Product & Planning

hexabot-ai Bundle

Create, scaffold, implement, review, debug, document, and improve Hexabot v3 messaging channel extensions, including local channels and npm `hexabot-channel-*` packages; HTTP webhook, Socket.IO, and SDK/Gateway transports; zod source settings and payload schemas; `SubscriberChannelDict` typing; inbound events and decoders; outbound encoders and capabilities; webhook authentication; subscriber profiles; attachments; lifecycle and health checks; dynamic discovery; packaging; and tests. Use when adapting an external messaging platform to Hexabot. Do not use for generic NestJS integrations, workflow YAML, standalone API clients, chatbot copywriting, frontend-only chat widgets, or non-Hexabot messaging adapters unless channel implementation is required.

hodlxxi Bundle

Read-only-by-default integration guide for HODLXXI / UBID Bitcoin-native identity discovery, OAuth2/OIDC metadata, LNURL-Auth boundaries, JWT verification guidance, and explicit operator-approved agent handoff.

idealley Bundle

Helpers to discover, rank, and invoke repository symbols from natural language with minimal context.

iftechio Bundle

Use when the user wants to discover, evaluate, or research creators / KOLs / influencers on YouTube, TikTok, or Instagram. Covers creator discovery (natural-language search, lookalikes), creator profiling, audience analysis (age/gender/region/fake-follower rate), bulk email extraction, video analysis, and account setup. Use when the user mentions finding influencers, checking a creator's audience, getting creator emails, analyzing a video, or setting up EasyKOL access.

igorwarzocha Skill

This SKILL provides detailed instructions on how to use the planning plugin tools. MUST be loaded when: Situations: - User asks to create a plan, roadmap, or break down work into steps - User mentions specs, requirements, or standards that need to be documented - User references an existing plan that needs to be read or updated - User asks to mark work as complete or done - User wants to link requirements to a plan - User references a task that matches <available_plans>

ikajakam Bundle

Expert guidance for reconnaissance using subfinder and httpx during penetration testing, including subdomain enumeration, technology detection, and asset discovery

indigokarasu Bundle

Monitors agent gateway logs, cron jobs, skill journals, and OCAS data directories for operational failures. Detects errors, applies safe non-destructive fixes autonomously during quiet hours, and escalates only what it cannot fix. Performs root cause analysis on recurring errors with fix-loop detection and confidence-tier auto promote/demote. Use when: cron jobs fail or show stale errors, gateway logs show repeated error patterns, skill journals have gaps, disk usage exceeds thresholds, MCP servers crash-loop, or after any gateway restart. Keywords: cron health, log analysis, system monitoring, error fingerprinting, auto-repair, fix-loop detection, operational conformance. NOT for OKR trend analysis, skill design evaluation, behavioral lesson extraction, briefing delivery, entity knowledge queries, or social graph queries.

indigokarasu Bundle

Accomplishes tasks that need tools the agent does not have. Plans approaches, fills capability gaps with sandboxed tools, executes within an isolated session. Disposable identity, parallel discovery, incremental checkpoints, graceful degradation. Output: task result plus replay script. No global installs, no real identity, clean state in and out. Do not use for tasks solvable with installed skills, permanent skill installs, skill builds (use Forge), or general web research (use Sift).

indigokarasu Bundle

Behavior-driven taste model built from real consumption signals. Scans email and calendar for consumption data (restaurant reservations, food delivery, hotel bookings, purchases), enriches entities with taste-relevant attributes via Google Maps, and generates discovery-focused recommendations that respect dietary restrictions. Not for generic search, editorial top-10 lists, or ad-copy generation.

indranilbanerjee Bundle

Enterprise AEO strategist for SEO/AEO practitioners on retainer client work. Use for any AEO or AI visibility task: audits, strategy, content briefs, schema markup, query libraries, competitive displacement, monthly reports, llms.txt, roadmaps, CMO explainers, client onboarding, tracking setup, and PR targeting. Covers 12 verticals (Pharma, BFSI, Real Estate, SaaS, Retail, Healthcare, EdTech, Legal, Manufacturing, Hospitality, Automotive, Media) and 8 markets (India, US, UK, UAE, SEA, Europe, Australia, Africa). Trigger for: AEO audit, AEO strategy, content brief, schema markup, query library, competitor AEO, AI Share of Voice, monthly AEO report, llms.txt, "why isn't [brand] in AI answers", "how do I get cited by ChatGPT/Gemini/Perplexity", roadmap, new client onboarding, tracking setup, PR targets, parametric knowledge, RAG optimization, AI crawler access, or any generative engine optimization task.

beevibe-ai Bundle

Architecture Deep Research — scan the current repo, draft a PRD, and run the deep-research loop with citation audits. Use when the user asks you to make an architecture decision, asks "what topology should we use?", says they need to pick between options like vector stores / message queues / retrieval patterns / storage engines / event bus designs, or wants you to think through an architecture choice before writing code. Proactively invoke this skill (do NOT decide directly) when the user describes an architecture choice and wants live, cited research instead of a model-from-memory answer.

belousov-petr Bundle

3-tier project memory (hot/warm/cold) with a unified issues backlog, operation-keyed learnings, generated indexes, immediate capture, and one-shot project initialization under .strata/. Invoke with no argument for rule lookup, "capture" to save a fresh finding/gotcha right away, or "init" to scaffold or migrate existing flat/0.0.1/0.0.2 memory without losing provenance. Used by /strata:save, /strata:load, and /strata:capture as the authoritative source of tier definitions and routing rules.

benjaming Skill

Convert PRDs to GitHub Issues for ralph-tui execution. Creates one issue per user story with native GitHub dependencies and a feature label for grouping. Use when you have a PRD and want to use ralph-tui with GitHub Issues as the task source. Triggers on: create github issues, convert prd to github issues, github issues for ralph, ralph github issues.

benjaminstelzer Bundle

Conduct source-backed web research for current multi-source questions, technology and implementation discovery, or literature synthesis, with GitHub-first Development routing, scholarly-source routing, contradiction checks, and optional durable deep-research artifacts. Use for explicit research, landscape, state-of-the-art, evidence-review, or implementation-option requests that need more than a simple lookup. Do not use for one known page or paper summary, ordinary repository inspection, pure brainstorming, planning, implementation, or wording work.

bladnman Bundle

Launch multi-agent ideation to explore a concept through structured dialogue between a Free Thinker and a Grounder, arbitrated by the team lead, and documented by a Writer. Three actions: Plan (interview + configure), Ideate (depth-aware exploration + conditional production), Continue (versioned resumption with smart discovery). Use "prd" mode to generate a Product Requirements Document from a completed session.

javi22020 Bundle

Run an autonomous iterate-test-replan loop until a multi-step coding task is complete. Use this whenever the user asks Claude Code to work autonomously through a backlog, fix plan, or specification with minimal supervision — phrases like "ralph this", "loop until done", "keep iterating until tests pass", "work autonomously on this", "finish the fix plan", "run until the build is green", or any request that implies sustained unattended progress across many turns. Prefer this skill over ad-hoc "just keep working" loops because it adds explicit exit criteria, a circuit breaker against stuck iterations, subagent isolation for tests and review, and persistent state that survives session compaction.

jed1978 Bundle

DDD Architecture Coach — a decision-making coach spanning DDD (Strategic + Tactical Patterns), AI/LLM engineering (intervention design, risk assessment, fallbacks), software engineering discipline (Clean/Hexagonal Architecture, testing, CI/CD, SBE), and cloud architecture (containers, serverless, observability, cost). Runs a four-phase architecture planning workflow (Phase 1 Domain Discovery / Phase 2 Architecture Design / Phase 3 Implementation Spec / Phase 4 Review & Iterate) and produces Context Maps, Aggregate designs, AI-ADRs, Key Examples (Gherkin), and decision records — NOT code. Supports parallel multi-BC development in team settings — per-BC phase commands (/phase-2 <BC>, /phase-3 <BC>) take BC as an explicit argument and write only to per-BC artifact paths, so multiple developers can work on different BCs in parallel without cursor-file contention. Trigger whenever the user asks for architecture planning or design; discusses Bounded Context, Aggregate, Ubiquitous Language, ADRs, AI intervention dec

jeroenvanwissen Bundle

Analyze an existing codebase or a documented project plan end-to-end and generate a structured, quality-enforced development backlog with prioritized tasks, coding conventions, and multi-agent configuration. Use when: (1) starting work on an existing project, (2) onboarding AI agents to a codebase, (3) creating a prioritized task backlog from scratch, (4) setting up coding standards and quality gates, (5) configuring Claude, GitHub Copilot, JetBrains Junie, Cursor, and Aider to share project rules without duplication, (6) scaffolding a new project from feature docs and technical docs. Triggers: "analyze this project", "create a task backlog", "onboard this codebase", "what needs fixing", "set up coding standards", "generate tasks", "scaffold from docs", "build this from the spec".

iamursky Bundle

Помогает исследовать потребности клиентов, проверять бизнес-гипотезы, готовить и проводить продажи, вести деловую переписку и follow-up, разбирать закупочную группу, договариваться о следующем шаге, составлять предложение, называть цену, вести клиентский проект, презентовать работу, разбирать комментарии, управлять сроками, скидками, оплатой, документами и конфликтами. Используйте для интервью с клиентами, customer discovery, квалификации спроса, переписки, переговоров, продаж, фриланса, агентской и творческой работы с заказчиком.

gtm-api Bundle

Act on LinkedIn through an account you own, over MCP or REST, using gtm-api.com. Use when a task involves LinkedIn search, connection requests, messages and InMail, inbox reading, profile or company enrichment, post engagement, or checking what a LinkedIn account is still allowed to do today. Covers connecting the server, the three meta-tools and their discovery order, the preview-and-confirm gate on outward actions, and how to read a limit rejection instead of retrying it.

guelfoweb Bundle

Use this skill for static malware analysis and reverse engineering of suspicious binaries, Android APKs, Office documents, web payloads, scripts, source-code droppers, and multi-stage chains across Linux, macOS, and Windows. It guides Codex through safe lab workflow, tool discovery with per-install authorization, triage, staged payload retrieval when authorized, decoding, evidence preservation, AGENTS.md memory, REPORT.md reporting, C2/drop URL extraction, and family attribution.

guim4dev Bundle

Capture tool and data needs from AI agents during task execution. When an agent identifies it needs a tool, API, or data source that doesn't exist, this skill provides a CLI to register that need. Needs are categorized automatically and can be reviewed periodically to build an integration roadmap. Use when the agent realizes it needs something that isn't available — e.g., "I would need X API to do this properly", "If I had access to Y logs I could investigate", "A tool that does Z would be useful here".

gusbavia Bundle

End-to-end Power BI delivery project lifecycle — folder bootstrap, PBIP file scaffold, Git tracking with private GitHub repo, theme refresh propagation, and environment promotion (Dev → Test → Prod). One skill that takes a Power BI delivery project from "empty disk" to "deployable, version-controlled, env-promotable" without requiring the operator to know git, the PBIP file format, or the MAX_PATH 256 quirks of Power BI Desktop. Phase 1 (folder bootstrap, additive-only) is generic and runs against any client. Phase 2 (PBIP scaffold from scratch in PBIR-Legacy with Auto Date/Time disabled by default and theme auto-applied) generates a working .pbip file that opens cleanly. Phase 3 (Git + GitHub CLI integration with always-private repos and project-scoped commits) gives version control without the operator typing a single git command. Phases 4 and 5 (theme refresh, env promotion) ship as design-locked roadmap until real-PBIP calibration completes. Use this skill whenever the operator asks anything resembling st

gusbavia Bundle

Build a complete Power BI project delivery vault in Obsidian — from client discovery to production sign-off. Asks 8 questions about your practice and first project, then generates folder structure, design system, technical reference, DAX/HTML guide, discovery framework, sprint board, templates, and live dashboards. Triggers on "Power BI project hub", "PBI project setup", "set up my Power BI practice", "consultant vault", "Power BI delivery system". Do NOT use for generic Obsidian vaults, non-Power BI projects, or single-file templates.

haaaiawd Skill

Industrial prompt review and optimization. Use when: you want a credible, explainable score (0–100) for a prompt/spec, then guided clarification and a rewritten, execution-ready integrated prompt (product + tech stack + data + security + operations). Keywords: prompt review, prompt quality, scoring rubric, spec prompt, PRD-to-implementation, requirements, architecture, offline/on-prem, security, observability.

hainrixz Skill

Interview the user about what they want to build, design the full architecture, and emit a self-contained blueprint another Claude Code instance can build from with zero prior context. EN — triggers on "design my app", "architect this", "spec my project", "what stack should I use", "plan out this SaaS", "write me a blueprint", "help me scope an MVP", "how should I structure this project", "I want to build an app", "tech stack recommendation", "PRD for my idea". ES — se activa con "diseña mi app", "arquitectura de mi proyecto", "qué stack uso", "hazme un blueprint", "planea esta app", "cómo estructuro este proyecto", "quiero construir una app", "diseña la arquitectura", "especifica mi proyecto", "plan técnico", "MVP". Also handles brownfield: "document my existing codebase", "documenta mi repo", "add a feature to this project". Does NOT write application code — it designs systems and produces blueprints.

harrisliangsu Bundle

暗色科技风 HTML 一页应用的视觉风格系统。当用户需要做架构图、技术全景页、产品 Landing、Dashboard、控制台、Roadmap、技术汇报页、One-Pager、Showcase、深色主题信息密集型页面时，必须使用此技能保证视觉一致性。触发词包括：架构图、技术全景、Landing 页、Dashboard、产品介绍页、技术汇报、暗色主题、深色科技风、cyber 风、tech style、dark theme。即使用户没有明确说"用 dark-tech-style"，只要是构造一个结构化的、信息密集的、偏技术调性的网页，都应当默认采用这套风格。

egebese Skill

Use DataSEO MCP for SEO research workflows including backlink analysis, keyword research, traffic checks, domain comparison, backlink opportunity discovery, AI search query planning, and SEO content briefs. Use this whenever the user asks to investigate a domain, compare competitors, plan SEO content, find backlink gaps, or generate search-intent queries with DataSEO MCP.

emamulmursalin47 Bundle

UI/UX craft + design-decision communication skill, distilled from Albert Chipman's *UX/UI Design 2022* and Tom Greever's *Articulating Design Decisions*. Five modes: AUDIT a screen/component against visual-hierarchy, typography, readability, alignment/grid, consistency and microcopy rules; RATIONALE — write the 'Big Three' justification for any design decision (what problem it solves, how it affects the user, why it beats the alternative); RESPOND to design feedback or a stakeholder request with the IDEAL response (Thank→Repeat→Prepare, strategy, tactics, ask for agreement); PREP a design review (anticipated objections, alternatives, data, follow-up); INTAKE a new design project (goals, users, metrics, decision-maker). Use when the user says 'audit this UI', 'design review', 'looks amateur/unprofessional/AI-made', 'why did you design it this way', 'justify this design', 'the client/stakeholder wants X', 'present this design', 'readability', 'typography', 'visual hierarchy', 'microcopy', 'design rationale', or

epismoai Bundle

Use Epismo to find, inspect, author, version, share, and improve reusable Playbooks; start and coordinate Cases, Tasks, Records, assignments, reviews, and handoffs; and manage durable work context through the available Epismo MCP or CLI surface. Trigger for workflow discovery or authoring, real-work coordination, AI delegation with shared state, Playbook suggestions, aliases, access changes, session handoff, or any request to read or write Epismo data.

erdogant Bundle

Use this skill when working with bnlearn, a Python library for Bayesian networks, probabilistic graphical models, causal discovery, parameter learning, structure learning, inference, sampling, and directed acyclic graphs (DAG).

ericyoung-183 Bundle

Business Analyst Skill. Triggered when users ask about business analysis, industry research, competitive analysis, product analysis, business model analysis, business opportunity discovery, market entry strategy, investment decisions, strategic planning, due diligence, and other strategic topics. Delivers in-depth, decision-grade HTML research reports through a seven-stage workflow (Briefing → Framing → Planning → Research → Insights → Report → Iteration).

erongcao Bundle

Rigorous Polymarket prediction market analysis toolkit. Academic-grade analysis using Wolfers & Zitzewitz (2004), Hanson (2003), Chen & Pennock (2007), Oesterheld et al. (2023). Features market discovery, liquidity analysis, Shapley signal aggregation, equilibrium learning, and performative bias detection.

espressif Bundle

Migrates Espressif Python tools to the shared esp-pylib library. Use when the user explicitly asks to migrate to esp-pylib, replace duplicated code (FatalError, logging, console output options via set_console_options, set_info_stream, progress bars, collapsible log stages, byte progress or unbounded counters, IDE WebSocket, INI config, ROM ELF resolution, serial port discovery, DTR/RTS reset primitives, named reset sequences, Click ParamTypes and Click option classes), convert argparse CLIs to rich-click, remove dependencies superseded by an esp_pylib.* module, or troubleshoot common migration pitfalls (pinned stdout file vs TTY progress, soft_wrap defaults, terminal width in tests, logger prefix assertions in tests, leftover argparse imports after rich-click, breaking vs cosmetic API changes).

johnlindquist Skill

Publish a skill to GitHub for discovery via `npx skills`. Use when asked to "publish skill", "share skill", "make skill discoverable", or "upload skill to GitHub".

johnpcutler Bundle

Search and explore John Cutler's "The Beautiful Mess" (TBM) newsletter archive (~440 posts). Covers product management, org design, strategy, prioritization, delivery, metrics, leadership, and systems thinking. Use when the user mentions TBM, John Cutler, "Beautiful Mess," or asks about product strategy, roadmaps, OKRs, discovery, team health, prioritization, operating models, or organizational change.