Product & Planning

activeing123 Skill

Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window is filling up with tool schemas, or they need the same MCP servers configured across Claude Code, Cursor, Codex, Cline, Windsurf and other agents. Also covers managing an agent's skill catalog with `mcptoon skills` (list / resolve / sync / add / remove, plus a version gate, derived Roo/OpenCode views, and tombstoned removals). mcptoon compresses 71,929 tokens of tool schemas to 581 (-99.2%) and serves as an MCP 2026-07-28 stateless-first bridge.

activeing123 Skill

Connect any AI agent to MCP servers through mcptoon — one config synced everywhere, one stdio gateway, 99.2% fewer tokens on tool discovery.

vfarcic Skill

Close a PRD that is already implemented or no longer needed

vfarcic Skill

Update PRD progress based on git commits and code changes, enhanced by conversation context

compozy Skill

Executes provider-agnostic PR review remediation using existing review round files under .compozy/tasks/<name>/reviews-NNN/. Use when resolving batched review issues, updating issue markdown files, implementing fixes, and verifying the result. Do not use for PRD task execution, review export/fetch, or generic coding tasks without review issue files.

compozy Bundle

Maintains workflow-scoped task memory for Compozy runs using .compozy/tasks/<name>/memory/ files. Use when a task prompt provides workflow memory paths and requires the agent to read, update, compact, and promote durable context across PRD task executions. Do not use for PR review remediation, global user preferences, or programmatic event-log summarization.

dragoon0x Skill

Write a product requirements document (PRD) that captures problem, goal, scope, approach, and risk. Use whenever the user mentions PRD, product requirements, product doc, product brief, requirements doc, or needs to write a structured document about what to build and why.

dragoon0x Skill

Plan a product roadmap including themes, bets, and sequencing. Use whenever the user mentions roadmap, planning, quarterly planning, what to build next, sequencing features, or needs to organize work over a meaningful time horizon.

dougfsantos2026 Bundle

Audita as funcionalidades de um SaaS de referência navegando pelo produto com o Playwright MCP (preset pronto para o Codental, app.codental.com.br), repete os mesmos fluxos no app do usuário (localhost ou staging) e gera um relatório de gaps com backlog priorizado. Use quando o usuário pedir comparação de funcionalidades com um concorrente, paridade de features, "o que falta no meu site/sistema", auditoria de funcionalidades, feature gap analysis, benchmarking de produto ou testes exploratórios de fluxos (agendamento, cadastro, orçamento, financeiro) com Playwright.

yulin-bi Skill

将当前对话上下文和代码库理解转化为 PRD（产品需求文档）并发布到项目 backlog。适用于需求讨论完成后，需要将共识落地为文档的场景。

carlymr Bundle

Co-author a lightweight product requirements document through structured conversation. Guides non-technical teammates through problem statement, users, goals, success signals, and open questions — producing a short doc (~1 page) that's ready to hand off for a tech spec. Use when writing product requirements, a PRD, feature brief, or scoping a new product idea.

conforma Skill

Triage and manage automated dependency update PRs (Renovate, Konflux) across the conforma and enterprise-contract GitHub orgs. Use when discussing Renovate PR backlog, dependency update management, or automated PR triage.

tonkatoyxl Skill

Use when a task, fix, research flow, content pipeline, or agent workflow repeats or is likely to repeat. Converts one-off work into durable SOPs, skills, scripts, checklists, memory notes, or backlog items so the agent compounds instead of rediscovering.

nimblehq Bundle

Technical pre-sales and solution design for Nimble consulting proposals. Use when creating or populating one-pager documents, drafting scope of work or SOW proposals, defining team compositions and sizing, preparing for sales discovery calls, writing client-facing proposal sections, or explaining costs, timelines, or team structures to clients. Triggers include "one-pager", "proposal", "SOW", "scope of work", "pre-sales", "sales discovery", "team composition", "solution design", and "Nimble proposal".

paulasilvatech Skill

Answer natural-language business questions over existing Power BI reports and semantic models through the FabricIQ MCP endpoint. Orchestrates artifact discovery, schema inspection, entity resolution, DAX generation, and query execution to return plain-language answers. Use when the user asks what, which, compare, rank, explain, or summarize questions about the data in a Power BI report or semantic model, including asking for a DAX query to be run against a named model. Triggers: "ask power bi", "PBI question", "discover my Power BI report", "report data", "dashboard data", "what are the top", "show me the power bi data", "which products sold", "compare sales in report", "which customers churned", "ask the Power BI report", "query a Power BI semantic model", "run a DAX query against a semantic model".

gt0698 Bundle

把需求、原始 PRD、竞品分析等原始素材，提炼成一份可以直接发给 Claude Code / Codex 做 vibe coding 的工程化 PRD。当用户说「帮我写一个用来 vibe coding 的 PRD」「把这个需求整理成能丢给 Claude Code 的 PRD」「根据这份竞品分析出一份给编码 agent 的 PRD」，或给出一段需求/一个飞书 PRD 链接/一份竞品分析并希望据此生成可编码的 PRD 时，务必使用本 skill。凡是用户想把模糊的想法或面向人的文档转成面向编码 agent 的、可直接开工的 PRD，即使没有明说「vibe coding」四个字，也应触发。

jayyang999 Bundle

Use when 用户针对票圈业务要求撰写、整理、补充或追加产品、推荐、数据 PRD，针对票圈业务提到需求文档或飞书 PRD，或给出飞书链接要求形成票圈需求；这些情况必须使用本 Skill。纯阅读、摘要或评论，技术方案、复盘或周报，以及与票圈无关的通用行业 PRD 不使用本 Skill。

jayyang999 Bundle

Use when 用户要用画板、流程图、架构图、调用图、数据流或少文字的方式讲清票圈项目需求、产品方案、推荐/算法方案、数据方案、技术实现、评审材料或项目复盘；即使用户只说“把这个项目讲直观一点”“给老板看”“画一下业务和实现链路”，也必须使用本 Skill。票圈 PRD 同时使用 piaoquan-feishu-prd，由后者控制文档结构和飞书写入；简单问答、单点代码或 SQL 修改、纯文本润色、与票圈无关的通用可视化不使用本 Skill。

jiujiugou Bundle

正式开发阶段工作流(承接 project-intake 预热):把 backlog 需求转化为可验证交付。特性循环:需求三问 → Spec → 用户确认 → Plan → Tasks;修改循环:Explore → Plan → Implement → Verify → Commit。当用户需要:在已完成预热(docs/ + AGENTS.md 就位)的工程上做需求开发、缺陷修复、优化时使用。前置:项目已完成 project-intake 预热。

mmo66666 Bundle

Use when connecting AI agents such as Codex, Claude Code, Cursor, VS Code, Gemini, or MCP Inspector to Unreal MCP in Unreal Editor projects, especially UE 5.8 designer workflows, ModelContextProtocol setup, ToolsetRegistry discovery, All Toolsets diagnosis, slow MCP calls, terminal startup, or connection troubleshooting.

psylch Bundle

Discover music, get personalized recommendations, and download high-fidelity audio files. Use when user wants to find new music based on their taste, search for songs/albums/artists, get recommendations similar to artists they like, or download lossless audio (FLAC/Hi-Res) from Qobuz or TIDAL. Trigger phrases include "find music like", "recommend songs", "download album", "lossless", "Hi-Res", "FLAC", "music discovery", "similar artists", "setup music".

dmno-dev Skill

Varlock Agent Discovery

webmaxru Bundle

Build, validate, test, and update registries and catalogs that follow the Agentic Resource Discovery (ARD) specification. Use this whenever the user works with an ai-catalog.json, a capability manifest, an ARD/AIR catalog or Agent Registry, urn:air: identifiers, trustManifest/attestations, representativeQueries, or an Agent Finder / discovery service — including authoring a new manifest, scaffolding one, fixing schema or URN errors, running conformance/validation, probing a registry's /search, /explore, or /agents REST endpoints, reviewing trust and federation metadata, or preparing to publish at /.well-known/ai-catalog.json. Trigger it even when the user only says "ARD", "agentic resource discovery", "AI catalog manifest", "agent registry", or "make my agents discoverable" without naming the file.

junhua Skill

Expert skill for milestone planning, issue creation, and backlog assessment—optimized for Claude Code single-prompt development. Use for Inframagics and Omnisonant project management.

tensho1026 Skill

Analyze a software repository for meaningful improvements and, when explicitly requested, turn them into separate Japanese GitHub Issues, implement selected issues, create PRs, repair CI failures, and merge them. Use for repository-wide improvement discovery or an explicitly requested issue-to-merge workflow. Do not use for ordinary single-feature implementation, generic code explanation, or code review without improvement discovery.

wendysun718 Bundle

Operate a logged-in Miaoshou ERP workflow for TikTok Shop Malaysia product discovery, product screening, profit estimation, listing preparation, and reviewed publishing. Use when the user asks to search or select products in 妙手 ERP, evaluate low-price traffic products, prepare Malaysian TikTok Shop listings, move products into the TikTok collection box, or publish approved listings. Prefer browser operation through the user's existing login; never store credentials or call undocumented private endpoints.

zhoupeixian Bundle

Automate ZHERP/YigoERP SVN workflows for update, entity generation, Maven compile, revision discovery, diff retrieval, and optional code-review reports. Use when Codex is asked to run ZHERP SVN automation, especially in sandbox/restricted environments that need workspace-local SVN config, Maven path discovery, bokeerp maven_settings.xml, erp-entity-generator, or review report output.

mindfold-ai 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.

rooseveltadvisors-claude-agent-stack Bundle

Security assessment and intelligence — network reconnaissance, web app security testing, prompt injection testing, security news monitoring, and annual report analysis. USE WHEN recon, reconnaissance, port scan, subdomain, DNS, WHOIS, ASN, netblock, CIDR, mass scan, path discovery, endpoint discovery, corporate structure, bounty programs, IP recon, domain recon, passive recon, web assessment, OWASP, pentest, threat model, vulnerability analysis, ffuf, Playwright, Gemini analysis, prompt injection, jailbreak, LLM security, guardrail bypass, direct injection, indirect injection, multi-stage attack, security news, sec updates, breaches, tldrsec, security research, annual reports, threat landscape, security trends, vendor reports, fetch report, list sources.

outlinedriven-odin-gemini-cli-extension Skill

Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope. Trigger on "explore", "find where X is", "how does X work in the code", "map the codebase", "what files handle Y", or any architecture/pattern/tooling/dependency context request on a local repo — even without naming /explore.

agentpmt Bundle

Data Generator - Programming and Web: Generate random data: UUIDs (v1/v4), strings, integers, hex, bytes, passwords, API keys, JWT secrets, colors, emails, IPs, Lorem Ipsum, timestamps. Use when an agent needs data generator programming and web, data generator programming and web, uuid generation, unique identifier creation, uuid v4 random, uuid v1 timestamp, api key, length through AgentPMT-hosted remote tool calls. Discovery terms: data generator programming and web, uuid generation.

olivia-wen Bundle

Design and build teaching mini-apps as playful games first, not explanation-heavy classroom tools. Use when Codex is creating or improving subject-learning games, classroom interactive widgets, math mini-games, HTML teaching plugins, gamified courseware, or child-facing learning tools where the user wants game feel, tactile feedback, visual delight, and discovery-based learning.

socialgouv Bundle

Use to AUDIT a repository, site, or page against WCAG 2.2 AA or a country standard such as RGAA; produce a dated conformance report, criterion grid, PRD backlog, or tickets; AUTHOR accessible markup; fix accessibility; or wire a repo gate and rendered-DOM capture pipeline. The bundled install-free engine runs 93 static checks tied to success criteria, while the agent adjudicates judgment criteria and routes rendering criteria to browser scans; check/verify reject invented non-conformities. Use `review-a11y` instead for a review scoped only to a diff, branch, or PR.

socialgouv Bundle

Use to REVIEW changed frontend code for accessibility: staged files, a working diff, branch, or PR; prompts such as 'review a11y', 'is this accessible?', or 'anything to fix before merge?'; and hook or CI findings on a change. Run the bundled install-free engine with cross-file JSX/TSX analysis, then adjudicate candidates and return a severity-ranked WCAG 2.2 AA review with file:line fixes, residual rendering risks, and a verdict. Use `ultra11y` instead for whole-repo audits, dated conformance reports, country standards, PRD backlogs, or authoring accessible markup.

vfarcic Skill

Start working on a PRD implementation

danieldekay Bundle

Strategic project planning system for creating and maintaining planning artifacts. Use when creating or updating vision, roadmap, epics, backlog, project status dashboards, or milestone reviews. Use when breaking down large goals into actionable work. Use when triaging scope (L1 spec / L2 task-batch / L3 quick-fix). Templates live in this skill's templates/ directory. NOT for spec-kit artifacts (spec.md, plan.md, tasks.md) — those belong to speckit agents.