Product & Planning

metrikia-io Bundle

Turn a month of ad exports into a client-ready performance report - the numbers, a written explanation of what changed and why, and an honest note on what the numbers can be trusted for. Use this whenever someone needs to report ad performance to a client or a boss, prepare a monthly or weekly marketing report, explain what happened across Meta/Google/TikTok and the store, write up campaign results for a non-technical stakeholder, or replace the manual pull-into-a-deck reporting a VA does by hand. Also use it when someone says their reporting takes too long, that clients don't understand the numbers, or asks how to present ad results credibly. Produces a print-ready report whose written analysis reads like a senior media buyer wrote it, because the model writes it from the actual figures.

mgicoda Bundle

Sentiment & Reputation Guard — comprehensive brand reputation audit through search engines and LLM perception analysis. Analyzes online reviews, forums, news, and social media to score brand reputation 0-100 across four dimensions: Search Sentiment, SERP Control, Platform Presence, and LLM Sentiment. Auto-detects industry niche (crypto, iGaming, SaaS, agency, ecommerce, fintech, etc.) and tailors the query matrix accordingly. Generates a visual inline HTML report with a prioritized recommendations roadmap (Quick Wins / Medium-term / Strategic). Use when user: - Wants a brand reputation audit, SERM analysis, ORM check, or reputation score - Asks "what do people say about [brand]", "check reputation of [brand]" - Asks about negative reviews, bad search results, brand sentiment, online complaints - Wants to know how AI systems (ChatGPT, Claude, Perplexity) perceive a brand - Asks about brand monitoring, trust score, complaint analysis, review analysis - Wants to compare two brands' online reputation side-by-side

vibheksoni Skill

Use this skill when you need to install, configure, start, verify, or hand off SSH ~ Api to another agent. It covers local bootstrap, config creation, startup, OpenAPI discovery, and the correct workflow for using the API against a Linux VPS.

vltansky Bundle

Analyze an existing product, then grill, challenge, and push back on it to make it sharper — or shape a new product idea from scratch. Use when the user wants to pressure-test, improve, or stress-test a product, decision, feature, spec, or PRD, or asks to grill a product.

waveinflu Bundle

Look up publicly discoverable contact data for up to 50 Instagram, TikTok, or YouTube creators with bounded concurrent WaveInflu requests. Use when a user supplies supported creator profile URLs and asks for public emails or contact links. Returned contact data is not ownership-verified. Do not use for private or guessed personal email discovery.

wenyuchiou Bundle

Operating harness for working on the method-harness-compiler project (or reviewing its artifacts). Use when starting ANY task on that project — phase reviews, tool discovery, PR review, eval design, memory updates, runtime export, repo maintenance, or A/B test design. Routes the agent to a minimal per-task file set instead of whole-repo reading. For work on ANY OTHER project, activate only when the task is long / multi-step, multi-agent, expensive-if-wrong, makes a completion claim (done / passing / fixed / ready / safe / staged), or touches governance (permissions, hooks, cron, CI, routing) — the portable entry is then core/GLOBAL_BOOTSTRAP.md. Skip for one-line / typo / format edits and pure capability asks.

withvibe Skill

Help a developer build a new WithVibe plugin from scratch — manifest.yaml, Dockerfile, HTTP server with health/UI/MCP endpoints, optional shared-postgres storage. Trigger when the user asks to build, scaffold, create, or write a WithVibe plugin (e.g. "I want to build a plugin for withvibe", "scaffold a withvibe plugin", "how do I add a plugin to withvibe", "write a roadmap-like plugin for X"). Walks through scope decisions (env vs workspace), storage, UI, MCP tools, builds the container, and installs it via the workspace admin Plugins page.

wonder-image Bundle

Work inside the wonder-image/app framework package — the Composer library at github.com/wonder-image/app. This is the framework core, not a site that consumes it. TRIGGER when: - the repo's composer.json declares `"name": "wonder-image/app"` - editing files under `class/App/*`, `app/config/routes/*`, `app/http/*`, `app/bootstrap/*`, `app/middleware/*`, `class/App/Module/*`, `class/Console/*` - editing shared UI components under `class/Elements/Components/*`, media under `class/Elements/Media/*`, or their renderers under `class/Themes/{Wonder,Bootstrap}/*` - modifying Model, Resource, PageSchema, Repeater, ModelRegistry, ResourceRegistry, ResourceRouteRegistrar, Credentials, or the `wonder-image.php` entrypoint - changing bootstrap order, `ROOT`/`.env` resolution, module discovery, generated backend/API CRUD routes, or `php forge ...` command sources - updating `docs/app/*` for bootstrap, architecture, routing, or layout conventions SKIP when: - the repo is a Wonder site that installs wonder-image/app under `v

woocommerce Bundle

Audit a fixed cohort of inactive WooCommerce pull requests against current trunk, linked issues, review history, repository labels, and representative user flows, then produce evidence-backed actions and a private checklist report. Use for stale or backlog PR cohort reviews, not ordinary single-PR code review.

wufei-png Bundle

Inspect, search, diagnose, and export local OpenCode SQLite sessions across projects. Use for session discovery, transcript reading, literal content search, live schema inspection, and safe Markdown or JSONL archives.

juvojustin Skill

CLI tool for the fluent-wp-client package that discovers WordPress REST API schemas and generates TypeScript/Zod/JSON Schema code artifacts. Use this skill whenever a user wants to run the CLI, generate schemas from a WordPress site, produce TypeScript types or Zod validators for WordPress resources, set up build-time schema generation, or automate schema discovery in CI. Triggers: "fluent-wp-client cli", "generate WordPress schemas", "wp schemas command", "npx fluent-wp-client", "generate Zod from WordPress", "WordPress TypeScript types codegen", "schema generation from WordPress", "wp-schemas.ts", "WordPress REST codegen", "build-time WordPress types".

kingbootoshi Bundle

Turns a brief, discussion, or PRD into a Locked Intent Boundary - a small human-signed artifact that fixes intent before planning, so an instruction-following agent cannot silently redefine the goal or grade itself against its own rewrite. ONE mechanism for every task - destination deltas, invariants, non-substitutions, authorized change rights, proofs, stop/relock - with rigor scaled to blast radius, not a destructive/additive split. Use when turning research + discussion into a master PRD, before phasing/Linear issues, or for any build/remove/replace/migrate/refactor task. Triggers - "intent contract", "/intent-contract", "intent boundary", "lock the boundary", "write the master PRD", "before we plan this", "is this remove or replace". Derives the phased plan and runs a change-surface audit where every diff op (add/modify/delete/rename) must map to a signed authorization.

xmzdesign Skill

辅助书写高质量技术方案文档。用户要写技术方案、技术设计、方案评审、研发设计文档、接口方案、库表变更方案、上线方案、交付执行方案，或希望把 PRD/需求/代码上下文整理成可评审方案时，必须使用本 skill。它会先识别需求复杂度，按 L0 交付执行单、L1 轻量技术方案、L2 标准技术方案、L3 深度评审方案选择输出结构；再结合代码、领域词汇、ADR、接口、SQL schema、分布式高并发与上线约束进行必要澄清，避免简单需求被完整模板拖慢，也避免高风险需求被轻量化。

ydbondt Skill

Use when working the Shkills roadmap — picking up the next ticket, starting the next roadmap item, asking what to work on next, or finishing and closing out a roadmap ticket. Triggers on "next roadmap ticket", "work the roadmap", "what's next", "pick up the next item".

yysun Bundle

Plan, coordinate, execute, track, review, and report product-delivery work as folder-native .projects state. Use to manage outcomes, tasks, dependencies, blockers, evidence, executors, impact, and stakeholder reporting; do not use for QA suite, case, or run management under .tests.

zafer-liu Bundle

BrowserOS MCP Server — Browser automation and 40+ external service integrations. ## Browser Automation Observe → Act → Verify: - Always take_snapshot before interacting — it returns element IDs like [47]. - Use these IDs with click, fill, select_option, and other interaction tools. - After any navigation, element IDs become invalid — take a new snapshot. - After actions, verify the result succeeded before continuing. Obstacle handling: - Cookie banners, popups → dismiss and continue. - Login gates → notify user; proceed if credentials provided. - CAPTCHA, 2FA → pause and ask user to resolve manually. Error recovery: - Element not found → scroll down, re-snapshot, retry. - After 2 failed attempts → describe the blocker and ask user for guidance. ## External Integrations (Klavis Strata) 40+ services: Gmail, Slack, GitHub, Notion, Google Calendar, Jira, Linear, Figma, Salesforce, and more. Progressive discovery — do not guess action names: 1. discover_server_categories_or_actions → always start here. 2. get_cate

viniciusmq25 Skill

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

mithunyc Bundle

End-to-end enterprise-grade AI software delivery workflow. The master CTO orchestrator for spec-to-production development. Prefer explicit invocation with "Use enterprise-ai-dev as my master CTO orchestrator for this repo." Treat /orchestrator or similar natural-language phrasing as best-effort aliasing, not a guaranteed platform command. Use when asked to build, fix, refactor, launch, review, harden, or operate software — especially when the request involves: enterprise-grade, production-ready, brownfield project, new project, PRD, architecture, TDD, QA, security, deployment, or release. Automatically selects GREENFIELD, BROWNFIELD, GOVERNED, REVIEW_ONLY, RELEASE, or AUTONOMOUS_LOOP profile. Uses Buildloop runtime tools only when they are present in the current repo.

akarachen Bundle

Interrogate a proposed feature before implementation by studying the repository and all project documentation, then asking one product or technical question at a time until intent, scope, acceptance criteria, boundaries, failure modes, and trade-offs are resolved. Use when a user describes a feature idea, asks to clarify or design a feature, wants product and technical requirements challenged, or needs the resulting decisions recorded in docs/prd, docs/adr, and docs/spec.md.

pearlthoughts Skill

Use this when user requests architectural analysis, migration planning, or technical debt assessment. Provides 6-layer framework: system structure, domain model, design patterns, technical debt, modernization strategy, and DDD analysis. Apply when user asks for architecture review, refactoring strategy, or system modernization roadmap

garabed96 Bundle

Creates and executes a durable gated product decision in Obsidian when user behavior, scope, visual direction, or staged acceptance is unsettled. Use for consequential product ambiguity requiring approval; not for settled technical work, debugging, or ordinary implementation.

garabed96 Bundle

Executes a settled technical outcome through the smallest complete vertical slice with bounded context and evidence. Use for implementation, bugs, refactors, review feedback, focused QA, or verification when product behavior and acceptance are already decided; escalate unresolved product decisions to ctx-prd.

mr-karan Bundle

Query logs from the terminal with the Logchef CLI. Covers LogchefQL search filters (`query`, `tail`), raw ClickHouse SQL and VictoriaLogs LogsQL (`sql`), seeing the generated query without running it (`explain`), field and value discovery (`fields`, `schema`), counts-over-time (`histogram`), finding which source holds a service/host/message (`find`), saved queries and collections, live follow, output formats and piping to jq, config/contexts/auth, and troubleshooting query errors. Use whenever the user mentions logchef, LogchefQL, LogsQL, log search, or wants to investigate logs from a ClickHouse- or VictoriaLogs-backed source.

product-on-purpose Bundle

Grades and reviews a product document that already exists against the researched rubric for its own document type, returning an itemized report card that quotes the document's own text as evidence, names the anti-patterns it hit, and lists the three fixes worth an hour. Use when someone asks for a review, a critique, a quality check, a second opinion, or a score on a PRD, user stories, acceptance criteria, an ADR, an RFC, a software design document, a test plan, a test case, a bug report, a risk register, a RAID log, a KPI dashboard definition, OKRs, a product vision, strategy or roadmap, a business case, a user persona, a definition of done, a runbook, an incident postmortem, retrospective notes, a status report, a backlog, or release notes.

product-on-purpose Bundle

Selects and fills a researched product-document template from a 27-bundle library covering the full product lifecycle, then grades the result against that document type's own rubric. Use when writing a PRD, user stories, acceptance criteria, a risk register, a RAID log, a KPI dashboard definition, a test plan, a test case, a bug report, an ADR, an RFC, a software design document, a product vision, strategy, roadmap, OKRs, a business case, a user persona, a definition of done, a runbook, an incident postmortem, sprint retrospective notes, a status report, a product or sprint backlog, or release notes. Each bundle carries a lean and a full variant, a worked example, and the research log every claim traces to.

quocbao201104 Bundle

Evidence-informed marketing decisions and execution for AI agents. Use for customer and market research, segmentation/ICP/JTBD, positioning and value, brand identity/visual systems, pricing/packaging and commercial design, messaging/copy and critique, landing pages, email, social/platform content, paid media, commerce/product discovery, search/discovery, funnel diagnosis, experiments, localization, and postmortems. Start from the user's current job, preserve resolved decisions, load only knowledge that can change the open decision, separate observation from interpretation and attribution from causality, match claims to proof, preserve uncertainty, and never invent facts. Do not use for generic writing or non-marketing tasks.

serverless Bundle

Host Model Context Protocol (MCP) servers on AWS with the Serverless Framework's built-in MCP support — an official-SDK server module deployed to AWS Lambda behind a streaming API Gateway REST endpoint, with gateway access control, OAuth protected-resource discovery, packaging and elicitation state handled for you. Use whenever the user wants to deploy, host, secure or debug an MCP server on AWS or Lambda, writes or edits an `mcp:` block in serverless.yml, exposes tools, resources or prompts to Claude or another AI client over HTTP, or hits an `MCP_*` configuration error (MCP_UNSUPPORTED_NODE_RUNTIME, MCP_FUNCTION_NAME_COLLISION, MCP_INVALID_STATE_ARN, and the rest). Trigger even when neither "Serverless Framework" nor "MCP" is named but the user describes putting their own tools in front of an AI client over an HTTPS endpoint.

sterlingchin Skill

Use when MARVIN is asked to build, fix, debug, review, or ship software. Routes to gstack development workflow skills. Handles gstack bootstrap if not installed. Manages PRD decomposition for large projects. Triggers on: build a feature, fix a bug, review code, implement a PRD, ship this, debug this, create an app/tool/service/CLI/API. Does NOT trigger on: content ideas, event planning, campaigns, meetups, or any non-software intent. If ambiguous, ask.

stickystyle Bundle

Index-based file discovery using ABOUTME headers. Use INSTEAD of grep or Explore agent when searching for files by purpose or feature. Faster and more accurate than scanning code. Invoke this skill when user asks "which files handle X", "where is Y implemented", or when you need to find files related to a feature or task.

vechain Skill

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

vechain Skill

Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.

prometheas-labs Bundle

Use when the user asks to create a feature, write a PRD or TRD, add user stories, write scenarios, create acceptance criteria, plan implementation, initialize product docs, set up product documentation, create, approve, amend, or validate a Product Constitution, run the Constitution Grill, create or maintain Product Vision, run a Vision Grill, or work anywhere in the product development lifecycle from project setup through implementation planning.

ragnos-labs Bundle

Search the web with Exa through a credential-safe, deterministic JSON CLI built on Exa's official Python SDK. Use when an agent needs Exa web research, source discovery, domain-filtered searches, or a local Exa CLI that receives EXA_API_KEY from a broker or environment without placing the key on the command line.

rcarmo Skill

Use Memento shared memory effectively through MCP. Covers discovery, scoped search and reading, inventory and manifest comparison, proposals and curation, assets and shared skills, namespace policies, retry reconciliation, and the trusted graph debugger. Use whenever an agent needs to recall, file, compare, review, or diagnose durable shared knowledge.

rizsotto Skill

Triage a GitHub issue for rprof — classify it against project scope and the requirements, decide the next action (bug fix, new requirement, rejected direction, or question), and propose labels. Use when the user asks to triage an issue, label issues, or work through the issue backlog.

rodovalhofs Bundle

Evidence-based skill router and meta-orchestrator. Use when the user invokes $maestro or /maestro, asks which installed skills fit a task, or wants a dependency graph for work spanning specialist skills. Uses local retrieval, content review and targeted remote discovery when local capabilities fall short.