Product & Planning

wheakerd Bundle

Design, initialize, audit, split, migrate, maintain, or validate a repository's AGENTS.md instruction system, routed .agents guidance, and repo-local .agents/skills that support that system. Use for active-instruction discovery, durable AGENTS updates, route ownership, oversized guidance, or an explicit effective-instructions, effective-instructions:preview, effective-instructions:refactor, effective-instructions:force, effective-instructions:reconcile, or effective-instructions:reconcile-preview mode. Do not use for packaged or installed plugin Skills, ordinary documentation, or general Codex usage optimization unless the requested change is specifically to AGENTS architecture.

xylvvv Bundle

Run lowcode-server persisted real-chain scripts with real providers, persist run records, verify MySQL records, write result JSON, and produce standardized reports. Use only for explicitly authorized regression, observation, or asset-workflow runs that require run-record persistence and MySQL verification. Do not use for bounded non-persistent product-discovery experiments, code fixes, or run review.

yannickyamo Bundle

Run continuous discovery to find problems worth solving. Use when setting up weekly discovery rhythm, building Opportunity Solution Trees, creating interview snapshots, exploring solutions, or testing assumptions before committing engineering resources. Part of the Modern Product Operating Model collection.

nemanli Bundle

Writes a measurement plan **before** the work ships — hypothesis, primary metric, counter-metric, guardrails, decision rule, sample size — so the team agrees on what "success" means before any number exists. Triggers on "measurement plan", "what counts as success?", "how will we know if this worked?", "PRD for metrics", "pre-register the analysis". Skip after data exists (use metrics-diagnose), for picking which metric to track without committing to a decision (use metrics-ux), for tracking-plan design (use metrics-instrumentation), for stakeholder communication (use metrics-present).

nemanli Bundle

Defines UX measurement frameworks, terms, and philosophy when the user is learning the foundation rather than applying it — "what is HEART?", "define cohort retention", "what is MDE?", "what's a decision rule?", "why do we measure things this way?". Skip when a real situation is in mind (redesign, metric drop, stakeholder report, pre-launch plan, A/B test, tracking plan, claim review) — those go to the content skills.

nemanli Bundle

Turns metric results into stakeholder-ready output — board slide, exec email, retro deck, design impact story, stakeholder defence, "how do I explain this to the CPO/board?". Translates design findings into business language, frames counter-metrics. Skip for picking metrics (use metrics-ux), for diagnosing a movement (use metrics-diagnose), for HEART definitions (use metrics-basics).

nemanli Bundle

Diagnoses metric movements when the user has data — a number dropped/spiked/plateaued, before/after numbers, a funnel, a cohort table, or a CSV — and asks "is this real?", "why?", or "what to check next?". Skip if no data exists yet (use metrics-ux), for stakeholder communication (use metrics-present), or for pure metric definitions (use metrics-basics).

neuron-core Skill

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving evaluator discovery, output configuration, result analysis, or building custom assertions.

nhhthong Skill

Turn a long requirement document (contract, PRD, spec.md, ticket export) into the distilled spec layer — one .claude/docs/specs/memory/*.md per domain area plus the requirements.md row table — marking every undecided point ⚠️ instead of inventing an answer. Run once after /clio:setup when the project has a requirement source, and again whenever a new source arrives.

oimiragieo Skill

REVENG GA/release honesty rules from Scope C 2026-08 (Waves 0–2 honesty closeout merged; Waves 3–10 JS recovery climb in progress; R-RALPH-2 open). Use when verifying GA readiness, editing verify_ga_readiness, support matrix claims, capability reports, managed recompile, JS behavior grades, native fixtures / analyze probes, Sol/Fable plan-validate loops, backlog clearance waves, JS recovery Option C metrics, or writing CEO/release status.

microsoft Bundle

Explore Power BI semantic model schemas using DAX INFO functions. Progressive metadata discovery strategy, scope estimation, and narrowing techniques for tables, columns, measures, and relationships.

mo-hawary Bundle

Run source-backed QA discovery, recommend audit tracks, build fix-ready bug-hunt plans, and define verification gates.

rishbjain1 Skill

Turn any linear workflow into a graph and run it. Walks a workflow you already do step-by-step, applies the fake-edge test to find the waits that carry no data, audits for hidden edges (shared files, browser, rate-limited APIs), picks the shape (chain / diamond / router / cycle), emits a GRAPH SPEC, then runs it as a coordinated fleet via the Workflow tool with caps and fresh-context verifiers. Domain-agnostic — works on research, discovery pipelines, content pipelines, repo sweeps, analytics, launches, not just code. Triggers - "graph loop", "/graph-loop", "draw the graph", "graph this workflow", "fake edge test", "can this run in parallel", "make this parallel", "fan this out".

warpdotdev Skill

Full experiment analysis, report, insight capture, ship/kill PR. Triggered by bud_server webhook when a Roadmap entry's Status changes to 7-analyzing.

warpdotdev Skill

Propagate Owner changes from the Page Registry to the Roadmap & Backlog. Triggered by Notion automation when the Owner field changes on a Page Registry entry.

warpdotdev Skill

Twice-daily scan of idle pages (6 AM & 6 PM UTC): dispatch builds, notify when pages need prioritization, trigger research for empty backlogs. Runs as the first pass of the cro-monitor cron.

entropy-cloud Bundle

Create roadmaps and mission configs, then drive the mission-driver AI dev-loop engine. mission-driver lives at tools/mission-driver/ — it reads missions/<name>.json and loops CHECK → REVIEW_PLANS → EXEC_PLANS → DRAFT_PLANS → DEEP_AUDIT until the roadmap is done or the audit budget is exhausted. Use this skill when the user wants to: (1) plan a development goal as a roadmap ("create roadmap", "make a roadmap", "new dev goal"); (2) bootstrap a mission config from an existing roadmap ("create mission", "config mission", "draft mission"); (3) launch / resume / monitor a mission ("run mission", "start mission-driver", "continue mission", "mission stuck"); (4) mentions "roadmap", "mission-driver", "dev loop", "auto development", "AGE loop". Trigger words: roadmap, mission, mission-driver, dev loop, draft-mission, list-missions.

pabasara-mahindapala Skill

Generate a self-contained, presentation-ready HTML report from any completed analysis or conversation output. Use after finishing an investigation, security scan, query analysis, or incident analysis when the engineer wants to share findings with a customer or stakeholder as a polished document.

phoebefu6 Bundle

Turn raw marts into a board-ready executive scorecard - define metrics explicitly, validate each against the naive version an analyst ships by accident, then generate a self-contained HTML scorecard where every number is computed, not hand-typed. Use when asked to "build a scorecard", "executive/board dashboard", "KPI report", "define our metrics", "revenue dashboard", "what do we put in front of the board", "metric definitions", or when a stakeholder wants numbers they can trust and audit. Walks the 6-step pipeline - input, sample data, objective, find-skills, build (metric definitions + validation + HTML scorecard), expert review - and outputs an auditable scorecard, not a pile of aggregates.

pingidentity Bundle

Guide for building web apps with the Ping Orchestration JavaScript SDK (also referred to as the Ping Identity JavaScript SDK, formerly the ForgeRock JavaScript SDK / @forgerock/javascript-sdk; npm packages: `@forgerock/journey-client`, `@forgerock/davinci-client`, `@forgerock/oidc-client`). Use when the user wants to add Ping authentication to a web app — phrases like "add Ping auth to my web app", "use PingOne in React", "set up Journey in JavaScript", "build a Ping login page", "use DaVinci in my SPA", "integrate @forgerock/journey-client", "set up @forgerock/davinci-client", "migrate from @forgerock/javascript-sdk to the new SDK", or "add OIDC login to my React app". Detects framework (React active; Angular, Vue, vanilla JS on the roadmap), collects shared config, delegates Journey to ping-orchestration-reactjs-journey-sdk and DaVinci to ping-orchestration-reactjs-davinci-sdk, and handles OIDC centralized login inline. Covers both new sample app creation and integrating into an existing project.

posthog Bundle

A starter kit for running one area of ongoing work as a living skill that agents and people share across sessions: a numbered issues/ backlog with an index, ideas/, open-prs.md, a sectioned HANDOVER.md each session overwrites, environment-notes.md for durable gotchas, field-feedback.md, roadmap.md, and a rolling-window CHANGELOG.md. It is the layout PostHog uses internally for its own scouts and self-driving backlogs, with a walkthrough of how those hubs are worked. Install it once per workstream (bind the project name and the changelog window), then use the installed skill to log an issue or idea, record or clear a PR, resume work in a fresh session, or triage the backlog. Trigger on 'log an issue for <project>', 'what is the state of <project>', 'resume <project> work', 'track this for <project>', 'end of session handover'.

amazingphotovideo Skill

Build pre-appointment discovery flows for buyer, seller, investor, and open-house leads so agents enter meetings with complete context.

arrowshq Skill

Arrows post-call workflow. Run this right after any sales call. Reads your call recording, CRM, email, and the seller's website to generate up to three things: a follow-up email draft, a copyable CRM note (no CRM writes), and relevant resources to send. Only includes sections that can be filled with verifiable information — drops anything where data is missing and flags the discovery gap. Say 'Run my Arrows post-call' or 'Run the Arrows post-call on [company]' to start. Also responds to 'run post-call on [company]'.

arrowshq Skill

Arrows deal nudge. Two modes: (1) nudge a specific deal ('Run the Arrows deal nudge on Pendo') or (2) scan your pipeline for deals that need attention ('Run the Arrows deal nudge on my pipeline'). Pulls deal context, strategizes a play (send a resource, tap a prior topic, loop in a stakeholder, acknowledge a broken commitment), and drafts a send-ready nudge email. Respects your nudge preferences from project instructions. Say 'Run the Arrows deal nudge on [company]' or 'Run the Arrows deal nudge on my pipeline' to start. Also responds to 'nudge [company]' and 'which deals need a nudge?'

arrowshq Skill

Arrows pre-call prep. Quick, focused deep dive on one specific upcoming call. Pulls only the relevant context (deal history if any, attendees, past conversations across channels, open commitments, discovery gaps) and gives you a brief you can scan in 60 seconds right before the meeting. Works for first calls (form submissions, intro emails, meeting booking context) and for follow-up calls (every prior call, note, email, chat). Different from the daily brief — this is for ONE call, not your whole day. Say 'Run the Arrows meeting prep for [company]' to start. Also responds to 'prep me for my call with [company]' and 'pre-call prep on [company]'.

cookieshaha Bundle

PRD 写作工作流：从功能大纲同时生成本地 Markdown PRD 与飞书云文档 PRD 骨架，按统一章节规范（§1 版本信息 / §2 变更日志 / §3 整体说明 / §4 需求详细设计 / §5 功能清单 / §6 Open Questions / §7 附录）输出，便于后续用 lark-workflow-prd-sync 同步、lark-workflow-prd-to-userstory 拆成 User Story。当用户需要创建新 PRD、写 PRD、PRD 初稿、PRD 骨架、write-a-prd、起草产品需求文档时使用。

cookieshaha Bundle

发版公告自动生成：从 PRD 飞书文档提取更新内容，生成三个版本的发版公告（简略版、详细中文版、详细英文版），并创建为飞书云文档（用户名下）。当用户需要生成发版公告、版本发布说明、release notes、发版简报时使用。

cookieshaha Skill

PRD 文档工作流：从飞书下载 PRD → 本地 .md 落盘（含 YAML frontmatter）→ 提取评论为 Open Questions → 依据 §4 需求详细设计更新 §3.1 整体变更与 §5 功能清单 → 将三个章节增量同步回飞书（严禁覆盖 §4 需求详细设计）。支持增量同步：识别评论 is_solved 状态，删除本地已解决评论标记并更新 OQ 状态；按变更大小自动维护版本号（小版本 +0.1 / 大版本 +1.0）。触发关键词：prd sync / prd同步 / 从飞书下载PRD / 更新PRD

cookieshaha Bundle

PRD 转 User Story 工作流：把 PRD §5 功能清单生成 P0 User Story、写入飞书需求矩阵 Base 表，并同步到飞书项目对应版本中。当用户需要从 PRD 同步需求到飞书需求矩阵和飞书项目、prd-to-userstory、把功能清单转成 user story、按版本批量创建需求、对齐需求矩阵与需求管理时使用。

dahanitamar Bundle

Stage 2 of 6 in the spec chain. Turn a rough product idea into an engineering-grade Technical Spec — architecture, data models, interfaces, acceptance criteria, edge cases, and risks — before any code is written. Use when someone describes something they want to build ("I want an app that…", "I'm thinking of building…", "how should I structure a…"), asks for a PRD, tech spec, architecture doc, system design, data model, or stack recommendation, or is starting a new project or major feature from only a loose description. Also use to reverse-engineer a spec from an existing codebase before a large change. Produces one Markdown file meant to live in the repo and be loaded as project context.

simonrw Skill

Create a PRD through user interview, codebase exploration, and module design, then submit as a Linear issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.

simonrw Skill

Break a PRD into independently-grabbable Linear sub-issues using tracer-bullet vertical slices. Use when user wants to convert a PRD to issues, create implementation tickets, or break down a PRD into work items.

awjackson2 Skill

Use to turn a large goal into a well-chunked umbrella roadmap before any phase work starts. Trigger when the user hands over a big feature or project and says "break this down", "decompose this", "chunk this into phases", "plan out this whole thing", "make a roadmap", or when phase-loop needs an umbrella to drive. Produces the MAJOR.0.0 umbrella plan — the ordered roadmap of Minors and Patches — applying a quality bar (tiny independently-testable steps, dependency ordering, risk tags, right-sizing) and leaving numbering room so future work can append near its theme. Hands off to phase-loop (multi-phase) or phase-tracker (single Minor).

terryyin Skill

Reviews one completed or in-progress plan execution against its original story, aggregate commit set, current whole-product architecture, and test suite. Use for an execution retrospective, product review, or backlog recommendation even when cleanup removed the plan or the user supplies only a partial reference. `--skip-process` and `--skip-product` omit those reviews independently. May plan unresolved implementation findings, record supported process findings in `DearDough.md`, and recommend product work; never implements them.

ericgandrade Bundle

This skill should be used when the user needs to run continuous discovery to find problems worth solving. Use when setting up weekly discovery rhythm, building Opportunity Solution Trees, creating interview snapshots, exploring solutions, or testing assumptions before committing engineering resources.

ericgandrade Bundle

This skill should be used when the user needs to structure what to build and when by converting discovery opportunities into prioritized bets and roadmaps. Use when organizing product capability blocks, writing solution briefs, planning quarterly cycles, or communicating product direction without false precision.