Product & Planning

lancetw Bundle

Help non-technical stakeholders write clear, scoped requirements documents. Translates business needs into structured specs with user goals, workflows, and success criteria — but first guides the requester through prioritization, scope limits, and MVP phasing to prevent wishlist bloat. Output in Taiwan Traditional Chinese. Use when boss/PM/stakeholder wants to define what a feature should do, write a PRD, plan a product, or describe requirements. Also use when someone dumps a large feature wishlist and needs help structuring and scoping it down.

lancetw Bundle

Surface unknowns — the gap between the plan in your head and the territory of real code — as interactive, self-contained HTML artifacts the user reacts to instead of describing from scratch. Use when a feature request is ambiguous, the work touches unfamiliar code, the user lacks the domain vocabulary to ask precisely, a visual direction or UI behavior is still open, a known problem has no chosen intervention, external reference code is about to be ported, an implementation plan needs a review pass, mid-implementation reality deviates from the plan, finished work needs stakeholder buy-in, or a large change is about to merge.

lizliz404 Bundle

Audits, improves, and reports evidence-backed SEO and generative-engine visibility across technical, on-page, content, schema, performance, GEO/AEO, links, analytics, SERP, and tracking workflows. Use when a user requests an SEO/GEO audit, AI citation or brand-mention analysis, search remediation, content optimization, or a prioritized organic-discovery plan.

zesion21 Bundle

资深产品经理助手,提供PRD文档创作与评审、产品策略咨询、留存增长分析、竞品研究、功能优先级排序等全方位产品管理支持。适用于创作或评审PRD/MRD/BRD/用户故事等产品文档；诊断产品问题（留存低、转化差、增长瓶颈）并给出可执行策略；进行竞品分析和市场研究；设计功能方案和用户体验优化。当用户提到"PRD"、"需求文档"、"产品规划"、"用户留存"、"功能设计"、"竞品分析"、"产品指标"、"增长策略"、"用户体验优化"、"功能优先级"等产品管理相关话题时，使用此skill。即使用户没有明确说"产品"，但在讨论App功能设计、用户增长、商业模式、需求分析等话题时也应触发。

bmad-code-org Bundle

Builds, edits or analyzes Agent Skills through conversational discovery. Use when the user requests to "Create an Agent", "Analyze an Agent" or "Edit an Agent".

bmcgauley Bundle

Comprehensive quality assurance skill for validating and verifying project deliverables and educational content. This skill should be used when establishing quality standards, performing verification and validation activities, conducting reviews and audits, implementing continuous improvement processes, or ensuring deliverables meet requirements and stakeholder expectations. Provides systematic approaches to prevent defects and ensure excellence.

jwd83 Skill

Resume an in-progress codebase from its actual current state, identify the next smallest defensible implementation step, make that change, and update tests, docs, or plans to match. Use when a rewrite, migration, refactor, feature, or cleanup is underway and you want the agent to move the work forward safely without inventing a whole new roadmap.

madteacher Skill

Сформировать PRD на русском языке из текущего контекстного окна, а именно - уже обсужденных требований, решений, ограничений, пользовательских сценариев, технического контекста и понимания кодовой базы. Использовать, когда пользователь хочет получить PRD на основе уже имеющегося контекста без дополнительного интервью.

madteacher Skill

Разбить план, спецификацию или PRD на независимые задачи для реализации с помощью вертикальных срезов. Использовать, когда пользователь хочет превратить план, PRD, описание функции или техническую спецификацию в набор исполнимых задач.

mindgames Bundle

Plan and run milestone/cycle operations for multi-repo projects in GitHub with a shared milestone per project. Use when defining or revising current/next milestones, deciding cycle load, shaping backlog into AI-ready issues, creating/updating milestones and issues across repos, reviewing GitHub project board health, or producing daily/weekly project execution plans.

mrveiss Skill

Pick and solve the backlog issues that need no decision. Use when asked to work the backlog, drain issues, "solve what you can", run the loop autonomously, or whenever a loop tick has no assigned issue. Selects work; delegates execution to batch-implement.

mrveiss Skill

End-to-end GitHub issue implementation — umbrella gate, worktree, design, code, verify, PR, CI, and the three-gate closure check. Use when told to implement, fix, or solve a specific issue number, or when picking the next issue off the backlog. Supersedes the former `issue` skill.

neetx Skill

Discover important work the radar does NOT yet track, by iterating the discovery-venue list in SOURCES.md every run — significance-first: read the top / most-attention items in each venue REGARDLESS of topic, not by searching tracked axes. Surfaces off-axis significance and candidate new axes. Use for the daily exploration slot, after the sweeps.

nocodemrli Bundle

Orchestrate evidence-first engineering for WeChat and other mini programs from a vague idea or existing repository through project discovery, product specification, architecture, implementation, debugging, device adaptation, verification, and release readiness. Use when users ask to build a mini program from zero to one, take over an existing mini-program project, deliver a cross-stage feature, diagnose project status, coordinate development and testing, or judge whether a mini program is ready to upload or release. Enforces fact discovery, change boundaries, stage gates, evidence-calibrated status, sensitive-information redaction, and continuity after side questions.

nocodemrli Bundle

Apply evidence-first engineering discipline to any agent-built software project: fact discovery before action, evidence-calibrated status reporting, explicit change boundaries and stage gates, controlled confirmation for risky or external actions, sensitive-information redaction for anything shared publicly, and resumable continuity after interruptions. Use when users ask an agent to take over an existing codebase, deliver a feature across stages, verify whether work is actually complete, judge release readiness, or keep conclusions honest about what is proven versus assumed. This foundation skill is domain-neutral; vertical suites (for example mini-program engineering) build on it by adding domain facts and platform rules.

olaradiallysymmetrical491 Skill

AI-powered tools for Web3 bug bounty automation. Use when you want to automate recon, run autonomous audits, or use AI agents for vulnerability discovery.

olaradiallysymmetrical491 Skill

External research synthesis from Trail of Bits, SlowMist, ConsenSys, Immunefi, and Cyfrin. Use this for advanced audit methodology, Echidna/Medusa fuzzing setup, Slither custom detector writing, attack pattern deep dives, or the 4-phase learning roadmap.

pesty-marketing Bundle

Use when building a buyer persona, customer persona, or ICP from real inputs — sales/discovery call transcripts (Fathom), win-loss interviews, surveys, reviews, CRM won/lost notes — and you want a decision-focused persona, not a demographic profile. Triggers like "make a buyer persona", "build a persona for <client/segment>", "turn these call transcripts into a persona", "what drives these buyers". Applies the Kraus & Revella 5 Rings of Buying Insight method.

robingru Skill

Initialisiert ein neues SaaS-Projekt aus einem Briefing und optionalen UI-Prototyp. Verwenden, wenn PRD, Roadmap, Datenmodell, App-Shell und Feature-Board noch erstellt werden müssen.

sanjithbolloju18 Bundle

触发：当你需要收集多方意见、把零散反馈整合成可执行方案，或把方案带回真实使用者/执行者验证时调用；常见信号包括 stakeholder input、user feedback、意见汇总、对齐与验证。 English: Trigger when input must be gathered from many people, synthesized into a clearer plan, and returned to the affected users or executors for validation. Use this skill for a collect-synthesize-validate loop.

securitymindedsolutions Bundle

Autonomous task runner that works through a PRD one task at a time. Launches ralph.sh in the background and monitors progress.

securitymindedsolutions Skill

Interactive PRD builder for the Ralph autonomous coding loop. Guides users through creating structured plans with explicit file paths.

ludovic33fr Skill

Utiliser à chaque révision trimestrielle de roadmap pour simuler trois variantes selon des hypothèses de capacité et de risque. Produit une variante prudente, une variante agressive, une variante équilibrée, comparées ligne à ligne.

ludovic33fr Skill

Utiliser pour cadrer une nouvelle discovery utilisateur. Produit cinq hypothèses concurrentes, leurs observables de validation, le profil cible, un guide d'entretien et une grille de codage des verbatims.

ludovic33fr Skill

Utiliser avant chaque communication transverse importante pour décliner un même sujet en versions calibrées par stakeholder. Produit un encart d'une page par stakeholder, dans le format de prédilection identifié dans la matrice.

ludovic33fr Skill

Utiliser la veille de chaque cérémonie de refinement pour pré-réviser un ou plusieurs tickets de backlog. Produit un tableau des critères manquants par dimension, un test INVEST argumenté, des scénarios edge cases en Given/When/Then, et la liste des dépendances détectées.

daydeda Skill

Manages all documentation for game development projects — including GDD (Game Design Documents), Software Design docs, and Agile management artifacts. Use this skill whenever the user mentions GDD, game design, sprint planning, backlog, software architecture for a game, class diagrams, or wants to create/update/review any project document. Trigger even for casual requests like "write up the game concept", "plan this sprint", "draft the system design", or "check if our docs are consistent". Outputs Markdown (.md) format. Designed for small teams (2–5 people) using an engine-agnostic approach.

dominikwozniak Bundle

Scaffold a private/solo repo for the solo loop — `.ai/` (work / backlog / archive), `docs/decisions/`, `CONTEXT.md`, a tracked `AGENTS.md` with a Task Router and a size budget, the guardrail hooks, settings with a derived allow-list, and an optional pre-commit. Explicit-invoke only.

dominikwozniak Skill

Walk `.ai/backlog/` and decide every entry out loud: drop what is stale or already done, do what is cheap and unblocked, bundle what ships with a cousin, leave the rest. Explicit-invoke only.

dominikwozniak Bundle

Turn a request, a backlog entry or a finished `dw-grill` conversation into the change doc: write a durable `CHANGE.md` under `.ai/work/` with the goal, the decisions taken, a task checklist and anchors in real files; one per goal, never per shippable piece, depth scales with size, and in its own worktree when you ask for one.

aws-samples Bundle

Build an OAuth + MCP protocol facade in front of Bedrock AgentCore Gateway or Runtime so strict MCP clients (Claude Code, Cursor, Amazon Quick, mcp-remote) can connect. Use when an MCP client fails OAuth discovery ("Fix highlighted fields", DCR errors), when tools beyond 30 silently disappear (Gateway tools/list pagination), when tool calls return 404 or "Unknown tool" (dual session-id, tool name prefix), or when adapting Cognito to RFC 9728/8414 metadata, redirect_uri rewriting, or Gateway schema limits.

cedmandocdoc Bundle

Manages structured task folders (plan.md, status.md) for cross-session agent handoff. Creates, creates multiple (plan a backlog of new tasks), executes, executes multiple (plan then implement backlog), triages (status, readiness, roadmap), updates, blocks, unblocks, or cancels tasks. Done and Cancelled tasks auto-archive. Use when the user works with tasks/NNN-slug folders or asks about task status, blockers, readiness, or lifecycle.

cedmandocdoc Bundle

Creates and amends product specification markdown — PRD, FRD, TRD, user story, and UI specs (flow, screen structure, view states) — with consistent layout and frontmatter. Use when the user asks to draft or amend prd.md, frd.md, trd.md, user-story.md, or ui-specs.md at product or feature level — no code implementation.

full-stack-skills Bundle

Manages the installation and discovery of AI skills from the PartMe marketplace.

jojious Bundle

ALWAYS use this skill before answering brainstorming, ideation, prompt crafting, or open-ended exploration requests. Transforms vague requests into actionable outputs via adaptive guided questioning — triages into Prompt Mode (craft/improve prompts), Explore Mode (brainstorm ideas), or Focused Mode (specific problem strategies). Trigger when user says: "brainstorm", "ช่วยคิด", "help me think", "I have an idea", "improve this prompt", "let's explore", "I want to build", "I'm thinking about", "brainstorm วิธี", "ช่วยคิดหน่อย", "อยากทำ", "ยังไม่รู้จะทำอะไร", "not sure about the approach", "help me figure out", "what should I". Also trigger for: side projects, career decisions, project planning, migration strategies, architecture decisions, cost optimization, or any request where the user hasn't decided direction yet and would benefit from structured discovery. Do NOT skip — adapts depth automatically (2-7 questions) and produces BETTER results by asking targeted questions first.

ndisisnd Bundle

Root menu for msg skills, plus harness modes. `--init` is the one-time project bootstrap — use it when the user says "initialise project", "bootstrap repo", "set up the framework", "start a new project", or asks to set up project structure in an empty repo. Other modes: `--init-staging` (add a staging branch), `--update` (re-scan a bootstrapped repo), `--gui` (local PRD board), `--doctor` (tally and triage the harness-incident ledger), `--aha` (sweep, triage, and compact the devkit/AHA.md learnings ledger), `--version` (print the installed release in one line), `--help` (guided skill picker).