Product & Planning

encod3d-sec Skill

External recon and OSINT pipeline - subdomain enum, live host discovery, URL crawl, JS analysis, nuclei scan. Outputs to Attack-surface.md and scope/. Queries wiki before each phase. Use when starting recon on any target.

paulingram Skill

Use when entering Phase −1 of the architect-team pipeline, when any agent needs to consult codebase or integration maps, or when checking whether existing maps need refresh. Defines codebase discovery rules, the per-codebase ralph-loop with 3 reviewers (exit string "CODEBASE MAP COMPLETE"), frontend detection that triggers the route-mapper, and the integration ralph-loop with 3 explorers + master-synthesizer (exit string "INTEGRATION MAP COMPLETE"). Handles re-entry freshness checks against git commit timestamps.

paulingram Skill

Discovery-phase verification discipline that — for every frontend codebase in scope at Phase −1B — cross-walks ROUTE_MAP.md × DESIGN_MAP.md × INTEGRATION_MAP.md and produces an explicit per-element intuition of what action each control takes and which endpoint it likely calls, with confidence high / medium / low / unknown, evidence, and a precise ambiguity question for every low-confidence item. The end of Phase −1 fires a bulk-verify gate: every low-confidence and unknown element is presented to the user as a single numbered list (`all correct` / a list of incorrect indices / `all incorrect`), then a targeted drill-down resolves only the flagged items. The confirmed intuition map is a binding input to Phase 0 spec authoring and Phase 1 coverage criteria. The Phase −1D bulk-verify is a domain gate (the user-confirmation step IS the feature) and fires regardless of the v0.9.20 process-gates-opt-in rule.

paulingram Skill

Use when authoring a spec or DESIGN_MAP from a mockup, when implementing any screen that renders values, or when reviewing shipped UI — a cross-role discipline for telling a genuine static literal (a fixed label) from sample data standing in for a dynamic, data-bound value. Classify every displayed value static vs. dynamic FROM CONTEXT (its position, its nature, the requirements/design language) — never from the literal itself, since the same string is static in one place and dynamic in another. Mandates that every dynamic value is bound to a named data source rather than shipped as the design's hardcoded sample, and requires escalation to the human when a classification is genuinely ambiguous. Rejects rationalizations like "the design says John Smith so I'll render John Smith."

paulingram Skill

Two-pass discovery of interactive HTML mockups as oracle artifacts. Pass 1 (observation) runs the mockup in headless Chrome and records every interactive element's observed behavior; Pass 2 (intent inference) flags semantic-vs-observed mismatches (e.g., "Logout" button routing to /dashboard) and surfaces them at the existing Phase −1D bulk-verify gate so the user-resolved intent — not the mockup's literal behavior — becomes the binding contract. Adds a 6th spec_shape to oracle-deriver, a new interaction-observer agent, an INTENT-INFERENCE mode to interaction-intuiter, a new Layer 3 tool (verify-interactions-honored), and an OPTIONAL schema v7 field.

cyz26 Bundle

Use when Feishu/Lark platform work needs one fail-closed entry point backed by lark-cli and compact FeishuOps delegation: docs, IM, contacts, calendar, meetings, Sheets, Base, Wiki, Drive, whiteboard, approvals, attendance, mail, OKR, slides, tasks, apps, events, notes, live VC agents, workflows, auth/profile operations, or explicit OpenAPI fallback.

dauquangthanh Bundle

Maintains the product backlog — an ordered markdown list of user stories / items keyed by priority, with lightweight estimates, acceptance-criteria pointers, and status. Drafts and re-orders the list from priorities the user states; does not decide priority or commit a team to deliver. Use when managing a product backlog, adding user stories, reprioritising features, or preparing for sprint planning.

dauquangthanh Bundle

Drafts a product roadmap grouping backlog items into release windows (Now / Next / Later or date-based). Proposes windows from the backlog's priority order; the user (product-owner) confirms. Does not commit a team to a delivery date. Use when planning product direction, grouping features into releases, or creating a Now / Next / Later roadmap view.

dauquangthanh Bundle

Triages open bugs into fix-now / next-sprint / defer / won't-fix buckets from severity + priority + age + business cost. Produces a dated triage list the bug-fixer / PO can act on. Use when prioritising a bug backlog, deciding what to fix next, or preparing for a bug-fix sprint.

marvin-lijunzan Bundle

Comprehensive academic research lifecycle toolkit: literature discovery, research question formulation, experiment tracking, LaTeX manuscript writing, citation compliance, and simulated peer-review.

marvin-lijunzan Skill

Master unified academic research inspection & improvement suite. Triggers on phrases like '调用我们科研skills来检查一下', '科研skills审查', '用科研skills改一下'. Integrates: 1) End-to-End Autonomous Experimentation & Review (AI Scientist, ARIS, Karpathy Autoresearch), 2) Deep Literature Discovery & Anti-Hallucination Citation Verification (STORM, Cite-Verify, Reference-Checker), 3) Top-Tier Manuscript Architecture & De-AI Humanization (PaperSpine, Benchmark-Paper-Template, Nature-Skills, CCC-Author-Guide, Human-Writing), and 4) Publication-Grade Visual Diagnostics (Academic-Figure, Scipilot-Figure, Nature-Figure).

marvin-lijunzan Skill

Auto-Research-in-Sleep (ARIS): Autonomous machine learning and academic research workflow. Supports overnight multi-agent idea discovery, code execution, adversarial cross-model review loops, narrative report synthesis, and LaTeX submission rebuttal.

ferroxlabs Skill

Build a long-form About page that converts visitors into subscribers and buyers - not a bio expanded into paragraphs, but a full DR asset that hooks with the reader's problem, tells a story-of-discovery, proves the path with results, and closes with an explicit next step. Outputs a structured content brief plus paste-ready section copy. Use when a website About page exists but reads like a résumé, career history, or humble-brag parade - or when building a new About page from scratch for a personal brand, consultant, coach, or founder. Not for a bio (use content-bio) and not for a full sales page (use convert-sales-page) - the About page is the trust asset in the awareness layer, not the conversion layer.

johnqtcg Bundle

Use when the user asks for unit tests (e.g, "单元测试", "unit test"), wants to add/fix Go tests, wants table-driven and subtest organization, or wants to enforce a minimum coverage gate (default 80% for logic packages). Prioritize bug discovery (especially boundary, mapping loss, and concurrency defects) over test volume. Do NOT use for benchmarks, fuzz tests, integration tests, E2E tests, load tests, or mock generation.

johnqtcg Bundle

Use when the user wants help finding information through Google or Google-style web search and expects more than raw links. Handle current facts, public-information lookups, official documents, tutorials, reports, tools, materials, or source discovery by classifying the search goal, generating precise queries, executing search, ranking sources, cross-checking key claims, and returning a concise conclusion plus reusable search strings. Also use for programmer-specific searches (error debugging, official docs, GitHub code search, Stack Overflow, RFC lookup, benchmarks).

creatorland Skill

Standing discovery profile re-run on demand — save your recurring search criteria (briefs, lookalike seeds, filters) once as a scout profile, then say "run my scout" anytime to get a diff report of NEW creators who entered your search space since last run. Use when the user says "set up a talent scout", "watch this space for new creators", "run my scout", "any new creators since last time", or wants recurring discovery without re-explaining the brief. Deliverable is a what's-new diff report.

dauquangthanh Bundle

Drafts a sprint plan — sprint goal, candidate backlog items, capacity arithmetic, and risk flags — from the backlog + a user-provided velocity. Prepares the artefact; the team owns the commitment. Does not facilitate a planning meeting. Use when planning a sprint, selecting backlog items for a sprint, or calculating team capacity.

fbakiyev Skill

Изучение незнакомого репозитория или технического проекта перед реализацией: точки входа, команды проверки, границы выполнения и существенные ограничения. Применяйте при нехватке контекста проекта, а не как обязательный этап самостоятельной офисной задачи.

fbakiyev Skill

Создание или уточнение запрошенного бэклога либо структуры работ с критериями приёмки, зависимостями и приоритетами. Применяйте для управления несколькими рабочими пунктами; одной хорошо определённой задаче бэклог не нужен.

nexadevapp Bundle

Generates the project overview — a browsable page that shows every cluster, which of its use cases are delivered, and which are not, plus the technical tasks that support each cluster and the umbrella tasks that support the whole system. Each use case links to its specification, its design, and its acceptance tests. Use when the user asks to "update the dashboard", "generate the overview", "show project status", "what is delivered", "regenerate the report", or mentions the project dashboard, delivery status, or a stakeholder report.

nexadevapp Bundle

Gathers, organizes, and documents software requirements into structured catalogs with functional requirements (user stories), non-functional requirements (measurable quality attributes), and constraints. Use when the user asks to "write requirements", "create a PRD", "gather requirements", "document feature specs", "write user stories", "define NFRs", "list constraints", or mentions requirements catalog, requirements analysis, product requirements document, or feature specification.

nexadevapp Bundle

Creates structured change request documents for intentional modifications to already-implemented use cases. Use when the user asks to "create a change request", "log a CR", "document a change", or describes a stakeholder-requested modification to existing behavior (e.g., renaming a field, changing validation rules, restructuring data). A change request always references exactly one use case and describes only the delta — the original use case remains immutable.

mindgoblinstudios Bundle

Wick (Moth of Rabbit Holes): A tiny moth entranced by light. Scattered curiosity settles into deep focus, following an idea through to discovery.

davie521 Skill

Turn the current conversation context into a PRD, saved as a local markdown file by default (published to the project issue tracker only when the user asks). Use when user wants to create a PRD from the current context.

creatorland Skill

Design an outreach campaign as a guided interview — collect the structured brief (archetype, on-behalf-of identity, offer, ask, exclusions, proof domains), preview the exact email the matchmaker will send, and only then launch. Use when the user says "set up an outreach campaign", "design my campaign", "I want to reach creators about [offer/perk/event/collab]", "preview the outreach email", or arrives with a promo/gifting/event/collab idea that is not yet a runnable brief. Ends with an approved preview handed to request_creator_connection (or cast-and-connect for discovery + reach).

creatorland Skill

Cast with NO brief — start from just a brand name. Profile the brand's existing affiliated creators (pro affiliation data), lookalike off the best, and propose a "based on who already works with you" slate. Use when the user has only a brand, no brief or seed — "who should [brand] work with", "find creators, we have no brief", "build a slate from scratch for [brand]", or "discover talent from our existing partners". Deliverable is an affiliation-grounded discovery slate. Pro plan required.

imtangyujing Bundle

飞书 OKR：管理目标与关键结果。查看和编辑 OKR 周期、目标（Objective）、关键结果（Key Result）、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。

hack23 Skill

Product backlog management, user stories, acceptance criteria, sprint planning, and stakeholder management for agile development

chocholous Skill

Scrape e-commerce data for pricing, reviews, bestsellers, and seller discovery across 30+ platforms including Amazon, Walmart, eBay, Shopify, WooCommerce, and more. Use when user asks about product prices, competitor analysis, store scraping, tech stack detection, food delivery, real estate, or marketplace intelligence.

chocholous Skill

Search and verify newly collected public Meta Threads data with Apify. Use when a user asks to search Threads posts by keyword or hashtag, compare top and recent public results, collect public posts from known Threads accounts, or discover public Threads profiles by niche or local phrase. Do not use for reply trees, private or login-only content, publishing or account actions, non-Threads platforms, generic programming threads, hidden contact discovery, exhaustive coverage claims, or analysis that must use only an existing local file. Sentiment and themes are downstream analysis, not scraped fields.

chocholous Bundle

Find genuine google flights deals from a home airport with the Apify Google Flights Deals API Actor (johnvc/google-flights-deals-api). Give one IATA code and get the thirty cheapest destinations back as rows, each carrying the fare, what that route typically costs, the saving between them, and an is_below_typical flag. That flag is the point, because a cheap fare and a good deal are different things, and most of a cheapest-first list is short-haul that is cheap because it is close, not because the price is unusual. There is no arrival airport, the feed answers where can I go cheaply rather than what does this route cost. Filter by stops, cabin, budget, or trip length. Use when the user wants flight deals, cheap flights from an airport, fare drop discovery, or destination inspiration priced against a baseline. Pay per deal returned, MCP-ready for Claude and other AI agents.

chocholous Bundle

Score and enrich a CSV of B2B leads using Apify Actors. Takes a CSV with company URLs, free-text scoring rules, and an enrichment preference; runs BuiltWith (tech stack), Website Content Crawler (content classification), and Contact Info Scraper (company metadata) for scoring; enriches with either department-specific contacts (Contact Info Scraper + Bulk Email Finder fallback) or copywriter discovery (Google Search Scraper → AI Web Scraper → Bulk Email Finder). Outputs an enriched CSV with a numeric score and a per-lead outreach_hook column that personalizes cold email copy (e.g. "uses Shopify → send Shopify install guide"). Use when user asks to score leads, qualify leads, enrich a lead list, detect a company's tech stack for outreach, find marketing/sales/engineering contacts at a list of companies, hunt down blog copywriters for guest-post pitches, personalize cold email at scale, or turn a raw domain list into a ready-to-pitch account list.

chocholous Skill

Research YouTube channels, videos, Shorts, playlists, search results, comments, and creator positioning using Apify Actors. Use when the user asks for YouTube competitor analysis, creator research, content strategy, keyword/video discovery, audience comment mining, Shorts analysis, sponsor/brand mention discovery, or channel performance benchmarking.

chocholous Skill

Turn App Store and Google Play reviews into product-roadmap intelligence by chaining Apify Actors for iOS reviews, Android reviews, SERP-based app discovery, and website or help-center crawling. Use when the user asks to analyze mobile app reviews, compare app competitors, find bugs or feature requests in reviews, prioritize a mobile roadmap, monitor release feedback, audit ASO sentiment, or explain why an app's ratings changed across iOS and Android.

iblai Bundle

Manage an ibl.ai organization's RBAC via the platform API — roles (actions + data actions), policies, groups, permission checks, resource/action discovery, agent and team access sharing, bulk user policies, and student creation/LLM-access toggles. Org-wide access control. Use to define who can do what.

yenhao-huang Bundle

Create or refine repository governance docs through discussion with the user. Use when Codex needs to help set up a repo, define AGENTS.md and docs/rules including Git workflow rules, establish human-owned roadmap and changelog docs, define issue acceptance demos, or teach repository management.