Product & Planning

tjboudreaux Bundle

Audits publishability, optimizes listing surfaces, distributes agent skills across supported public registries and marketplaces, and tracks adoption metrics. Use when asked to market a skill, publish to skills.sh or LobeHub, prepare Claude plugin or curated-list submissions, optimize SKILL.md metadata, or track skill installs. Also use when looking for skill ASO, marketplace submission, or skill directory discovery. For product or SaaS marketing directories, see directory-submissions; for product launch campaigns, see launch.

tomaszstaniak Bundle

Framework based on April Dunford's "Sales Pitch". Use this skill whenever the user is discussing sales conversations, pitch decks, demos, buyer messaging, or stalled deals — even if they do not explicitly say "sales pitch," "positioning," or "Dunford." Triggers include: (1) structuring a B2B sales conversation that builds buyer confidence rather than pushing features, (2) developing a pitch narrative grounded in competitive positioning, (3) diagnosing why deals are stalling or ending in "no decision," (4) training sales teams on a consistent, repeatable pitch structure, (5) translating product positioning into a sales story, (6) creating pitch storyboards with cross-functional teams, (7) drafting a deck for a customer demo or first discovery call, (8) responding to "how are you different from X?", (9) rewriting cold outbound that is getting ignored, (10) preparing a champion to sell internally to their buying committee

tomaszstaniak Bundle

Product management framework based on Melissa Perri's "Escaping the Build Trap". Use this skill whenever the user is discussing product strategy, roadmap construction, product team maturity, or symptoms of feature-factory behavior — even if they do not explicitly say "build trap" or "outcome-driven." Triggers include: (1) diagnosing whether a team is stuck shipping features without measuring outcomes, (2) shifting from output-driven to outcome-driven product development, (3) evaluating product manager archetypes (Waiter, Project Manager, Mini-CEO, Strategic) or team maturity, (4) designing a strategy deployment cascade from vision to product initiatives to team-level options, (5) converting a feature roadmap into an outcome roadmap, (6) running a pre-mortem against a quarterly plan to detect build-trap patterns before committing, (7) coaching a PM who is acting as an order-taker for stakeholder requests, (8) writing the case for killing a low-adoption feature.

tomaszstaniak Bundle

Framework based on April Dunford's "Obviously Awesome" and "Sales Pitch". Use this skill whenever the user is discussing how to describe, frame, differentiate, sell, or talk about their product — even if they do not explicitly say "positioning," "pitch," or "messaging." Triggers include: (1) defining or evaluating product positioning using the five-component framework, (2) translating positioning into a compelling pitch for execs, boards, partners, or buyers, (3) choosing a market category strategy that shapes what you build and how you compete, (4) developing differentiated value claims, (5) diagnosing why your product story isn't landing with customers or stakeholders, (6) aligning teams around a shared positioning narrative and connecting it to roadmap priorities, (7) writing a launch announcement, website headline, or tagline, (8) deciding which features to highlight in marketing copy, demos, or sales decks, (9) responding when a buyer says "you sound like everyone else."

tomaszstaniak Bundle

Product discovery framework based on Teresa Torres' "Continuous Discovery Habits". Use this skill whenever the user is doing product discovery work — even if they do not explicitly say "OST," "Teresa Torres," or "discovery." Triggers include: (1) building, critiquing, or restructuring an opportunity solution tree, (2) identifying, organizing, or prioritizing customer opportunities, (3) designing assumption tests before committing to a feature, (4) writing or critiquing interview snapshots from customer conversations, (5) generating multiple solution candidates for an opportunity (especially with How Might We), (6) mapping a current-state customer experience or journey to surface unmet needs, (7) diagnosing why a product team is shipping without moving outcomes, (8) running a discovery pre-mortem before committing to a solution branch, (9) building or strengthening a weekly customer-interview habit, (10) connecting business outcomes to product outcomes to opportunities to solutions in a coherent tree.

uwe-schwarz Bundle

Estimate the replacement cost, engineering effort, calendar time, and market-rate value of a software project by analyzing a repository's size, architecture, complexity, and delivery maturity. Use when asked for a build-cost estimate, rebuild quote, delivery timeline, stakeholder-facing budget range, pricing sanity check, or ROI/value analysis for work produced by Claude, Codex, OpenCode, Crush, or another AI coding agent.

wangwenyao Bundle

Use when 需求逻辑调整、PRD变更、接口变更、数据库变更需要分析影响范围，或需要前后端技术同步、验证代码实现是否符合需求、实现偏差反馈产品经理，或提到：分析一下影响、前后端对齐、检查实现、技术方案评估、分配任务、分发任务、反馈产品、方案调整、生成接口文档、OpenAPI规格、接口定义、生成数据库脚本、DML脚本、SQL脚本、建表语句。

wangwenyao Bundle

Use when 用户需要写PRD、写需求文档、需求评审、功能设计、产品规划、用户故事，或提到：帮我梳理需求、整理功能点、写产品方案、这个功能怎么设计、帮我想想产品逻辑、产品需求文档、生成线框图、页面原型、设计页面结构、处理偏差反馈、技术反馈、偏差决策、接受技术建议。

mfraunhofer Bundle

Project-management chat skill that coordinates parallel spawn chats through a shared PM inbox. The PM chat never does the work, it maintains a state file (`<workspace>/.scratch/pm-state.md`), keeps the overview, and hands work out as dispatch prompts written to disk; spawn chats do the actual work and report back through the inbox. Measurable facts (branch, worktrees, inbox backlog, file size, board state) are stamped by bundled scripts instead of written by hand. Use when the user says "box <project>", a bare "box", "/pm", "status [project]", "recap", "what's next?", "where are we on [project]?", "pm status", or pastes a report from a spawn chat. NOT for deep issue thinking, code edits, research, TDD, or reviews (all spawn-chat work).

mfraunhofer Bundle

Lightweight pre-planning skill that turns a fuzzy idea into a structured Feature Pitch (pitch.md) before any deeper planning or PRD step runs. Asks 6 questions one at a time with adaptive multiple-choice anchors, then writes the pitch file. Use when the user says "/pitch", "I have an idea for", "let's pitch this", "new feature idea", "I want to build", or whenever a software idea needs to be shaped before a domain/spec review. NOT for full PRDs, abstract strategy, or ideas that already have a detailed spec.

mininglamp-oss Skill

Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.

mrveiss Skill

After completing a batch fix or implementation, audit adjacent files for the same issue and file GitHub discovery issues for each gap found. Use after any batch implementation, bug fix, or remediation campaign.

dmythro Bundle

GitHub Projects (v2) setup and management via gh CLI + GraphQL: organize a repo's issues into epics with native sub-issues, drive a board Status flow (Todo -> In Progress -> Done), set Project Priority, classify with native issue Types (Task/Bug/Feature) instead of labels, scope work with milestones (incl. resolving "current milestone"), and maintain an Epic + Upcoming roadmap. Use when setting up or managing a GitHub Project/roadmap, creating an epic with issues, adding or moving issues between epics, picking up or closing work on the board, (re)prioritizing, setting issue types, creating or closing milestones, enabling project workflows, or configuring gh project read-only allowlists. Not for PR workflows (git-pr), CI/CD status (git-ci), or commit messages (git-commit)

dppdppd Bundle

One-step rpm orchestrator, or a bounded internal sequence when given a count or scope. Runs preflight maintenance, then starts the next obvious backlog action (or, in direct use, asks for clarification when nothing is clearly next). With no argument it runs one step; with `N`, `blocked`, `all`, or a group name it runs several steps itself, skipping the heavy preflight between steps, and is the recommended way to work several backlog items at once — cheaper than wrapping `/next` in an external `/loop`. How wide it fans out — one worker at a time or a concurrent batch — is the orchestrator's judgment call, sized to how independent the selected work is; it never waits for input mid-sequence. TRIGGER on terse forward-motion prompts — phrasings like "next", "next?", "next.", "next task", "what's next", "do next", "go next", "keep going", "continue" (when the prior turn was rpm work) all qualify and must route through this skill instead of being answered inline from the SessionStart preview. Use whenever the user w

dppdppd Skill

Manage the rpm backlog (long-term project tasks in docs/rpm/future/tasks.org — distinct from Claude's native TaskCreate list, which is session-scoped). Add, list, review, postpone, or complete entries. TRIGGER on natural-language backlog operations — phrasings like "backlog X", "add X to backlog", "add to backlog", "backlog the following", "what's on the backlog", "show/list backlog", "review backlog", "postpone N", "done N", "mark N done", "defer X" all qualify and must route through this skill instead of editing tasks.org directly. Also use when the user wants to reorder execution sequence, defer to the bottom of a group, or evaluate backlog health.

drawthingsai Bundle

Use and troubleshoot an already installed Homebrew draw-things-cli for model discovery, authentication, local, cloud, or remote image generation, basic image-to-image and video generation, output verification, and safe agent operation. Use when a new user or agent needs to inspect Draw Things CLI commands or models, generate a first image, sign in to Draw Things cloud, connect to a Draw Things server, or diagnose common generation failures after installation.

themattberman Bundle

Pull raw performance signal from TikTok, Instagram, and YouTube using your saved Virlo comet. Fetch top videos, creator outliers, and ads for a niche. Use when: user asks what is performing, wants top videos, wants breakout creators, wants creator outliers, wants raw Virlo data, wants ads, needs a comet set up, or needs performance intelligence before synthesis. Do NOT use this as the final briefing layer — use content-radar when the goal is to combine performance with discussion signal and decide what matters.

jsynowiec Skill

Identifies build, test, lint, type-check, and formatting tooling in a repository. Use before running verification steps or assessing a project's development setup.

jtrackingai Bundle

Use when you need GA4 + GTM tracking delivery from site discovery through publish, or when the right phase entry point is still unclear.

jtrackingai Bundle

Use when the user wants crawl coverage, platform detection, dataLayer discovery, or a fresh artifact directory before grouping and schema work.

juspay Bundle

Use when generating connector coverage or capability metrics for meetings, manager/stakeholder updates, retrospectives, or "what changed" / month-over-month / since-release comparisons in the hyperswitch-prism (UCS) repo. Covers coverage diffs over a time window, current-state snapshots, merged-PR activity summaries, and per-connector / per-flow drilldowns. Triggers: "data for the meeting", "how much did coverage change last month", "what did we ship", "supported vs last release".

kengz Skill

You are the LEAD of this project — the role every project session runs as. Expand the north star into an ordered roadmap, own the architecture and technical choices, dispatch engineers, convene the review, hold the budget, and distil results upward. Load at the start of every session in a project repo, and again when planning a phase, writing a spec, deciding an architecture, dispatching work, judging whether a thread still serves the goal, spending against the budget, or building a progress deck.

kiluazen Bundle

Run Autark market-discovery loops for a product: create frozen hypotheses, source leads into the v2 lead sheet, write run narratives, and use Plumcake when blocked.

zaks-io Bundle

Grills an idea, plan, PRD, ADR set, or existing spec one question at a time and produces authoritative specs ready for ticket slicing. Use when the user asks to be grilled or material product, domain, scope, or architecture ambiguity blocks safe progress.

zaks-io Bundle

Use for script-guided issue tracker triage when managing the current project backlog, making issues ready for Orchestrator by running workflow scripts, inspecting their outputs, and fixing labels, statuses, dependencies, body contracts, estimates, stale tracker state, and explicit human questions without ad hoc exploration.

zaks-io Bundle

Use to turn a spec, PRD, or epic ticket into dependency-ordered one-PR implementation tickets, adopting any hand-created tickets, applying the agent-ready body contract, configured estimates, and kind labels, and emitting a dependency graph and predicted file footprint.

zaks-io Bundle

Use to orchestrate a specific ticket set, issue tracker filter, project, delivery scope, or Linear Backlog clear run by selecting startable issues, delegating workers, calling review and integrate steps, updating tracker state, and stopping when no safe workflow action remains.

ztemerbekov Bundle

Write the go-to-market communication for a chosen segment using Ivan Zamesin's AJTBD / Next Move Theory methodology. Input — a nmt-craft-value-proposition result (best), a nmt-product-requirements PRD, a nmt-market-research result, or a manual segment+Jobs description. Output — ready-to-publish landing-page copy, ad/creative copy built on the seven Job-language formulas, and a GTM/growth plan — channel hypotheses, lead magnets, viral loops, cross-sell / upsell / retention messaging. Everything is communicated through the Big Job (motivation), in concrete success criteria not adjectives, with features as proof not message. Use when the user wants landing copy, ad copy, creatives, channel hypotheses, or a launch plan — "write the landing / the copy / the go-to-market". Two modes — Quick (default, no internet) and Deep (subagents + web for real review language). Plain language; defaults to English.

ztemerbekov Bundle

Turn a chosen segment + Core Jobs into a build-ready PRD (full functionality + edge cases) using Ivan Zamesin's AJTBD / Next Move Theory methodology. It consumes upstream work — segments from nmt-market-research, value from nmt-craft-value-proposition — and never re-derives them; with no research done it routes you upstream first, or takes a manually described segment + value for a fast run. Before writing requirements it runs a "challenge the build" gate that looks for a more effective way to hit the same business goal; if a better way wins, the PRD is written for that. Output — a single PRD — functionality mapped Core Job → Big Job → value mechanic → success criteria → Aha Moment on the Critical Chain of Jobs, plus edge cases covering ~90% of use cases. Use when the user says "write the PRD / product requirements" or wants to turn a segment+value or a feature idea into a build spec. Two modes — Quick (default, no internet) and Deep (subagents + web parity check). Plain language; defaults to English.

ztemerbekov Bundle

Generate the strongest possible Value Proposition for a chosen segment using Ivan Zamesin's AJTBD / Next Move Theory methodology (distinct from generic Christensen JTBD). Input — a nmt-market-research result OR a manual segment+Jobs description. The skill extracts the segment's dominant success criteria, builds the Job Graph + Critical Chain of Jobs substrate, generates value hypotheses by walking the value-creation mechanics catalog over that graph, filters them on feasibility, cost-to-build, unit economics, and competitiveness, ranks by RICE, and surfaces a primary + supplementary value proposition with top-3 RAT cards and a PRD-ready implementation spec that feeds nmt-product-requirements. Use when the user wants a value proposition, differentiation, or asks "how do we win this segment". Two modes — Quick (default, no internet) and Deep (subagents + web competitor mining). Plain language; defaults to English.

cairn-ai-tooling Bundle

Use when creating or scaffolding a backlog artifact — an Epic, User Story, Task, or Implementation Plan — or when graduating a docs/roadmap.md item into a tracked artifact. Scaffolds the next-numbered file from docs/product/templates/, wires parent/child links, and adds a roadmap pointer — the same shape as /decision-record but for backlog artifacts.

cairn-ai-tooling Bundle

Use when retiring completed work from a docs/product/ backlog in one pass — archiving every shipped (Done) Epic and its whole subtree into per-type archive/ dirs, regenerating the shipped index, and pruning the roadmap. Trigger whenever someone says "close out the backlog", "archive the completed/shipped epics", "sweep the backlog", "retire the done epics", "regenerate the shipped index", or "clean up docs/product now that X shipped". It is the batch counterpart to /product-item (which creates artifacts; this graduates them out once they're Done).

cairn-ai-tooling Bundle

Use when mirroring a local product backlog (docs/product/ Epics, User Stories, Tasks, Plans created by /product-item) out to GitHub Issues, or onto a GitHub Project board — creating or updating issues, keeping status in sync, and recording the issue number back on each artifact. Trigger whenever someone says "push these to GitHub Issues", "sync the backlog to GitHub", "create issues for these tasks/epics", "put this on the GitHub Project board", "mirror docs/product to GitHub", or asks whether the backlog is big enough to move onto GitHub. The local Markdown stays the source of truth; GitHub is the mirror.

greenschool-ai Bundle

Client Discovery Brief Generator

skillmedev Skill

Designs a daily schedule that protects deep work - classifies tasks as deep or shallow, places 2-4 focus blocks of 60-120 minutes at peak energy hours, batches shallow work into fixed windows, and defines each session with a goal, definition of done, distraction plan, and first action, plus startup/shutdown rituals and a weekly scorecard. Use when someone says "I can't get any focused work done", "plan my day around deep work", "how do I stop context switching", or wants to defend calendar time for demanding work. Do NOT use for processing an email backlog - use inbox-zero instead - or for a full task-capture system - use gtd-system instead.

skillmedev Skill

Turns vague intentions into SMART goals with both lagging targets and controllable leading indicators, then keeps them alive with a 10-minute weekly check-in template, an accountability structure (visible goals, public commitments, partner check-ins), and a quarterly reflection that converts the quarter into lessons. Use when someone says "help me set goals I'll actually stick to", "I set resolutions and abandon them by February", "build me a goal tracking system", or wants a weekly review cadence for personal targets. Do NOT use for company or team objective-setting - use okr-builder instead - or for building daily habits - use habit-builder instead.