Latest Agent Skills
Everything added to the registry recently, newest first.
- lt23live BundleLaunchvet
Pre-launch security, legal and payments audit for the app in this repo. Runs a local zero-dependency scanner, then reviews the code for problems a regex cannot catch (permission checks, ownership checks, rate limits, SSRF, uploads, AI disclosure, cancellation, refunds), and writes launchvet-report.md with a verdict, ranked findings and a copy-paste fix prompt for each. Use when the user asks to audit an app before launch, asks if it is safe to ship, or runs /launchvet.
- blaisebaptist BundleT3 Fleet Onboard
Use for T3 fleet onboarding, repair, or `t3` commands.
- blaisebaptist SkillScreenshot
Use for screenshots on Blaise's Sway/Wayland desktop.
- jamespostsil BundleRainbow Writing Worksheet
Generate printable "rainbow writing" alphabet worksheets for young children: one giant hollow capital letter per 8.5x11 page with numbered dotted stroke-order guides, a rainbow the child colors one band of after each tracing pass, and a friendly line-art picture of something starting with that letter. Use when someone asks for rainbow writing, letter tracing pages, alphabet tracing, or letter-formation practice sheets for preschool/kindergarten, for the whole alphabet or a few letters.
- heyviet SkillWireframe Collaboration
Use when running a team wireframing session or design-studio workshop, breaking design-by-committee gridlock, involving engineers and PMs in design (or reining in a hijack), unblocking a solo-designer bottleneck, deciding who owns which wireframing decision, structuring PM→designer→engineer handoffs, resolving cross-role design disagreements, or adapting collaborative wireframing for remote and async teams.
- heyviet SkillWireframe Fundamentals
Use when deciding whether to wireframe or jump straight to high-fidelity design or code, choosing the right fidelity for a design artifact, or picking a wireframing tool or method. Also fires when stakeholders skip ideation and commit to the first concept, demand 'just make it look real,' polish visuals during early exploration, sign off on branding instead of structure, or when a project derails after coding starts because flaws weren't caught on paper.
- heyviet SkillWireframe Principles
Use when a wireframe reads flat and everything looks equally important, when boxes or text edges are misaligned and the layout feels thrown together, when reviewers can't tell what's clickable or where to look first, when greeked/lorem text is hiding real content decisions, when color or typography starts sneaking into a wireframe, or when reviewing any wireframe's visual logic — hierarchy, alignment, clarity — before sharing it.
- heyviet SkillWireframe Ideation
Use when starting a screen design from a blank canvas, jumping straight into one layout, or treating the first idea as the final idea — or when structure is missing before screens (no user flow, sitemap, or content inventory yet). Also fires when layout alternatives are needed, when divergent exploration should precede committing to a direction, when ideation stalls after one or two sketches, or when stakeholders debate what belongs on a page before anything is drawn.
- heyviet SkillWireframe Feedback
Use when requesting or giving feedback on wireframes, running or facilitating a design critique, or preparing wireframes for stakeholder review. Also fires when feedback arrives vague ('make it pop', 'I don't like it'), as solutions instead of problems ('just move it to settings'), when deciding which feedback to act on after a review, or when a review session went sideways — loud voices dominating, defensiveness, or the same debates repeating without decisions.
- heyviet SkillWireframe Elements
Use when choosing which UI component represents a need in a wireframe, tempted to invent a custom control where a standard one exists, unsure what belongs on a screen type (dashboard, list, detail, form, settings), deciding between list, table, tiles, or cards, picking horizontal vs vertical navigation, representing components at low fidelity, or consolidating repeated screens into page templates.
- heyviet SkillWireframe Handoff
Use when presenting wireframes to stakeholders, clients, or executives; when wireframes are ready for build and developers need a handoff; when a developer asks "what happens when..."; when annotating behavior, states, data sources, validation, or edge cases; when built screens drift from the wireframes during development; or when deciding what to spec in the wireframe versus leave to the build team. Also fires when preparing design alternatives for a sign-off meeting.
- heyviet BundleWireframe
Use when the user invokes /wireframe, asks to wireframe, sketch, or block out a screen, flow, or app before high-fidelity design or code — or when a build is jumping straight to polished UI without structural exploration, stakeholders demand pixel-perfect too early, or an existing wireframe needs review, critique, or handoff. Dispatcher that runs the full wireframe-* family and co-fires the matching design skills.
- sumedh08 SkillVeda Evidence Research
Use Veda's saved research evidence when answering evidence-based questions; inspect source provenance, exact passages, competing evidence, and coverage limits.
- leocanela279 BundleTaste Redesign
Redesign, restyle, polish or review the UI of an existing project: a live site, an app with screens people already use, a codebase with its own styles, components and brand. Classifies the request (review, polish, restyle, realign, redesign), records the current UI as a measured baseline, diagnoses what to change, keeps the brand constants (logo, palette, fonts) and everything people rely on, changes the cheapest layer in reversible steps, and proves the result against the before. Use whenever the user asks to redesign, refresh, modernise, clean up, improve, restyle or audit an interface that already exists, or says it looks generic, dated, cluttered or AI-made. For new pages with no existing UI, use the taste skill.
- leocanela279 BundleTaste
Art direction and visual taste for any web UI: landing pages, product and marketing sites, portfolios, app screens, dashboards, settings, lists. Grounds the design in the subject, measures real reference sites into numbers, writes a token plan before code, lints, and runs a screenshot critique loop against the reference. Use whenever you build or design a new web page or screen in any stack (HTML/CSS, React, Next.js, Tailwind, Vue, Svelte, Astro), when new output looks generic, templated or AI-made, and for small edits to a design this skill planned (design/DESIGN.md). To redesign, restyle, polish or review a UI that already exists, use taste-redesign. For motion polish after the layout is settled, use the animate or review-animations skills.
- agarzon SkillChallenge
Question a plan, design or decision until every choice in it is settled and nothing is silently assumed, before anything is built. Works in any project.
- agarzon SkillHandoff
Close the session. Save pending work to HANDOFF.md, the contract the next session starts from, after the end-of-session chores. Use when the user says "handoff", "hand this off", "wrap", "wrap up", "done for today", "close the day", "let's stop here", "save everything and stop", "start fresh", "the context is getting long", or when the context-fill nudge appears.
- agarzon SkillDebug
Find the root cause before proposing any fix. Use when a bug, test failure, failed build or deploy, or unexpected behaviour shows up, and before trying a second fix.
- agarzon SkillWhat
Re-explain the last answer in simple English when it did not make sense.
- agarzon SkillTdd
Build test-first, red, green, refactor. Use when implementing a feature, a bug fix or a behaviour change in code that has, or should have, tests.
- getzep SkillMigrating Zep V3 To V4
Procedure for a coding agent that migrates an application from the Zep V3 API and SDKs to V4. The procedure reads the V4 migration guide, finds each V3 call in the codebase, maps it to its V4 replacement, moves the application to Zep-generated UUIDs in the documented order, and verifies each step. Use when a user asks to "migrate to Zep v4", "upgrade zep-cloud to v4", "port my Zep code from v3", or "what breaks when I move to Zep v4". Use together with the building-with-zep skill from the same plugin. Activate that skill first if it is not active yet.
- getzep SkillTuning Zep Ingestion
Procedure for an agent that must turn a dataset (database records, documents, email, chat messages, meeting transcripts, event logs, or a mix) into a domain-specific Zep Context Graph, with or without a gold question set. The procedure splits the data into a deterministic import and narrative episodes, shapes each episode, designs the ontology and the custom instructions, runs a versioned ingestion on a new graph, measures the graph shape, reads the debug logs and the Ingestion Traces, and changes one variable per run. Use when a user asks to "ingest my data into Zep", "improve extraction quality", "why does my graph have duplicate or untyped entities", "tune the ontology or the instructions", or "evaluate Zep on my dataset". Use together with the building-with-zep skill from the same plugin. Activate that skill first if it is not active yet.
- jtanium BundleHexadci
Define business rules clearly and organize business logic as HexaDCI features — a rule sheet per business operation, one folder per operation, a Context that reads like the business process — casting records into feature-local roles with listeners and ports at the edges when the operation has effects, or a lean pure function returning result values when it doesn't — and table-driven tests. Use when adding or changing business behavior (billing, payouts, onboarding, approvals, reconciliation, notifications, reports with rules); when turning a stakeholder's request into precise rules; when asked what existing code actually does or to untangle rules scattered across controllers, models, jobs, and SQL; when a model or service class is accumulating unrelated methods; or when the user mentions HexaDCI, DCI, contexts and roles, use cases, business rules, or hexagonal/ports-and-adapters. Works in any object-oriented language; reference examples in Ruby, Python, TypeScript, and Dart/Flutter.
- kinwisenz-devops BundleNz Privacy Compliance
Use when drafting or reviewing a New Zealand privacy policy, privacy notice, data collection clause, cross-border data transfer wording, or a notifiable privacy breach process. Checks wording against the Privacy Act 2020's Information Privacy Principles and breach notification duties, clause by clause, with a section citation for every flagged issue. Do not use for general contract formation wording (nz-contract-drafting) or consumer trading terms with no personal information element (nz-trading-terms).
- kinwisenz-devops BundleNz Contract Drafting
Use when drafting or reviewing a New Zealand business contract's general wording: formation, representations and warranties, misrepresentation, mistake, cancellation, electronic signing, third-party rights, or precision of defined terms. Checks wording against the Contract and Commercial Law Act 2017 and general contract law, clause by clause, with a section citation for every flagged issue. Do not use for consumer-facing terms of trade, fair trading or product guarantee wording (nz-trading-terms) or privacy and data clauses (nz-privacy-compliance).
- kinwisenz-devops BundleNz Legal Specialist
Use when a task involves drafting, reviewing or checking the wording of a business contract, terms of trade, terms and conditions, or a privacy policy or notice, with a New Zealand governing law, or when it is unclear which legal skill applies. Router and shared guardrails for New Zealand commercial legal drafting: requires a specific Act and section for every flagged issue, never invents a citation, and always states that output is not legal advice. Do not use for litigation strategy, employment law, criminal law, tax law, or any jurisdiction outside New Zealand unless the user names that jurisdiction and it is treated as a separate exercise.
- kinwisenz-devops BundleNz Trading Terms
Use when drafting or reviewing New Zealand terms of trade, terms and conditions, sales terms, or any consumer- or trader-facing wording that touches misleading claims, unsubstantiated claims, unfair contract terms, product or service guarantees, pricing, cancellation rights, or competition law. Checks wording against the Fair Trading Act 1986, Consumer Guarantees Act 1993 and Commerce Act 1986, clause by clause, with a section citation for every flagged issue. Do not use for general contract formation wording with no trading or consumer element (nz-contract-drafting) or privacy and data clauses (nz-privacy-compliance).
- greyland-fireworks BundleAudhd UI Guide
Design, review or improve UI and UX using AuDHD-friendly interaction rules, accessible selectable appearance and verifiable workflow continuity. Use when the user says "audhd audit", or for dashboard organization, settings forms, status feedback, accessible controls and interruption recovery; not clinical advice or certification.
- aj-suresh BundleGoogle Ads Copy
Writes Google Ads Search copy (responsive search ad headlines, descriptions and display paths, plus sitelinks, callouts and structured snippets) for one or more ad groups. It uses the campaign and ad group, the keywords, the live landing page, the product context skill and competitor context, then fills the user's Google Ads Copy Template workbook. Use this whenever the user asks for Google Ads copy, RSA headlines or descriptions, search ad copy for a set of keywords, sitelinks, callouts or snippets, or to rewrite or refresh existing Google ads, or when they hand over the Google Ads Copy Template .xlsx or a Keywords & Intent sheet, even if they never say 'RSA'. Not for LinkedIn or Meta ads, for creating or launching campaigns, or for auditing account health.
- 653366873iuhm-source SkillFistagent Mint
Mint FISTAGENT shares on BNB Smart Chain (chainId 56) from a Binance Agentic Wallet that holds a .ai Agent ID. Use when the user asks about FISTAGENT, $FISTAGENT, the FISTAGENT fair mint, agent-only mints on BNB Chain, or wants to mint/check eligibility/price/progress. Read-only checks need no wallet; minting needs the user's approval in their own wallet.
- ostaninki SkillTelegram User Bridge Maintenance
Check and debug hermes-tg-bridge around a Hermes update, or when the Telegram user bridge misbehaves: no replies, a reply from the wrong profile, lost settings, cron results not delivered. Backup before, checklist after, where to look in the logs.
- ostaninki SkillTelegram User Bridge Setup
Install hermes-tg-bridge so Hermes can talk through the user's own Telegram account: backend service, QR login, plugin, restart. Walks the user through the steps only they can do.
- cerase-ai BundleBusiness Document
Applies when the person asks for a quote, an offer, a bid for a tender, a proposal, a report, a business letter or another document written for a client or for management, and when text has to go into a document that already exists, such as a Google Doc or a letterhead. Builds the document in five stages: a brief, an outline the person agrees, a Markdown draft, a revision that recomputes every figure with the calculator and traces every claim to its source, and a PDF rendered from the Markdown and delivered as an attachment. Not for a slide deck, which is the deck skill, nor for the text of an email, which is email-drafting.
- majidraimi BundleNextjs Patterns
Guide for building Next.js applications following a specific architecture with App Router, Zustand, TanStack Query, Axios, nuqs, react-hook-form, and Zod. Use when scaffolding features, creating components, setting up state management, building forms, or working with search params in Next.js projects.
- majidraimi BundleProduct Docs
Turn a finished grill-me session into a full product documentation set. Writes docs/product/DECISIONS.md from the conversation, has the user confirm it, then writes PRD, PRODUCT.md and DESIGN.md (impeccable), architecture, AI engine, security, data model, API, billing and roadmap specs with parallel subagents, then runs a skeptical cross-document review, settles the open decisions with them, and checks the result mechanically. Use when the user says "/product-docs", "generate the docs", "write the PRD and everything", "create all the documents", "PRD.md, DESIGN.md etc", or finishes a grill-me or mcq session about a product and wants it written down.
- majidraimi BundleDesign Md
Generate UI that matches a specific brand's design language using a bundled DESIGN.md spec (colors, typography, spacing, components). Triggers: 'make it look like <brand>', 'build a <brand>-style page', 'use the Stripe design', 'match Linear's aesthetic', 'design-md', 'apply a DESIGN.md'. Brands include Apple, Stripe, Linear, Vercel, Notion, Airbnb, Spotify, Tesla, and ~63 more.