Product & Planning

0xpolygon Skill

Agentic Services on Polygon — pay-per-call APIs gated by the x402 payment protocol, callable via the Polygon Agent CLI. No API keys or subscriptions; each call costs a small USDC amount drawn from the agent's smart wallet. Covers web search (Exa, SearchApi), web scraping (Firecrawl), news (NewsAPI), LLM inference (Llama 3.3/3.2 via NVIDIA NIM, OpenRouter), cloud browsers (Browserbase), email (Resend, AgentMail), on-chain wallet analytics and prices (Allium), and multi-chain JSON-RPC (QuickNode, 16 chains).

chris1wang3 Bundle

基于腾讯会议官方 tmeet CLI 的会后需求评审裁决 Skill。当用户需要复盘需求评审、PRD 评审或技术方案评审会议，判断需求是通过、有条件通过、驳回还是信息不足，并从智能纪要和逐段转写中提取质疑、答复、阻塞条件、原话证据与验收标准时使用；也用于用户同时提供 PRD、需求文档或方案文档，要求核对会议结论与文档的遗漏、冲突和新增内容。不用于普通会议纪要、会议预约、实时会中监听、自动外发、自动修改文档或员工表现评价。

chris1wang3 Bundle

Cold-start unpacker for vague boss/business requirements. Use when the user says "老板/业务只给了一个模糊方向", "帮我接一下这个需求", "信息不全先拆一下", "我还没 PRD 先给方案骨架", or needs a 30-minute to 2-hour PM alignment pack with confirmation questions, scenario narrowing, scope skeleton, readiness score, risk flags, and reply script.

chris1wang3 Bundle

PRD review stress-test simulator: 5 cross-functional roles challenge your requirements and outputs a scored HTML or Markdown survival report with radar chart and meeting script. Use when PRD review, requirement review simulation, or cross-functional pushback rehearsal, or when the user says「评审需求」「模拟评审会」「帮我预演一下」.

agent-field Skill

Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap — one `af ls -e` or capability lookup answers it, and the roster can be cached for the session. These agents are your AgentField subharnesses: workers running on cheaper open models, in parallel, off your own context, every run recorded on the control plane and watchable at <server>/ui/runs/<run_id>. This skill cannot know what your fleet does — runtime discovery is the only source of truth (swe-planner, pr-af, and whatever else the user installed). Also the reactive path when the user asks to use, call, or run an agent, to list what agents or reasoners exist, or to check on an execution. Resolves the right control plane (local or desktop-configured cloud) first, fetches the reasoner's exact contra

pramoddutta Skill

Triage a batch of defects instead of grinding through them one by one. Use when a lead says "triage these bugs", "prioritize the defect backlog", or pastes a list of open issues that need sorting. Groups likely duplicates, proposes severity/priority, routes each to a component or owner, and flags reports missing information. Every duplicate and routing is a suggestion for a human to confirm — it never auto-closes or reassigns silently.

llm-coding Bundle

Recover the "theory" (Naur 1985) of an existing codebase through recursive question refinement before writing documentation. Use on brownfield projects where the spec is missing — produces a Question Tree separating what is answerable from code (with evidence) from what must be asked of the team (routed by role). Phase 1 builds the tree; team answers the OPEN leaves; Phase 2 synthesizes PRD, Cockburn use cases, arc42 architecture, and Nygard ADRs from the answered tree.

the-vibe-company Bundle

Use the official XcodeBuildMCP CLI for deterministic Apple-platform discovery, build, test, simulator run, debugging, logs, screenshots, and UI inspection. Use for tool execution and verification, not for product shaping or SwiftUI architecture.

ghostlygawd Bundle

EXPERIMENTAL. Preview 2–4 alternatives or a measurable roadmap without changing the project. Use for low-cost incubation, preview-only brainstorming, or roadmap drafting with exact-target approval before any later action. Do not use when the user explicitly invokes the standalone brainstorm skill or requests independent parallel candidates; do not use as build or mutation authority.

jetbrains Skill

Experimental jbcontext org-wide dependency search across multiple repositories. Use when need to find APIs in other repositories, or dependency configuration are used across repos for upgrades, removals, CVEs, migrations, or ownership discovery.

joeseesun Skill

Use when creating a new OpenCLI adapter from scratch, adding support for a new website or platform, exploring a site's API endpoints via browser DevTools, or when a user asks to automatically generate a CLI for a website (e.g. "帮我生成 xxx.com 的 cli"). Covers automated generation, API discovery workflow, authentication strategy selection, TS adapter writing, and testing.

kanohorizonia Skill

Local-first, multi-product backlog management with agent collaboration discipline.

kanohorizonia Skill

Local-first, multi-product backlog management with agent collaboration discipline.

kanohorizonia Skill

Local-first, multi-product backlog management with agent collaboration discipline.

kimyx0207 Bundle

Cross-runtime Agent Teams orchestration playbook for Claude Code, Codex, OpenClaw, and Cursor. This skill should be used when the user asks to "create agent teams", "use agent swarm", "setup multi-agent collaboration", "orchestrate agents", "coordinate parallel agents", "organize team collaboration", "build agent teams", "implement swarm orchestration", "setup multi-agent system", "coordinate agent collaboration", or needs guidance on adaptive team formation, quality gates, skill discovery, task distribution, team coordination strategies, or Agent Teams best practices. 或者当用户说"多agent"、"agent协作"、"agent编排"、"并行agent"、"分工协作"、"拉团队"、"拉个团队"、"多代理协作"、"swarm编排"、"agent团队"时也应使用此技能。Note: "swarm/蜂群" is a generic industry term; Claude Code's official concept is "Agent Teams"; Codex, OpenClaw, and Cursor should map this playbook to their native or host-provided agent capabilities without deleting any workflow stage.

zhangliang0115 Skill

Write, structure, and publish a SKILL.md skill that works across every harness — Claude Code, DeepSeek Harness (dsh), Codex CLI, Gemini CLI, Copilot, Cursor — including the cross-agent gotchas generic guides miss: tier shadowing between project and user roots, discovery rules, and trigger-description design. Use when creating a new skill, fixing a skill that fails to load in some agents, or preparing a skill repo for distribution.

zhangliang0115 Skill

Audit whether an agent skill works across every harness (Claude Code, DeepSeek Harness dsh, Codex, Gemini CLI, Copilot, Cursor) before publishing or after a "my skill loads in Claude but not in dsh" report. Checks name collisions across roots, tier shadowing, discovery rules, and trigger quality per agent.

fantasymax Bundle

CRITICAL: If user says "design/make a skill for X" / "我想做一个 XX 的 skill" / "帮我做个 AI 写 XX 的 skill" — DO NOT write it yourself, USE THIS SKILL to interview them first. That IS the purpose. Use for personalized AI config or custom skill via structured self-interview, not copying templates. Two outputs: (A) Principles — CLAUDE.md / AGENTS.md / .cursorrules / system-prompt for Claude Code / Cursor / Codex / OpenCode / Aider etc. (B) Custom skill — design from scratch OR extract recurring task; works whether user has a clear task or needs AI to discover one. Trigger: 我的 principles / 自己的 skill / 个性化 AI / 帮我设计一个 skill / 我想做一个 XX 的 skill / 让 AI 写 XX 的 skill / 把我会的事教给 AI / build my own CLAUDE.md / make a custom skill / design a skill from scratch / build a skill for X / AI that understands me. Do NOT use for customer research, product discovery, market research.

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.

orfi Skill

Internal + shared ADR intake/create for Trackbed. Resolve the ADR location, scan and read existing Architecture Decision Records so planning respects them, and gap-fill a new ADR only when there is a genuine uncovered decision. Invoked inside trackbed-init (step 2, for an epic or project) and usable standalone — by a story flow, OR directly on an epic or project when you only need ADRs surfaced or created and do NOT want a roadmap. No manifest, roadmap, or caller is required to run it standalone. Reading existing ADRs is the common case; creating one is the rare exception. Trigger whenever an epic, project, or story needs its recorded architecture decisions surfaced — with or without a roadmap.

orfi Skill

Internal one-time planning pipeline for Trackbed. Turns a Jira epic — or a standalone project — into an optional PRD, optional ADRs, an ordered roadmap, and (optionally) tickets, then locks the storage format in the manifest. Invoked by trackbed when no roadmap exists. Skippable when a roadmap already exists. Never user-invoked directly; never drives execution.

orfi Skill

Create or update the persisted plan for a Trackbed phase. Writes the phase's plan file in the tracked planning layer so a phase is never executed planless. Default simple mode drafts from the roadmap's scope/done; naming a tool in the prompt ("using superpowers") runs that tool's planning flow and adopts its output. User-invocable.

orfi Skill

Reconcile the Trackbed planning layer to the live roadmap — refresh the state file, roadmap, phase↔ticket mapping, and regenerate the viewer, then check every phase has a persisted plan and notify if one is missing. Read-reconcile only; never advances a phase, authors a plan, or writes Jira. Callable directly, and invoked by trackbed-orchestrate on any material change. User-invocable.

orfi Bundle

Open the Trackbed roadmap viewer in the browser — a single self-contained HTML page that draws the roadmap three ways (phase board with color-coded status + Jira keys, rail strip, and dependency graph). Use whenever the user wants to see, open, visualize, or "show me" the roadmap for an epic or project. Regenerates the viewer from the live roadmap first so it always matches current state, then opens it. User-invocable.

akiselev Skill

Use ghidra-cli for reverse engineering tasks: binary analysis, decompilation, function inspection, cross-reference analysis, pattern discovery, and binary patching. Activate when the user requests: - Binary analysis or reverse engineering - Decompilation or disassembly - Function listing, inspection, or renaming - Cross-reference or call graph analysis - String or byte pattern searches - Binary patching or modification - Ghidra project management

surya8991 Skill

Meta-orchestrator that classifies tasks and routes to the right combination of installed skills across caveman (output compression), superpowers (dev workflow), anthropic-skills (business/domain expertise), and wired tactical libraries (wshobson, davila7, impeccable, anthropic-official). 26 routing categories including whole-codebase analysis via repomix-pack, LLM/AI app dev, a live task dashboard, meta skill discovery, and curated tactical skill libraries (wshobson, davila7) for backend/security/CI-CD/database depth. Also scaffolds the canonical project-doc spine (README/AGENTS.md/CLAUDE.md/PROJECTLOG.md) in new projects via `/agent-master scaffold`. Invoke with /agent-master. Use as default entry point for ambiguous or multi-domain requests.

akachandan1 Bundle

When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," "content planning," "editorial calendar," "content marketing," "content roadmap," "what content should I create," "blog topics," "content pillars," or "I don't know what to write." Use this whenever someone needs help deciding what content to produce, not just writing it. For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit. For social media content specifically, see social-content.

aws-samples Bundle

Perform a structured EKS operational excellence assessment against a live cluster. Covers 10 areas: cluster lifecycle, infrastructure as code, access and identity, observability, workload configuration, networking, autoscaling, deployment practices, operational processes, and add-on management. Produces a GREEN/AMBER/RED rated report with prioritized recommendations. Activate for any request to audit, review, health-check, or score an EKS cluster operational posture, including section-scoped reviews and version currency / current-state add-on and deprecated-API review with no target version. Not for upgrade readiness assessment against a target version, cluster discovery, or architectural design advice.

buiducnhat Bundle

Collaborative discovery and design framing for ambiguous or high-risk work. Use when requirements are unclear, multiple approaches are possible, or you need to turn an idea into a validated design brief before planning or coding.

cogine-ai Bundle

Explicitly synthesize the current conversation into a PRD or spec and publish it to the configured tracker.

cogine-ai Bundle

Turn ambiguous product or bug requests into de-duplicated, implementation-ready specs with acceptance criteria and validation.

anonaddy Bundle

Use this skill to analyze how a Laravel application is actually written and record its conventions as shared rules. Trigger when the user wants to detect, infer, document, or standardize project conventions or coding style, set up or grow `.ai/rules`, resolve mixed or conflicting patterns (e.g. "are we using Form Requests or inline validation?"), or onboard agents and teammates to "how we do things here". Covers: a systematic sweep of ~49 Laravel convention dimensions (validation, models, architecture, testing, frontend, database, console), open-ended house-pattern discovery, conflict reporting, and recording rules scoped to the right paths via the Boost `record-rule` MCP tool. Do not use for one-off code review, enforcing formatting a linter already handles, or editing `.ai/rules` files by hand.

arenukvern Bundle

Critically analyze whether a product, repo, skill, plugin, harness, or architecture vision still fits the real application, user intent, implementation, evidence, and likely future direction. Use when asked to assess vision vs application, predict future fit, critique roadmap direction, analyze strategic intent, or decide whether to keep, refine, pivot, or kill a plan.

arkan Skill

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

carlvellotti Skill

Draft a stakeholder update email using past updates for tone

carlvellotti Skill

Write a specific PRD section grounded in project research and goals