Product & Planning

peterbamuhigire Bundle

Use when ranking an approved backlog with MoSCoW and WSJF and assigning release or sprint order; use story-mapping when the user journey and walking skeleton are not yet visible.

peterbamuhigire Bundle

Use when producing product-specific ICP, discovery, demo, qualification, battlecard, and closing material for a sales-assisted SaaS. Use customer-success-playbook for post-sale operations and FAQ for customer self-service answers.

peterbamuhigire Bundle

Use when defining the schema-bound tools an AI agent may invoke, including side effects, reversibility, approvals, audit fields, quotas, and kill switches; use agent PRD for user outcomes.

peterbamuhigire Bundle

Use when specifying AI knowledge sources, ingestion, tenant isolation, freshness, retention, lineage, and training-data exclusions; use ai-feature-prd-spec for user-facing behaviour.

peterbamuhigire Bundle

Use when decomposing approved scope into traceable capabilities, features, subfeatures, and atomic requirements; use user-story-generation for Agile backlog phrasing.

peterbamuhigire Bundle

Use when a Business Requirements Document is needed to bridge strategy and detailed requirements; use prd-generation for product scope and user value, or initialize-srs for formal system specification.

peterbamuhigire Bundle

Use when auditing or improving the SDLC documentation engine or any PRD, SRS, architecture, test, deployment, governance, or game documentation product it produces.

starchild-ai-agent Skill

AI Learning Coach: turn vague learning goals into a concrete 30/60/90-day plan, weekly tasks, and progress tracking. Wraps the AI Learning Roadmap Tracker project (https://community.iamstarchild.com/3182-ai-learning-roadmap-tracker) and adds in-chat personalized planning on top.

cowork-os Bundle

Generate a structured Product Requirements Document from a feature request.

coco-research Skill

Review and promote backlog items to active milestone

teoslayer Bundle

Advanced agent discovery by tags and status. Use this skill when: 1. Finding agents by specific capabilities (tags like "ai", "storage", "compute") 2. Looking up detailed agent information and metadata 3. Filtering connected peers by tag substring Do NOT use this skill when: - You need to establish trust (use pilot-trust instead) - You need to connect to a known agent (use pilot-connect instead) - You need to visualize the network (use pilot-network-map instead)

teoslayer Bundle

Real-time online/offline/busy presence tracking for agent fleets using ping and pub/sub. Use this skill when: 1. You need to track which agents are online/offline/busy 2. You need to broadcast presence changes to interested peers 3. You need to discover available agents for task routing 4. You need to maintain a real-time agent directory Do NOT use this skill when: - You only need static peer discovery (use pilotctl trust instead) - You need detailed health metrics (use pilot-metrics instead) - You need persistent audit logs (use pilot-event-log instead)

teoslayer Bundle

Local directory of known agents with cached metadata. Use this skill when: 1. Maintaining a persistent directory of frequently contacted agents 2. Caching agent metadata for offline reference 3. Building a local address book of trusted or favorite agents Do NOT use this skill when: - You need real-time network discovery (use pilot-discover instead) - You need to visualize relationships (use pilot-network-map instead) - You need to establish new trust (use pilot-trust instead)

teoslayer Bundle

Deploy predefined network topologies (star, ring, mesh, tree) for structured swarms. Use this skill when: 1. You need specific communication patterns (star coordinator, ring consensus) 2. You want to minimize connection overhead with structured topologies 3. You need hierarchical organization (tree) for scaling Do NOT use this skill when: - Ad-hoc peer discovery is sufficient (use pilot-swarm-join) - Topology changes frequently (use dynamic mesh)

teoslayer Bundle

Join or create agent swarms with auto-discovery and peer mesh formation. Use this skill when: 1. An agent needs to join an existing swarm or create a new one 2. You need to discover and connect to peers in a named swarm 3. You want to establish bidirectional trust with swarm members Do NOT use this skill when: - You only need point-to-point communication (use pilot-p2p-connect) - You need structured topologies like star or tree (use pilot-formation)

teoslayer Bundle

Comprehensive mesh status — peers, encryption, relay, bandwidth. Use this skill when: 1. Getting a complete overview of network status and health 2. Debugging connectivity or performance issues across the mesh 3. Generating status reports for monitoring or dashboards Do NOT use this skill when: - You only need peer discovery (use pilot-discover instead) - You need detailed health monitoring (use pilot-health instead) - You need to visualize topology (use pilot-network-map instead)

teoslayer Bundle

Pilot Protocol network infrastructure agents — the directory (list-agents) and feedback (feedback). Use this skill when: 1. Discovering other agents on the pilot overlay (list-agents) 3. Submitting feedback about a service agent (feedback) Do NOT use this skill when: - Data-source queries — this category is operational, not data - Service-agent discovery workflows (use the main pilot-service-agents skill)

teoslayer Bundle

Deploy a decentralized agent marketplace with 4 agents. Use this skill when: 1. User wants to set up an agent capability marketplace 2. User is configuring a directory, matchmaker, escrow, or gateway agent 3. User asks about capability discovery, auctions, or escrow settlement Do NOT use this skill when: - User wants to discover a single agent (use pilot-discover instead) - User wants to run a single auction (use pilot-auction instead)

teoslayer Bundle

Deploy an API gateway management system with 4 agents. Use this skill when: 1. User wants to set up API gateway management with service discovery, routing, auth, and monitoring 2. User is configuring agents for API request routing, rate limiting, or backend health tracking 3. User asks about API gateway pipelines, service registries, or request authentication workflows Do NOT use this skill when: - User wants a single load balancer (use pilot-load-balancer instead) - User wants to verify a single token (use pilot-verify instead) - User only needs health checks (use pilot-health instead)

teoslayer Bundle

Deploy a scientific research team with 4 agents. Use this skill when: 1. User wants to set up a collaborative research pipeline with literature review, hypothesis generation, experimentation, and reporting 2. User is configuring agents for automated scientific discovery workflows 3. User asks about research automation, hypothesis testing pipelines, or experiment management Do NOT use this skill when: - User wants a single literature search (use pilot-discover instead) - User wants to share a file between two agents (use pilot-share instead) - User only needs data archival (use pilot-archive instead)

vivy-yi Skill

M&A 并购主流程 — 整合尽调支持、估值分析、交易结构建议与整合追踪。 适用情形：M&A 项目全周期（意向/尽调/谈判/交割/整合）执行时启动， 整合 financial-due-diligence、dcf-modeling、comparable-analysis、valuation-integration 和 integration-roadmap，输出完整的并购决策与执行包。 核心：尽调风险识别 → 估值锚定 → 交易架构 → 整合落地。

vivy-yi Skill

并购整合路线图 — 制定并购后整合计划，明确整合目标、时间表、 关键任务和责任分工，确保整合顺利推进。 适用情形：并购交易完成后 [X] 天内，或用户要求"制定整合路线图"时执行。 核心：整合范围确认 + 整合计划制定 + 协同效应追踪 + 风险管理。

cowork-os Bundle

Use when Codex is already in the finding-discovery phase of a security scan or the user explicitly asks to discover candidate security findings in a repository or code change. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

cowork-os Bundle

Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide Codex Security scan. Run repeated independent repository-wide discovery passes with worker-specific threat models, semantically merge candidates, synthesize one canonical validation threat model, then run validation, attack-path analysis, and final reporting once. Repository-wide targets only; do not use for PRs, commits, branch diffs, working-tree diffs, or scoped paths.

vishuwa2004 Bundle

Reset per-turn skill discovery tracking so long-lived sessions don’t leak outdated discovery flags while still honoring already-known skills.

vishuwa2004 Bundle

Ensure SkillTool only exposes MCP skills when they are registered as prompt-based commands and dedupe them against local commands.

vishuwa2004 Bundle

Bypass skill discovery when expanded SKILL.md or generated prompt content is being reprocessed for attachments, so non-user text does not trigger recursive discovery work.

openlabor Skill

Sam Altman's AI-first thinking: rebuilding companies around AI, identifying what AI can do 80% of, AI integration roadmap, when to build vs use existing AI tools, and AI-native product design — from Altman's blog, OpenAI writings, and public talks (2022-2024)

nvidia-omniverse Bundle

Extend the OVRTX Blender add-on with native LiDAR sensor authoring, runtime capability discovery, raw-return capture, coordinate conversion, accumulation, viewport presentation, and evidence. Use when adding LiDAR support rather than producing a synthetic point overlay.

nvidia-omniverse Bundle

Guide for deploying, configuring, and integrating the OneDrive Storage Service for NVIDIA Omniverse with Kit App Streaming. Use when configuring Entra ID / Azure AD authentication (tenant ID, client ID, client secret, Graph API endpoints), setting up Microsoft Graph delegated permissions, choosing between Bearer pass-through and On-Behalf-Of (OBO) token flows, wiring the service into Kit App Streaming (discovery endpoints, redirect URIs, ingress auth extension), validating end-to-end connectivity, or troubleshooting deployment failures (invalid/expired credentials, missing Graph permissions, token acquisition/exchange failures, tenant ID / redirect URI mismatches). Also explains the underlying Graph API implementation and the OBO token lifecycle (acquisition, caching, expiry, renewal) and why each auth component is required.

nvidia-omniverse Bundle

Make native builds, command-line tools, viewers, plugins, shaders, test harnesses, and packaged artifacts portable across working directories, install trees, copied build trees, users, and machines. Use when Codex works on CMake/install rules, RPATH/RUNPATH, dynamic library lookup, shader or asset discovery, CLI resource paths, packaging, deployment, or bugs that only reproduce outside the repo root.

nvidia-omniverse Bundle

Sequence a nanoUSD renderer build from nothing into a correct, scalable backend using only the renderer skill set. Use when Codex starts a new renderer or backend, plans renderer milestones and phase order, decides what must be correct before the next layer, or needs the contracts-first build order and reduced-fixture corpus that turn the other renderer skills into a buildable plan with no reference renderer to copy from.

aradotso Skill

Discover, explore, and learn about MCP (Model Context Protocol) servers from a curated list of 6000+ implementations across 30+ categories

aiunlocked1412 Bundle

AI นักเขียนหนังสือเต็มเล่ม — chapter outline, voice, pacing, nonfiction/fiction, manuscript planning, self-publish roadmap สำหรับตลาดหนังสือไทย

aiunlocked1412 Bundle

Project plan ครบ — WBS, Gantt, sprint, retrospective, RAID log, stakeholder communication

zhou210712 Skill

将合同审查转化为业务利益方实际会阅读的摘要。不是法律备忘录——是对 "能签吗？需要知道什么？"的两分钟回答。当用户说"给业务部门总结一下" "写给[利益方]"解释给采购""非法务摘要"或审查完成后需要发送给法务以外的人时使用。