTS.md`, `PRD.md`, `client/`, and optionally `server/`.

idkwhatimd0ing Bundle

Turn a non-coder's domain expertise into `AGENTS.md` and `PRD.md` at the repo root before scaffolding. Use this skill first for new projects, idea-to-spec work, PRD creation, app planning, or when the user describes a profession, workflow, constraint, or outcome and needs a buildable software blueprint.

idkwhatimd0ing Bundle

Create a PRD-driven FastAPI backend in `server/` from repo-root `AGENTS.md` and `PRD.md`. Use this skill after frontend scaffolding only when `PRD.md` says `Backend Needed?` is Yes, especially for API routes, Pydantic models, health checks, optional Supabase wiring, and type-safe placeholder data.

idkwhatimd0ing Bundle

Create a PRD-driven Next.js frontend in `client/` from repo-root `AGENTS.md` and `PRD.md`. Use this skill after `domain-to-spec` when the user wants the initial UI scaffold, pages, navigation, types, and optional API client generated from the confirmed PRD.

idkwhatimd0ing Bundle

Turn a PRD, product idea, app description, screenshot brief, or rough UI concept into a high-signal Vercel v0 prompt. Use this skill whenever the user wants a v0 prompt, landing page prompt, app UI generation prompt, visual direction, shadcn/Magic UI/Aceternity guidance, or a more distinctive interface than generic AI output.

samzong Bundle

GitHub issue management toolkit for project maintainers and contributors. Four modes: (1) scan — find contributable issues ranked P0-P5, (2) reply — draft and post concise maintainer responses to specific issues, (3) triage — classify issues and assign/remove labels, (4) analyze — deep root-cause or feature-design analysis saved to markdown. Use when: managing GitHub issues, finding contribution opportunities, replying to issues, triaging issues, labeling issues, analyzing bugs, designing features from issues, "what can I work on", "reply to this issue", "triage issues", "analyze this bug", "label these issues", "find easy issues", "show me contributable issues", issue cleanup, issue management, project maintenance, open source contribution discovery. Do not use for: PR review, code review, issue creation from scratch, or general GitHub operations unrelated to issue management.

andvl1 Skill

Go microservices — gRPC, REST, cloud-native patterns, service discovery, circuit breakers, observability, health checks, graceful shutdown.

bex-co Bundle

Autonomously work a `.pm` workstream to completion — pick the next pending milestone, implement every task end to end, /ship it, then move to the next until none remain. Use when the user asks to "loop", drain, or work through a whole workstream's backlog (e.g. `/loop-worker w1`). Sequential, not interval-based; for a timed poll use /loop.

bex-co Bundle

Analyze and decompose a product topic into a text-only proposal for the repository's .pm board. Use when the user wants to pressure-test scope, size milestones, identify dependencies, or prepare exact PM board commands without writing board files.

codagent-ai Skill

Drives interactive requirement discovery to produce spec files. Use when the user says "spec this", "write specs", "create specs", or "run the spec skill".

dasein108 Skill

Use to produce and publish a chosen Slope Studio backlog bet, then bind the run to the marketing journal so it can be measured later.

dasein108 Skill

Use when deciding what short video to make next for a Slope Studio channel: generate falsifiable viral bets and persist them to the marketing backlog.

thevibethinker Bundle

Generate gated, analytics-enabled founder memo pages for investors, customers, and vendors on zo.space. Use when creating or managing memo rooms from Google Docs, Markdown, text, PDFs, data, or images with strict source fidelity, stakeholder access controls, replay analytics, central reusable content blocks, and private admin/CLI operations.

ui5 Bundle

Fix Control renderer issues that UI5 linter reports but cannot auto-fix. Use this skill when linter outputs these rules: - `no-deprecated-control-renderer-declaration` - For missing renderer declaration, string-based renderer declaration, implicit renderer auto-discovery (removed in modern UI5) - `no-deprecated-api` - For missing apiVersion:2 in renderer objects, missing IconPool import when using oRm.icon(), deprecated rerender() override. NOTE: For Library.init() apiVersion errors, use fix-library-init instead. - `ui5-class-declaration` - For non-static renderer property in ES6 classes Trigger on: "missing a renderer declaration", "Deprecated declaration of renderer", "deprecated renderer", "apiVersion" (in renderer context), "IconPool", "rerender", "renderer must be a static property" Converts legacy renderer patterns to modern apiVersion: 2 format with proper module imports.

lglucas Skill

Create a 14–20 sprint roadmap in docs/SPRINTS.md plus individual sprint files, starting with Sprint -1 (consolidating the approved prototype into a design system). Runs at WIZARD stage 4.4, after BP v0.0.2, the approved prototype direction, the Product Brief, and the Technical Plan all exist. Use when the user asks "qual a ordem das coisas?", "quanto tempo isso leva?", "o que eu faço primeiro?", or runs /sprint-plan.

lglucas Skill

Check every Business Plan change for downstream impact before accepting it — price moves projections, ARPU, LTV and positioning; persona moves GTM, UX and MVP scope; stack moves costs, roadmap and risks. Runs at WIZARD stage 2.8 when turning BP v0.0.1 into v0.0.2, and any time the BP is edited after approval. Use when the user says "mudei o preço", "troquei a persona", "cortei o escopo", "e se eu cobrar por assento?", or when `grow-sustainably` / `multi-ai-review` flag a pricing or packaging change.

linegel Bundle

Use when designing a product change before building it — deciding whether it needs a BRD, PRD, UX note/XDS, or SD/SDD; authoring or amending those artifacts; writing user stories; designing journeys and interactions; choosing controls, states, failures, and recovery; reviewing the result; or handing product decisions to another stateless worker. This skill owns a CONDITIONAL DECISION CHAIN, the boundary between PRODUCT REQUIREMENT AUTHORITY and EXPERIENCE REALIZATION, the PRODUCT-STORY and INTERACTION-SCENARIO grammars, Data · Time · Path · Frame state prompts, durable repository/PR handoff, rendered review, and a PROPORTIONALITY rule that caps process cost. It is a thinking aid, not a governance system — it produces no statuses, hashes, approval records, artifact quotas, or merge gates.

lync-cyber Bundle

架构设计 — 模块划分、接口定义、数据模型、系统架构建模。当 PRD 完成、需要做架构风格选型、模块划分、接口契约或数据模型设计时使用此 skill。本 skill 不做需求分析（req-analysis）与 UI 设计（ui-design）。

lync-cyber Bundle

可选的设计深度澄清策略 — 对 PRD、Architecture 或 UI 设计沿决策依赖树逐分支穷尽收敛。默认关闭，经用户显式要求、项目偏好或阶段入口一次询问启用；启用后追问持续到全部分支解决且用户确认，普通信息缺口不触发。

lync-cyber Skill

需求分析 — 需求拆解、用户故事编写、验收标准定义。当用户提出新需求、需要编写 PRD、拆解功能点或定义优先级与验收标准时使用。

manager-dot-dev Bundle

Equips engineering managers with persuasion techniques and positioning strategies for getting things done without direct authority — produces tactical methods (Nemawashi, Decoy Pricing, Reverse Psychology, LMDTFY, Engineered Serendipity), conversation techniques for disarming resistance (Label the Concern, Get to "That's Right"), a headcount argument framework, and a three-level visibility/trust model. Use when the user says "how do I convince," "persuade," "get buy-in," "stakeholder management," "influence without authority," "get approval," "calibration," "nobody takes me seriously," "how do I get headcount," or "organizational politics." Do NOT use when the issue is the user's relationship with their own manager (use managing-up).