Product & Planning

rubicon Bundle

Forensic, source-grounded research workflow for reconstructing work history and client proof from connected files (Dropbox, Google Drive, and similar). Runs a three-pass workflow — discovery, targeted verification, final assembly — and classifies findings by client, firm/era, project type, evidence type, and outcome type, while keeping employer-side and agency/client-side work separate, quarantining unsupported claims, and never inventing details. Use when the user wants to build a client evidence database, find all projects of a given type, verify which projects have real outcome metrics, separate employer-side from agency/client work, assemble case-study candidates, or produce a fully-quoted CSV source appendix. Trigger phrases: "build a client evidence database," "find all website projects," "reconstruct my work history," "which projects have real outcome metrics," "separate employer-side from agency work," "source appendix CSV," "case-study candidates," "final assembly using prior findings."

scchearn Bundle

Use when agents must debate, conference, deliberate, or reach consensus on a goal — competing positions argue and converge on one deliverable, adversarial review with synthesis, multi-stakeholder deliberation, structured disagreement with a forcing-field deliverable. Triggers: 'have agents debate X', 'reach consensus on Y', 'argue distinct positions and converge'. Not for saved team configs, agents/<slug> artifacts, implementation, or open-ended research.

securityskills Skill

Run a STRIDE-based threat modeling workshop — diagram the system, enumerate threats per element, rank them, and drive mitigations into the backlog. Use during design reviews and new feature planning.

winhok Bundle

TestSpec 新建测试工作（流程第 1 步）- 创建测试变更目录，编写 proposal.md，并在用户提供已有 PRD/需求片段时净化成可验收的 requirements.md。当用户要「新建测试」「开始测试」「创建测试变更」「建一个测试项目」或执行 testspec-new / testspec new 时使用。也适用于用户说「我要测 XXX 功能」「帮我准备测试」「有个新需求要测」「帮我整理/审查 PRD」的场景——如果尚无 testspec/changes/ 目录，这是流程的起点。产出 testspec/changes/{name}/ 目录结构、proposal.md，必要时产出 requirements.md。

winhok Bundle

隔离导入和迁移历史测试用例，将旧 Excel、CSV、JSON、Markdown、文本、XMind 或旧 TestLib 数据转换为可审计的 staging artifact，并按当前 PRD 做 reconciliation。用户说「导入历史用例」「迁移旧 Excel/XMind」「整理旧测试用例」「旧 TestLib 被污染」「把老用例对齐新需求」或执行 testspec-import 时使用。导入数据不会直接写入 TestLib，代码也不是默认输入。

winhok Bundle

TestSpec 需求源更新与口径收敛（可重复执行的轻量 rebaseline）- 当已有 testspec/changes/{name}/ 后，用户补充、修改、删除、澄清或替换 PRD、产品回答、验收规则、接口/UI 口径和需求范围时使用。它是唯一能把 accepted/modified 产品决定晋升为 canonical REQ/AC 并增加 source revision 的 Skill，同时维护 question graph 和 stale 下游产物。

winhok Bundle

支持根据 Review 反馈定向返修需求引用和分析结论。TestSpec 需求分析和梳理（流程第 2 步）- 对需求做深度测试分析，运用等价类、边界值、状态迁移等方法，产出 requirements-analysis.md。当用户要「分析需求」「梳理测试点」「做需求分析」「拆解可测项」或执行 testspec-analysis / testspec analysis 时使用。也适用于用户说「这个 PRD 有哪些要测的」「帮我分析一下测试范围」「需求评审准备」的场景。注意：如果用户要的是简短的测试点清单而非深度分析，应使用 testspec-points。

winhok Bundle

对明确授权的一个或多个代码仓库做 PRD-first TestSpec 校准：比较实现快照与当前 PRD、从遗留代码恢复非 canonical 行为草稿，或对生产/测试/需求分支的 Git Diff 做变更追踪。用户明确执行 testspec-code-calibrate、要求「用代码校准 PRD」「联合校准后端、H5 和 Android」「对比需求和实现」「从代码恢复行为草稿」「检查生产和测试分支差异」「看需求分支改了什么」「对照 REQ/AC 与 Diff」时使用；普通 PRD 新建、更新、分析或导入请求不触发。

yaojingang Bundle

Build a company-specific GEO backend tracking plan from a company name plus optional supporting information, using authoritative retrieval anchored on the official website, business-feature recognition, and market-aware GEO monitoring methods, then deliver a direct-vs-indirect attribution design, data model, roadmap, and optional openable HTML and Word reports. Use when asked to 设计 GEO 后端效果归因框架、GEO 效果跟踪体系、AI 搜索效果监测方案、GEO 转化追踪方案、GEO attribution plan、GEO tracking plan、GEO 后端分析 HTML 或 Word 交付件. Do not use for generic GEO education, content planning, pure brand research, or CRM/BI implementation work without GEO attribution design.

yaojingang Bundle

Discover, compare, preview, clone, and orchestrate current GEOFlow frontend experiences across the default site and GeoFlow Agent channel sites, including Laravel Blade themes, homepage module/style JSON, lead_form conversion modules, theme editor, target-package capabilities, and cross-channel sync planning. Use for frontend theme discovery, reference-site mapping, homepage builder design, channel capability audits, and preview-first design iteration. Do not use for CLI operations, backend implementation, lead-form CRUD, raw HTML copying, unsupported remote edits, or direct live activation.

yaojingang Bundle

当用户需要把 GEO 全景诊断、机会地图、AI 平台采样结论或品牌事实底座转成 30/60/90 天综合实施方案时使用，输出页面技术、内容矩阵、标题体系、知识库、外部证据、监测闭环、角色分工、验收指标和四格式报告；覆盖 DeepSeek、豆包、千问、Kimi、元宝；不用于从零做全景采样诊断或只写单篇内容。

yugash007 Bundle

Use when structuring a multi-session learning roadmap with milestones, gates, and pacing calibrated to learner level and goal.

isnoobgrammer Bundle

Open Source Intelligence (OSINT) engine. Takes one identifier (email, phone, name, username, company, IP, domain) and recursively discovers everything: social accounts, leaked credentials, workplace, location, network infrastructure, exposed documents, and dark web presence — each discovery spawning new leads. Triggers on: 'osint', 'recon', 'background check', 'investigate', 'find info on', 'look up', 'whois', 'breach/leak check', 'username/email/phone lookup', 'subdomain enum', 'google dork', 'doxx', 'trace', 'find everything about', or any target identifier the user wants to know everything about.

isnoobgrammer Bundle

Generates comprehensive project plans: PRDs, design docs, architecture flows, task breakdowns, and project constitutions. Use whenever the user wants to plan a project, write a spec or PRD, design an architecture, decompose tasks, or prepare a project for AI-assisted development — including when they just describe an app idea and need structure first. Triggers on: '/plan', 'plan this project', 'create a PRD', 'write a design doc', 'architecture for', 'break this into tasks', 'spec this out', 'what should I build'.

isnoobgrammer Skill

Interview the user relentlessly about a plan, design, or topic, checkpointing every answer to a brainstorm file so nothing is lost. Use when the user wants to stress-test a plan, get grilled on a design, run a brainstorm or discovery session, extract what's in their head into a doc, or says "grill me", "no doubts", "any doubts", "stress test this", "what am I missing", "poke holes", "challenge this", "steel man this", "red team this plan".

312362115 Bundle

通用写作技能：以"内容→组件→组合"的方式产出技术文档、产品文档、汇报材料。 覆盖 spec / plan / PRD / 用户手册 / 项目汇报 / 方案路演 / 调研报告 等所有结构化文档场景。 核心理念：组件驱动，不预设模板。先看内容形态，再挑能装这种形态的组件， 组合自然成文——不强制章节结构、不预设"必备模块"。 组件库（HTML / Markdown / 图示）见 references/components.md， 常见组合范式（spec / plan / PRD 等）见 references/templates/——但模板是参考不是规定。 触发词：写文档、写方案、写计划、写 PRD、写汇报、项目总结、写指南、帮我写、文档、方案设计。 即使用户没有明确说"写"，只要意图是"产出一份结构化的文档/报告/材料"，都应触发此技能。 本 skill 只负责"写"，不负责"调研"（调研由 deep-research 承担）和"调度"（流程由 task-start 承担）。

312362115 Skill

需求全生命周期管理：收集、排序、清理、跟踪、关闭。 管理 docs/backlog/ 目录下的需求文件和 INDEX.md 索引。 核心职责：需求状态变更是整个工作流的驱动力—— open（收集）→ 启动 task-start → 执行 → done（关闭时触发复盘 + 经验沉淀 + 文档更新）。 触发词：梳理需求、排优先级、backlog、需求管理、看看还有什么要做的、需求池、 这个需求做完了、标记完成、关闭需求。 触发场景：开新迭代前梳理需求、积累了一堆需求要排序、定期清理过期需求、需求完成关闭时。 本 skill 管"做不做、做哪个、做完了吗"，task-start 管"怎么做"，plan 管"做到哪了"。

kingxiaozhe Bundle

用户说“修复这个可复现 bug”或要求根据失败报告修代码时使用。执行红灯测试、根因定位、最小修复、独立审查和回归；尚未确认的问题先用 cm-test，新功能和架构重设计转交 cm-prd。

kingxiaozhe Bundle

用户说“把需求拆成可开发规格”“变更现有功能需求”或要求整理方案、任务和验收时使用。支持新项目、存量二开与需求变更；完成后停在人审规格，不直接编码。

kingxiaozhe Bundle

用户说“我有个点子”“帮我梳理产品”或需要先聊清目标时使用。通过逐题访谈整理为可交给 cm-prd 的 PRD；已有明确需求文档时改用 cm-prd，不写代码、不拆开发任务。

kingxiaozhe Bundle

用户明确要求“只整理结构，不改变行为”时使用。执行边界分流、行为判官、分批重构和独立审查；缺陷修复转交 cm-fix，新增或变化的业务行为转交 cm-prd。

thecraighewitt Skill

When the user wants to ask for a warm introduction, build a referral program, or systematize their referral channel. Also use when the user says 'get me an intro,' 'ask for a referral,' 'write a forwardable email,' 'warm introduction,' 'partner referral,' 'reference request,' 'intro email,' 'leverage my network,' 'referral program,' 'ask for an intro at dinner,' or 'track referrals in CRM.' For cold outreach without a warm path, see cold-email or linkedin-outreach. For sequencing referral asks into a cadence, see outbound-sequence. For running the meeting after a referral intro is made, see discovery-call.

thecraighewitt Skill

When the user wants to build a proposal, structure pricing, create an SOW, or present a deal to a prospect. Also use when the user says 'write a proposal,' 'help me price this deal,' 'create an SOW,' 'build a pricing page,' 'put together a quote,' 'send them pricing,' 'scope this out,' 'write up the deal,' 'draft the SOW,' 'pricing options for this deal.' For negotiation after the proposal is sent, see negotiation. For discovery that informs the proposal, see discovery-call.

xhqing Bundle

Agent-to-agent trading for the EigenFlux network. Covers service discovery, placing orders, order lifecycle (delivery, release via Kovaloop transfer), and the buyer gate. Use when user says "find a service", "hire an agent", "buy a service", "list my services", "publish a service", "check my orders", "deliver the order", "release payment", "check trade gate", "search for agents who can do X", "offer my service on eigenflux", "how many active orders do I have", or any trading-related intent. "how many active orders do I have", or any trading-related intent. This includes equivalent phrases in any language the user speaks. Do NOT use for regular broadcasts (see ef-broadcast skill). Do NOT use for private messages (see ef-communication skill). Do NOT use before completing authentication and onboarding (see ef-profile skill).

xhqing Bundle

Find Skill — skill discovery and installation

xhqing Bundle

Feed consumption and publishing for the EigenFlux agent network. Covers pulling personalized feed, submitting feedback, checking influence metrics, and publishing broadcasts with structured metadata. Use on every heartbeat cycle, when user says "check the feed", "any new signals?", "what's happening on the network", "broadcast this", "share this with the network", "publish a signal", "post an alert", "check my influence", "delete my broadcast", or "pull updates from eigenflux". Also use to publish when there is something worth sharing with the network — either useful signal (a discovery, a resource they can offer, a need they have, a timely signal) or a genuine lifelike update (project progress, a milestone, what the user's been up to) — during heartbeat if recurring_publish is enabled, or when an ordinary conversation surfaces something the user may want to broadcast, offering to summarize and broadcast it. Do NOT use before completing authentication and onboarding (see ef-profile skill). Do NOT use for priv

yusifeng Bundle

Use after receiving WebGPT or another LLM review on a Formax todo and before sending the todo back for another pass. Produce a concise handoff response that says what we adopted, what we reject or question, and what the reviewer should specifically re-evaluate in `docs/todolist.md`.

bonnguyenitc Skill

Use when defining product requirements, prioritizing features, planning a roadmap, validating user problems, or making build/buy/don't-build decisions

pedronauck Bundle

Decomposes PRDs and TechSpecs into robust, independently implementable task files, assigning every test case from _tests.md to exactly one task and enriching tasks from codebase exploration. Use when a PRD or TechSpec exists and needs to be broken down into executable tasks, or when task files need enrichment with implementation context. Do not use for PRD creation, TechSpec generation, or direct task execution.

pedronauck Bundle

Executes one PRD task end-to-end uninterrupted — resolves spec conflicts autonomously, implements, validates, and updates tracking without pausing for questions. Use when a prompt includes a task specification that must be implemented, validated, and reflected in task tracking files. Do not use for PR review batches, generic coding tasks without a PRD task file, or standalone verification-only work.

pedronauck Bundle

Performs a comprehensive code review of a PRD implementation and generates a review round directory with issue files compatible with cy-fix-reviews. Use when reviewing implemented PRD tasks, creating a manual review round without an external provider, or performing a quality audit of code changes. Do not use for fetching reviews from external providers, fixing existing review issues, executing PRD tasks, or editing source code.

pedronauck 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.

arogyareddy Bundle

4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.

arogyareddy Bundle

3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.

aws-samples Skill

AWS service capability discovery producing research.json with structured capabilities, API surface, and existing mitigations. Uses MCP servers for AWS documentation, service authorization, and best practices. Downstream skills (Validate, Map) consume this output. Split into 3 focused sub-skills for better accuracy; this skill orchestrates and merges.

l-gevity Skill

Moves recurring DevOps and operational work out of individual memory, manual execution, ticket queues, and team-local practice into documented procedures, repo standards, shared platforms, self-service controls, and adaptive feedback loops. Use when reducing toil, designing an improvement roadmap, deciding what to standardize or automate, assessing where operational work currently lives, pruning prose documentation duplicated by code/config/tests/policy-as-code/architecture-as-code, or asking how to move work from humans into durable systems.