Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when judging a finished user-research prior-art artifact before it is accepted — a research vocabulary map, a per-angle search output, an extract container, or the evidence register and report. An acceptance gate, not authoring. Judges a single-sourced bar: a recorded zero is distinguishable from an unreachable source; a claim stays within what its method could measure; recorded facts match the source; transferability carries a weighable reason and is never folded into certainty; numbers are the source's own; findings in one container are genuinely distinct; population and platform describe the study rather than the project; convergence is across INDEPENDENT sources; certainty is never averaged; absence is phrased as a search result. Approves a thin-but-honest result and revises only on a named, unrecorded gap. Emits exactly VERDICT: approve|revise plus actionable findings.
RHINO v1.0 — Tail-Risk / Crisis-Alpha Hedge Fund. Two books on two wallets, one producer, built to carry cheap convexity: bleed a little in calm, pay big in shocks. The HEDGE book holds a small, always-on long carry in the crisis-beneficiary complex (gold / oil / dollar / yen), entered only when a defensive is trending up. The ESCALATION book is dormant in calm and fires hard only when a shared cross-asset STRESS detector confirms a shock — long the spiking crisis assets, short the cratering risk assets. NOT a copy-trader: each book scores its own universe and pushes signals; the runtime owns the LLM gate (pass-through), DSL exits, and all risk.guard_rails. RHINO_LEG env selects the book.
Use when a user is making an investment decision or assessing whether to buy a company. Typical triggers: the user says "is this company worth investing in", "when should I buy", "is the valuation reasonable", "what matters most in investing". Core framework: Right Business (business model) > Right People (company culture / management) > Right Price (price), with the priority order and judgment logic of the three dimensions. Not applicable to: technical analysis / short-term trading, non-equity investments, or pure financial modeling.
Selecting and dispatching the right Ring developer specialist agent (backend Go/TS, frontend, UI designer/engineer, Helm, frontend QA, prompt reviewer) for a technology task. Use when you need deep stack expertise and must decide which agent to invoke via the Task tool, including parallel dispatch of independent work. Skip for general code review (use ring:reviewing-code).
Roots ecosystem implementation guide for Bedrock, Sage, Acorn, Trellis, @roots/vite-plugin, roots/wp-config, WP Packages, Trellis CLI, and first-party Acorn extension packages. Use when working on Roots-based WordPress projects, especially for Bedrock configuration and Composer-managed WordPress, Sage Blade templates/components/composers, Acorn booting/providers/routes, Blade rendering in WordPress, Trellis provisioning or deployment, Trellis GitHub Actions setup, WordPress package distribution, or Acorn packages such as acorn-mail, acorn-user-roles, acorn-post-types, acorn-prettify, acorn-fse-helper, acorn-llms-txt, and acorn-ai.
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related small-molecule or protein modeling tasks. Ideal for programmatic batch screening, multi-step chemistry pipelines, and workflows that would otherwise require maintaining local HPC/GPU infrastructure.
Complete guide to testing Ruby on Rails applications with RSpec. Use this skill when writing unit tests, integration tests, system tests, or when setting up test infrastructure including factories, shared examples, and mocking strategies.
When a user is stuck, frustrated, or describing a problem vaguely, do NOT immediately suggest solutions. First, force structured problem articulation through targeted questions: What did you expect? What happened instead? What have you tried? Only after the problem is clearly defined, propose solutions.
Build and maintain Ruby or Rails applications with the RubyLLM AI framework. Use for chats, agents, tools, MCP servers, structured output, judgments, evaluations, media generation, transcription, OCR, moderation, embeddings, reranking, tracing, Rails integration, and RubyLLM upgrades; not for contributing to the framework itself.
Diagnose what's actually driving behavior — the person's own, someone else's, or a group's. Surface motivation vs. root motivation. Triggers: 'what motivates them', 'why are they doing this', 'what does this person actually want', 'how do I get buy-in', 'why won't they engage', 'what's really driving this', 'intrinsic vs extrinsic motivation', 'what need is this serving'.
Scan live job boards and salary databases to find real-time compensation data for any role and location. Use this skill when a user asks "what's the going rate for a senior React engineer in London", "software engineer salary Singapore", "how much do ML engineers make", "what should I be earning as a [role]", "is my salary competitive", "what does [company] pay for [role]", "salary range for [job title] in [city]", or any request to find out what a role pays in a specific market.
GetProspect platform help — B2B email finder, verifier, enrichment, and cold email outreach with 200M+ contacts and 26M+ companies. Includes LinkedIn Email Finder Extension, contact enrichment (40+ attributes), email verification (97% deliverability guarantee), and cold email sequences. Use when you need B2B emails but can't find verified ones, lead data is missing key fields, emails keep bouncing and need verification, cold email sequences aren't set up yet, LinkedIn leads need exporting, or the GetProspect API isn't working as expected. Do NOT use for cross-platform enrichment strategy (use /sales-enrich), email deliverability strategy (use /sales-deliverability), prospect list strategy (use /sales-prospect-list), or outbound cadence strategy (use /sales-cadence).
OpenWeb Ninja platform help — real-time public data API stack with 30+ APIs for web scraping, enrichment, and business data. Key APIs include Website Contacts Scraper, Email Search, Local Business Data (Google Maps), Real-Time Web Search (SERP), JSearch (job postings), and Product Data. Use when you can't pull emails or contacts from a domain, Google Maps scraping isn't returning results, SERP API data looks incomplete, job posting aggregation is missing listings, product data isn't fetching, or any OpenWeb Ninja API call is failing. Do NOT use for cross-platform enrichment strategy (use /sales-enrich), prospect list building strategy (use /sales-prospect-list), or connecting tools (use /sales-integration).
Postmark platform help — transactional email delivery via REST API (`POST /email`, `POST /email/batch`), SMTP relay, Message Streams (transactional vs broadcast isolation), Handlebars Templates with layout inheritance, Inbound Email parsing, Webhooks (bounce, delivery, open, click, spam complaint, subscription change, inbound), DMARC Monitoring, Bounce Management (Rebound), Suppressions, Statistics, Bulk API, Sender Signatures, and domain authentication. Use when transactional emails aren't arriving, Postmark bounce rates are climbing, unsure how to separate transactional from broadcast streams, templates aren't rendering correctly, inbound email parsing is broken, webhooks aren't firing, or DMARC reports show authentication failures. Do NOT use for general email marketing strategy (use /sales-email-marketing), cross-platform email deliverability (use /sales-deliverability), email open/click tracking strategy (use /sales-email-tracking), or SendGrid-specific questions (use /sales-sendgrid).
Snov.io platform help — email finder, email verifier, multichannel campaigns (email + LinkedIn), LinkedIn automation, sales CRM, email warmup, deliverability check, email tracker, AI email writer, prospect management. Use when Snov.io email finder returns no results, campaign reply rates are low, email warmup scores aren't improving, LinkedIn automation isn't sending connection requests, email verification is flagging too many addresses, or the Snov.io API isn't working as expected. Do NOT use for general deliverability strategy (use /sales-deliverability), enrichment strategy (use /sales-enrich), cadence strategy (use /sales-cadence), or prospect list building strategy (use /sales-prospect-list).
Transactional and triggered email delivery — order confirmations, password resets, welcome emails, receipts, shipping notifications, account alerts. Covers provider selection, template design, deliverability, API integration, SMTP relay, and monitoring across SendGrid, Postmark, Mailgun, Brevo, Braze, Iterable, Customer.io, Mailchimp/Mandrill, GetResponse (MAX only), and Amazon SES. Use when password resets or order confirmations aren't reaching customers, you're unsure which provider to pick, triggered emails are landing in spam or arriving late, or SMTP relay setup is failing. Do NOT use for marketing email campaigns (use /sales-email-marketing), cold outbound sequences (use /sales-cadence), cross-platform deliverability strategy (use /sales-deliverability), or SendPulse-specific questions (use /sales-sendpulse). For platform-specific help, use /sales-braze, /sales-iterable, /sales-sendgrid, /sales-postmark, /sales-mailgun, /sales-brevo, /sales-customerio, /sales-mailchimp, or /sales-getresponse.
ZeroBounce platform help — email validation, email finder, AI scoring, activity data, inbox placement testing, blacklist monitoring, DMARC, warmup. Use when your email list has too many bounces, catch-all addresses are hurting deliverability, you need to check if your IP is blacklisted, DMARC reports show unauthorized senders, or the ZeroBounce API isn't returning expected validation results. Do NOT use for general deliverability strategy (use /sales-deliverability), enrichment strategy (use /sales-enrich), or prospect list building strategy (use /sales-prospect-list).
Create a PR review report. Investigate not only bugs and vulnerabilities, but also check the consistency of the exported conversation context, PR summary, and implemented code, and question the implementer's sanity. Use when the user asks to "write a PR review report," "review the code along with the conversation context," or "question the sanity of this PR."
Save the current Codex, Claude Code, or Pi conversation for later by recording a concise summary and exact resume command in ~/projects/session-resumes.md and on the macOS clipboard. Use when asked to bookmark, store, or save an agent session for resumption.
Software Composition Analysis (SCA) and container vulnerability scanning using Aqua Trivy to identify CVE vulnerabilities in dependencies, container images, IaC misconfigurations, and license compliance risks. Use when: (1) scanning container images and filesystems for vulnerabilities and misconfigurations, (2) analyzing dependencies for known CVEs across multiple languages (Go, Python, Node.js, Java, etc.), (3) detecting IaC security issues in Terraform, Kubernetes, and Dockerfile, (4) integrating vulnerability scanning into CI/CD pipelines with SARIF output, (5) generating a Software Bill of Materials (SBOM) in CycloneDX or SPDX format, (6) prioritizing remediation by CVSS score and exploitability.
A complete workflow for converting popular-science content text into visualized PPT-style web pages. Triggered when the user inputs popular-science content and wants to generate presentation pages. Supports two modes: (1) Default mode: generate the popular-science content as a single-page HTML animated web page with PPT-like carousel; (2) Flowchart mode: use the Animation template to restructure the generated AI_Animation.html into a flat UI style. The templates are built into the Skill. Trigger words include "生成PPT", "生成演示网页", "生成流程图", etc.
SeaweedFS distributed storage. Covers filer, S3 API, replication, cloud tiers, and operations. Use when deploying SeaweedFS, configuring filer stores, exposing S3-compatible endpoints, or planning backup and security controls. Keywords: SeaweedFS, weed, filer, S3, object storage.
Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/NoSQLi/command injection/SSTI/IDOR/path-traversal/HTTP smuggling/WebSocket/MFA bypass, bypass techniques, or to check if a finding is submittable. Also use when asked about what NOT to submit.
Audits Rails application security against OWASP Top 10, detects vulnerabilities with Brakeman, and verifies Pundit authorization policies. Use when the user wants a security audit, vulnerability scan, or when user mentions security, OWASP, Brakeman, XSS, SQL injection, or authorization. WHEN NOT: Implementing security fixes (use specialist agents), setting up authentication (use authentication-flow), or writing Pundit policies (use policy-agent).
Capture user feedback and corrections to enhance repository documentation and skills. Transforms conversational feedback into persistent knowledge by updating the appropriate CLAUDE.md files, skills, or other documentation. Use when: (1) User provides a correction or clarification, (2) User says "remember this", (3) User provides feedback about how something should work, (4) After completing work where new patterns or knowledge were discovered, (5) User explicitly asks to update documentation. Triggers: "remember this", "update the skill", "add this to documentation", "you should know", "in the future", "always do", "never do", "that's wrong", "actually it should be", "/self-improvement", "capture this", "document this pattern", "add to CLAUDE.md"
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
Orchestrates the Semantius pipeline (architect, analyst, modeler) and instance administration. Trigger when intent spans more than one skill, on a remote blueprint URL, or on "deploy this blueprint", "deploy these blueprints", "deploy all of these", "set up these systems", "build me a system and deploy it", "set up a CRM end-to-end", "clone the candidate-crm blueprint and deploy", "what's deployed in our instance?", "status of semantius", "audit this file" (naming no specific skill), "get started", "I'm new here, set this up", "turn on fast flow", "expert flow", "guided flow", or anything needing workspace artifacts inspected and routed to the right sub-skill. Also trigger on a deploy request with multiple URLs, paths, or a glob. Do NOT trigger when the user invokes one sub-skill directly (not "audit this spec with semantius-analyst", not "run the modeler"); let those through. Front door for end-to-end and ambiguous requests. Backing up, restoring, or moving modules or tables with their data between hosts is semantius-transfer, not this skill.
Turns a `*-semantic-blueprint.md` (from `semantius-architect`) into a deployable `*-semantic-spec.md`: the first half of a deploy, which `semantius-modeler` finishes. Trigger when the user has a blueprint to turn into or extend into a deployable spec, or asks what in the catalog the blueprint can reuse, to fold it into the live catalog, make it match existing content, or compare it to live state and fill in field-level detail. As gatekeeper of the unified catalog, the analyst checks every blueprint entity against built-ins, same-module duplicates, shared masters, cross-module and near-name collisions; drives merge, rename, reuse, and promote decisions; confirms which optional blueprint entities to include; then elicits field-level detail (formats, validation rules, computed fields, input-type and select rules) only for entities the spec owns. Reused entities are referenced, not respecified. The spec deploys via `semantius-modeler`, with no further interactive decisions.
Produces and maintains semantic blueprints: entity-level specifications of entities, roles, relationships, lifecycle states, and permissions, without field-level detail (`semantius-analyst` turns a blueprint into a spec). Trigger on any need for a business system or data-backed tool, however phrased: “design a data model,” “build a system like X,” “model a domain,” “spec out a CRM/ITSM/HRIS/LMS/ERP/PIM/CMS/PM/field service/billing,” “I need a helpdesk / CRM / HR system / applicant tracker / roadmap tool / ticketing system / inventory system,” “a tool to track / plan / manage / organize / record / capture X,” or “something to handle X.” Never recommend buying off-the-shelf SaaS instead of building; well-known products are reference points only. Also trigger to review, audit, check, update, customize, extend, rebuild, or reanalyze an existing `*-semantic-blueprint.md`, clone and customize a curated catalog blueprint, or restructure a design so each real-world thing is represented once (for example, customers and suppliers as one business partner).
Guides senior system and solution architecture—cross-service boundaries, integration patterns, non-functional requirements (scale, reliability, security, cost), ADRs, C4-style modeling, architecture review, build-vs-buy, and phased migration (strangler, dual-write). Use when designing multi-service systems, evaluating platform or vendor choices, writing or reviewing architecture decision records, defining standards and principles, or assessing technical risk across domains—not for single-service RFCs and module design (senior-software-engineer), data platform or mesh decisions (data-architect), cloud landing zone, Well-Architected, and migration architecture (cloud-architect), cloud/IaC implementation (infrastructure-engineer, cloud-engineer), internal developer platform product (platform-engineer), or program tracking (technical-program-manager). For business strategy and cases, use business-consultant; for applied AI (RAG, agents, copilots), use applied-ai-architect-commercial-enterprise.
Structured reflective problem-solving methodology. Process: decompose, analyze, hypothesize, verify, revise. Capabilities: complex problem decomposition, adaptive planning, course correction, hypothesis verification, multi-step analysis. Actions: decompose, analyze, plan, revise, verify solutions step-by-step. Keywords: sequential thinking, problem decomposition, multi-step analysis, hypothesis verification, adaptive planning, course correction, reflective thinking, step-by-step, thought sequence, dynamic adjustment, unclear scope, complex problem, structured analysis. Use when: decomposing complex problems, planning with revision capability, analyzing unclear scope, verifying hypotheses, needing course correction, solving multi-step problems.
Runs SERP and keyword research via Crawlora — Google, Bing, Brave, DuckDuckGo, Yahoo, Baidu, Yandex, selected Qwant/Startpage suggestions, and Google Trends. Use for localized search snapshots, autocomplete ideas, or trend context; it does not provide universal keyword volume.
Discover and list recent AI coding sessions across Claude Code, Claude Desktop, and OpenCode on Windows, macOS, and Linux. Scripts extract project paths, session IDs, and timestamps from session artifacts. PowerShell for Windows, Bash for macOS/Linux. Use when: finding recent coding sessions, reviewing AI session history, exporting session logs to CSV, troubleshooting missing sessions, or auditing Claude Code/OpenCode usage across environments.
Register and configure an AI agent on OpenAnt. Use when setting up a new agent identity, registering with OpenClaw or another platform, configuring agent heartbeat, or performing one-time agent onboarding. Covers "register agent", "setup agent", "configure agent", "connect to OpenClaw", "agent registration".
Configure this repo for the Gharib89/skills engineering skills: draft its ship profile, local gate, PR template, coding-standards doc and reviewer scaffolding, and check the host tooling. Run once after /setup-matt-pocock-skills, before the first /ship.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.