Product & Planning

stardustai Bundle

Generate high-coverage Chinese functional and business-flow test cases from PRDs, especially Web admin or platform PRDs. Use when Codex is asked to extract PRD text, design QA coverage, generate the fixed 7-column testcase table, export CSV/XLSX, validate testcase format, or optionally consult an external indexed PRD memory source without reading full historical archives.

stardustai Bundle

Discover and send a daily frontier technology brief for AI, LLMs, agents, memory systems, trustworthy AI, data-centric ML, enterprise/private AI, GitHub developer tools, autonomous driving, world models, and embodied intelligence. Use this skill whenever the user asks for daily tech discovery, frontier AI research scanning, OpenReview/arXiv/GitHub trend monitoring, or sending a concise technical brief to a DingTalk group.

janszewczyk Bundle

Defines the standard PRD (Product Requirements Document) and TDD (Technical Design Document) formats and the rules for mapping document content to specialist agents. Use when writing, reviewing, or parsing a PRD/TDD, breaking a feature spec into agent tasks, or orchestrating the spec-driven development (SDD) flow — including from the product-owner agent.

darkroomengineering Skill

Clarify a vague scope through interview, then compile it into a PRD. Triggers "help me figure out", "define requirements", "PRD", "product spec", "feature spec".

devcxl Bundle

从固定点（commit、branch、tag 或 merge-base）开始，沿两条轴线审查变更——规范（代码是否遵循仓库文档化的编码规范？）和规格（代码是否与原始 issue/PRD 的要求一致？）。两条审查线在并行子 agent 中运行，并以并排方式报告结果。当用户想审查一个分支、PR、进行中的变更，或要求"从 X 开始审查"时使用。

cspulse Bundle

Maps the people who decide an account's outcome by what they can do to it, not by their job titles. Trigger whenever the user says "stakeholder map", "who are the stakeholders", "relationship map", "who do I need to know", "who actually decides", "who signs", "map the account", "we are single-threaded", "my champion left", or asks who to call about a renewal. Also trigger when an account has gone quiet, when a new executive has arrived on the customer side, or before any first meeting with an inherited account. It sorts people by influence on the outcome rather than seniority, flags who has never actually been met, tests for single-threading, and tracks who is new, who has gone, and who used to respond and stopped. Runs on whatever the user knows and marks every gap as a gap.

cspulse Bundle

Turns customer noise into something the product team will actually act on: the job to be done rather than the requested feature, how many accounts have it, what it is worth, and what happens if nothing changes. Trigger whenever the user says "product feedback", "feature request", "the customer wants", "raise this with product", "log this request", "they are asking for", "submit this to the roadmap", "product gap", "how do I get this built", or forwards a customer request expecting it to reach engineering. Also trigger when the user asks what happened to a request they raised, or says product ignores their input. It separates a request from a bug, a gap and a misunderstanding, refuses to inflate the revenue at stake, and closes the loop back to the customer including on a no. Use internal-escalation when the ask is urgent attention rather than roadmap consideration.

cspulse Bundle

Prepares fifteen minutes with a senior person on the customer side who has no context, did not ask for the meeting, and will leave early. Trigger whenever the user says "exec conversation", "meeting their CFO", "meeting the VP", "C-level meeting", "executive sponsor meeting", "I have fifteen minutes with", "talking to my champion's boss", "exec sponsor", "senior stakeholder meeting", "how do I talk to an executive", or names a title two or more levels above their usual contact. Also trigger when a new executive has arrived on the customer side and is reviewing what their predecessor bought. It establishes why the meeting exists, what the executive is measured on, the first sentence, the single ask, the two questions worth their time, how to protect the champion, and the five-line follow-up. Use business-review when the meeting is a QBR, and hard-conversation when the point of the meeting is bad news.

cspulse Bundle

Scripts the customer conversation you are putting off: a price increase, a feature you will not build, a commitment you missed, or a failure that cost them money. Trigger whenever the user says "hard conversation", "difficult conversation", "how do I tell them", "I have to tell the customer", "price increase", "raising their price", "we are not building", "roadmap no", "we missed the deadline", "we slipped", "the outage", "how do I break this to", "they are going to be angry", "I have been putting this off", or describes bad news they owe a customer. Also trigger when they ask you to soften a message that is honestly bad. It works out what is true and what you can offer before a word is said, writes the opening two sentences, sets the concession ladder and the walk-away in advance, and drafts the written record for afterwards. Use email-critic once the record is drafted, and exec-conversation when the conversation has escalated above your contact.

cspulse Bundle

Gets your own company to act, with the ask and the evidence shaped for the people you are asking rather than for you. Trigger whenever the user says "internal escalation", "escalate internally", "I need engineering to look at this", "get leadership involved", "how do I get this prioritised", "nobody is picking this up", "I need an exception", "raise this with my manager", "who do I go to", or describes needing something from another team on a deadline. It works out who can actually decide, states a specific ask rather than a request for attention, refuses to inflate severity, and plans the follow-through. Use escalation when the customer is the one escalating and the first four hours are customer-facing, and product-feedback when the ask is roadmap consideration rather than action now.

dariopalminio Skill

Orquestador del pipeline completo de ProjectSpecFactory. Ejecuta las tres fases en secuencia (project-begin → project-discovery → project-planning) en una sola sesión interactiva, con gates de revisión entre etapas para asegurar que cada documento quede en Estado: Ready antes de continuar.

dariopalminio Bundle

Produce project-plan.md (paso 3 de ProjectSpecFactory) delegando la generación del backlog al agente project-architect. Usar para planificar el proyecto a partir de project.md. Invocar también cuando el usuario mencione "planificación del proyecto", "plan del proyecto", "project-planning" o equivalentes.

dariopalminio Bundle

Produce project.md (paso 2 de ProjectSpecFactory) delegando discovery y requisitos a agentes especializados. Usar a partir de project-intent.md para iniciar la fase de discovery. Invocar para "discovery del proyecto", "especificación de requisitos" o "project-discovery".

rockclaver Bundle

Write a PRD grounded in the current codebase — reuse inventory, user stories, module design, testing decisions — optionally filed as a GitHub issue. Use when the user wants a PRD, feature spec, requirements doc, or feature planning.

rockclaver Skill

Turns a PRD into a phased implementation plan using tracer-bullet vertical slices, saved to ./plans/. Use when the user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".

stephenrogan Bundle

Builds a 30/60/90 onboarding and ramp plan with learning path, stakeholder map, early wins, role expectations, check-ins, and risk signals. Use for new hires, promoted managers, internal transfers, or leaders entering a new scope.

stephenrogan Bundle

Builds a stakeholder prewire plan with influence map, likely objections, conversation sequence, audience-specific framing, decision asks, and alignment tracker. Use before cross-functional proposals, executive decisions, process changes, or politically sensitive initiatives.

stephenrogan Bundle

Converts agent failures, user corrections, eval misses, review notes, and workflow friction into a prioritized improvement backlog. Use when improving agent skills, prompts, tools, memory, evals, or operating procedures over time.

yamcodes Skill

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

yamcodes Bundle

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `.agent/docs/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` - or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

coleam00 Skill

Interactive, problem-first PRD generator — interviews the user to surface the thesis (the problem, and WHY build it) and a falsifiable hypothesis, then writes a focused PRODUCT-level PRD (problem · evidence · hypothesis · users · MVP · success metrics · non-goals · open questions). Use at the start of a greenfield effort to discuss the product. A PRD is INTENT (what/why), never engineering decisions (how) — those are the `plan-architecture` skill's spec.

coleam00 Skill

Interactively explore HOW to approach an intent (a PRD, epic, brief, or free-form idea) and decide the high-level architecture — the approach, stack, libraries, data shape, and risks the intent left open. A working session with a CTO/staff-engineer advisor that asks questions, proposes 2–3 options with trade-offs, recommends a direction with reasoning, and flags what to de-risk with a spike. Produces a high-level architecture decision doc — a separate page linked to the epic in your tracker (Confluence/Jira), or folded into the PRD/epic, or a standalone doc — NOT a task-by-task implementation plan (that comes later, per ticket, with piv-plan-implementation).

coleam00 Bundle

Take a PRD and build a dark factory around it - a repository that takes work in as an issue and ships validated code out with nobody at the keyboard - one component at a time, into the user's actual repo. Covers the five components in construction order - the guidance layer, the validation harness, the workflow-driven repo, deployment, and the trigger that makes it autonomous - and is agnostic about which coding agent runs underneath (Claude Code, Codex, Archon, the Agent SDK, Cline, Goose, Amp, Pi). It encodes the AI coding process the user already runs rather than replacing it. Requires a PRD as input and deliberately does not write one. Use when the user wants to build a dark factory, an autonomous or self-driving repository, a software factory, an agent that ships its own code, an unattended or overnight coding loop, or asks how to get to level 4 or level 5 of AI coding autonomy; and when they mention dark factory, lights-out coding, autonomous PRs, or a repo that maintains itself.

coleam00 Skill

Decomposes a PRD into well-formed, engineer-ready tickets — Jira issues or GitHub issues. Use after a PRD exists, to turn its phases and user stories into a structured backlog. Works for a new codebase (MVP scope) or an existing one (epic scope).

coleam00 Skill

Set up your project's global rules, a lean and well-structured root CLAUDE.md (plus a starter .claude/), following the course methodology. Greenfield: pass your PRD and/or architecture-spec path and it derives rules from your engineering decisions (a PRD alone is product context). Brownfield: leave it blank to derive from your primed codebase (run /prime-codebase first), or pass a codebase-analysis doc for a large repo. Use when initializing or re-deriving the AI Layer's rules, onboarding a codebase, or replacing a generic /init output. The customizable replacement for /init.

jamestexas Skill

Research-first feature implementation workflow. Use when building new features or net-new code that should follow existing codebase patterns. Enforces pattern discovery before coding; dispatches to repo-specific standards skills for convention checks.

jabrena Bundle

Facilitates conversational discovery to create Architectural Decision Records (ADRs) for functional requirements covering CLI, REST/HTTP APIs, or both. Use when the user wants to document command-line or HTTP service architecture, capture functional requirements, create ADRs for CLI or API projects, or design interfaces with documented decisions. Part of the skills-for-java project

jabrena Bundle

Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable quality criteria. Part of the skills-for-java project

dxos Bundle

Use when work spans multiple steps, phases, or sessions, when resuming a task started earlier, when the user asks for a plan/roadmap/progress tracking, or when they use the `/dxos:project` command (any verb — list, tasks, new, end, track, hydrate, resume). Covers the project registry, maintaining a durable TASKS.md + DESIGN.md per work-stream, and checkpointing/reloading project state across sessions and PRs.

yipng05-max Skill

企业战略制定工具（Corporate Strategy Maker）。当CEO或高管提出以下需求时触发： 制定战略、战略规划、战略诊断、战略审视、年度战略、三年规划、竞争策略、增长路径、 商业模式设计、战略迭代、战略执行方案、OKR制定、战略重点、业务方向选择。 适用场景：新公司战略制定、现有战略审视与迭代、特定战略议题深度分析、 年度战略复盘与更新、竞争应对策略、转型路径设计。 不适用：日常运营决策、单一产品功能需求、HR/财务等职能级决策（除非上升至战略级别）。

enthrium Skill

Write an executive summary for a senior stakeholder — runs only after manual approval

shafthq Bundle

Use when a SHAFT task needs a deterministic one-shot command, machine-readable output, offline discovery, or code generation from a persisted recording.

shafthq Skill

Canonical provider-neutral skill router and working contract. Use at the start of every task, on every host, in every main thread and delegate, before discovery, planning, edits, or answering.

shafthq Bundle

Use when translating verified SHAFT coverage, outcomes, defects, trends, and residual risk into business quality or release decisions.

b-m-capital-research Bundle

Design, inspect, create, update, and validate Hone skills, including Codex-native discovery through workspace .agents/skills and compatibility with legacy Hone runners.

grant-ge Bundle

OKR 制定辅导助手。用于公司、部门、团队或个人的 Objective 设定、Key Result 设计、KPI/指标选择、目标拆解和对齐检查。