Skills
Security-reviewed skills, MCP servers, and toolkits for AI agents. Filter by type, price, and delivery, then install any listing with one command. Every listing is scanned before an agent can run it.
Status Copy Trust Audit
Audit CLI and app status wording, repeated-run behavior, and client label alignment.
Tools Visual State Machines
Model user journeys, retention loops, or process states with ASCII state machines and storyboards.
Wide Open Brainstorm
Run multi-model brainstorming for product strategy and experience design.
Tools Mermaid
Mermaid diagram syntax for flowcharts, sequence diagrams, ER diagrams, state machines, and other visualizations that render in GitHub/GitLab markdown.
Ralph Loop
Run repeatable multi-LLM hardening sweeps: review, fix, document, repeat.
Pre Mortem
Run a multi-agent pre-mortem that returns ranked risks and mitigations.
Remote Host Verifier
Compare commands, versions, config, and behavior across local and SSH hosts.
Django Smoke Alarm
Run and triage Django/DRF security smoke checks before shipping or after scanner findings.
Empathy Audit
Review code through user, machine, developer, and support lenses.
Tools Visual Ascii Arch
Express product, service, or data architectures through layered ASCII diagrams suitable for terminals, PRs, and ADRs.
Handle Pr
Handle GitHub PR comments: assess, fix approved findings, test, commit, and reply.
Research Person
Research a person from public sources into a confidence-marked Obsidian People dossier.
Tools Visual Cheatsheets
Build portable ASCII command panels summarizing CLI workflows (e.g., GitHub CLI, deployment scripts) for quick reference.
Contacts Unify
Merge and dedupe macOS, iCloud, Google, Zoho, or VCF contacts with reviewable provenance.
Changelog Writer
Draft plain-language changelog entries from Git history, optionally updating CHANGELOG.md.
Logika
>
Visual Qa Loop
Run before/after visual QA for local UI changes with screenshots and concise findings.
Parallel Isolated App Testing
Plan isolated parallel test lanes for desktop apps and local tools with shared state.
Tools Visual Workflows
Communicate multi-step workflows using consistent ASCII flowcharts and timelines that paste cleanly into PRs, issues, and chats.
Tools Visual Retro
Facilitate retrospectives and experiment readouts using ASCII grids, timelines, and heatmaps for rapid comprehension.
First Contact
Red-team onboarding and first use to find confusion, broken expectations, and abandonment.
Release Operator
Run a CLI or app release: verify, version, test, publish, and verify installs.
Dependency Pinning
Audit Docker, CI, and language dependencies for SHA/digest pinning and cooldowns.
Trust Audit
Audit product trust: permissions, privacy, billing, file changes, and silent failures.
Launch Sequence
Run first-contact, support-storm, trust-audit, and pre-mortem for a launch verdict.
Technical Style Editor
>
Gtm Seven Part Research
Run a data-backed GTM analysis using Frank's seven-part framework (User insight, Product design, Brand positioning, Content strategy, Marketing channels, Conversion strategy, Path optimization) with Apify MCP research, a full competitor sweep, and a styled HTML report plus a Markdown report. Use for any new product, idea, or client GTM.
Gtm Seven Part Research D2c
Run a data-backed e-commerce D2C GTM analysis using Frank's seven-part framework (User insight, Product and offer design, Brand positioning, Content strategy, Marketing channels, Conversion strategy, Path optimization), with unit economics, an Amazon, Shopify, and Meta Ad Library competitor sweep, Apify MCP research, and a styled HTML report plus a Markdown report. Use for any physical consumer p…
Gtm Seven Part Research Zh
用 Frank 七步框架（用户洞察、产品设计、品牌定位、内容策略、营销渠道、转化策略、路径优化）对新产品或新想法做数据驱动的上市（GTM）调研，通过 Apify MCP 检索真实数据，包含完整竞品扫描，最终产出带样式的自包含 HTML 报告和补充 Markdown 报告，全部为中文。适用于任何新产品、新想法或客户 GTM 分析。Use for any new product, idea, or client GTM when a Chinese-language research report is wanted.
Gtm Seven Part Research D2c Zh
用 Frank 七步框架（用户洞察、产品与报价设计、品牌定位、内容策略、营销渠道、转化策略、路径优化）为电商 D2C 品牌做数据驱动的上市（GTM）调研，包含单位经济模型、覆盖品牌独立站、Amazon 和 Meta 广告库的竞品扫描，通过 Apify MCP 检索真实数据，最终产出带样式的自包含 HTML 报告和补充 Markdown 报告，全部为中文。适用于面向美国等海外市场的实体消费品、D2C 品牌、Shopify 独立站、出海品牌、Amazon 或 TikTok Shop 上新，以及客户电商 GTM 分析。Use for any physical consumer product or D2C brand GTM when a Chinese-language research report is wanted.
Impots Fr
Agent expert en declaration d'impots sur le revenu en France. Utilise ce skill quand l'utilisateur parle de declaration d'impots, IR, impot sur le revenu, avis d'imposition, credit d'impot, reduction d'impot, deduction, niche fiscale, frais reels, don, PER, emploi a domicile, garde d'enfant, travaux, FIP, FCPI, Pinel, Jeanbrun, Relance logement, Denormandie, Malraux, LMNP, LMP, deficit foncier, i…
Kry Debrief
Act 1 — cửa vào pipeline build. Trigger khi user gõ /kry-debrief, hoặc nói 'bắt đầu build app', 'debrief dự án', 'tôi với team vừa họp xong', 'có đống ý tưởng cần làm rõ', 'kickoff project', 'dump ý tưởng app'. Skill bóc dump thô (note họp/brain-dump) → Business Brief có cấu trúc (spawn agent debrief-analyst) → hỏi bạn trên đúng 🚩 → KICKOFF dự án: git init repo private dưới github <YOUR_GH_USER>…
Kry Ux
Đặc tả UX (hành vi sản phẩm) trước khi /kry-plan. Trigger khi user gõ /kry-ux, hoặc nói 'đặc tả UX', 'spec UX', 'user flow cho app', 'thiết kế luồng', 'làm rõ màn hình/nút/kịch bản', 'app này có những màn gì', 'flow mua hàng/đăng ký thế nào', 'viết spec cho tool', 'UX spec', 'logic flow'. Skill đọc business logic (từ CWD/CLAUDE.md hoặc prompt từ /kry-debrief) → đề xuất hướng triển khai → viết UX…
Kry Ui
Act 4 — Ngôn ngữ thiết kế (cửa 1 chiều nhẹ). Trigger khi user gõ /kry-ui, hoặc nói 'định hình thiết kế', 'ngôn ngữ thiết kế cho app', 'hướng design', 'mood/visual cho app', 'thiết kế trông thế nào', sau khi đã có /kry-system. Skill ĐỊNH NGHĨA TƯƠI ngôn ngữ thiết kế riêng cho app này từ intent của nó — mood + 3-5 nguyên tắc + 1 TRỤC ĐỘT PHÁ + token sinh từ product. KHÔNG bốc archetype/template có…
Kry Docs
Act 7: tài liệu hoá dự án SAU khi /kry-done ship lần đầu (hoặc khi docs đã lệch code). Trigger khi user gõ /kry-docs, hoặc nói 'viết docs', 'tài liệu hoá project', 'viết README', 'ghi lại cách chạy', 'document lại', 'làm docs để sau này sửa', 'docs lỗi thời rồi'. Skill đọc code THẬT + spec đã chốt (Brief, UX, system, ui, CHANGELOG) rồi sinh bộ docs cố định 5 file: README (chạy/deploy), docs/FEATU…
Kry System
Act 3 — Dữ liệu + Kiến trúc (cửa 1 chiều). Trigger khi user gõ /kry-system, hoặc nói 'thiết kế data model', 'schema cho app', 'kiến trúc hệ thống', 'dựng nền kỹ thuật', 'chốt stack + database', 'auth thế nào', sau khi đã có UX spec từ /kry-ux. Skill define TƯƠI cho app này: entity→bảng→field→ràng buộc + state machine + boundary/contract + auth/role (RLS) + stack + host. Spawn agent challenger-sys…
Kry Update
Act 8: vòng bảo trì sau ship, cho project ĐÃ /kry-done + /kry-docs. Trigger khi user gõ /kry-update, hoặc nói 'thêm tính năng X', 'sửa bug Y', 'app chạy rồi giờ muốn thêm', 'fix lỗi trên prod', 'nâng cấp tính năng', 'update project', 'sửa cái này chút'. 2 mode: feature (thêm/đổi tính năng) · fix (lỗi). Skill đọc docs/ + CHANGELOG + state THAY VÌ đọc lại cả repo → tìm vùng đụng qua FEATURES.md → p…
Kry Done
Act cuối — chốt phiên build. Trigger khi user gõ /kry-done, hoặc nói 'xong rồi', 'chốt lại', 'lưu lại đi', 'commit lên git', 'dọn dẹp và lưu', 'checkpoint', 'để mai làm tiếp'. Skill dọn rác + commit + push lên github <YOUR_GH_USER> (private) + cập nhật sổ project-state để cron <YOUR_TELEGRAM_BOT> biết nhắc bước kế. Mục tiêu: người nocode quay lại sau không lạc, không mất commit. Đây là bookend củ…
Kry Ux Website
Đặc tả UX/IA cho WEBSITE doanh nghiệp (Corporate / Business Info / Brochure site) trước khi build. Trigger khi user gõ /kry-ux-website, hoặc nói 'làm website công ty', 'web giới thiệu doanh nghiệp', 'corporate website', 'brochure site', 'website business info', 'sitemap cho web', 'web giới thiệu dịch vụ/sản phẩm', 'landing trang chủ công ty', 'web 5-7 trang giới thiệu'. Skill đọc thông tin doanh…
Ls Backlog And Reminders
Record deferred ideas, to-dos, and reminders (with optional due date or 'whenever'); show due/overdue when user starts a session or asks. Use when user says 'add to backlog', 'remind me', 'I'll do this later', 'what's due?', 'show my backlog', 'start my session', or wants to capture ideas for later.
Ls Framework Audit
Run doc, link, skill matrix, and version/facts checks before release. Single entrypoint script; output to user-specified path only; no in-repo default. Use when user says 'run audit', 'run framework audit', or before release.
Ls Architecture
Guide architecture analysis and decision records. Use for ADRs, tradeoff
Ls Agent Email Inbox
Guide agent email inbox workflows with prompt-injection defenses. Use
Ls Accessibility Review
Guide accessibility reviews for UI, documents, and workflows. Use for
Ls Context Index
Use when building, querying, or refreshing the LocalSetup context index with hybrid SQLite retrieval, deterministic freshness/worklist surfaces, and agent-preflight checks.
Ls Github Actions Builder
Guide GitHub Actions workflow authoring. Use for CI, release, scheduled
Ls Cloudflare Dns
Use the cf CLI for Cloudflare zones, DNS records, settings, DNSSEC, scans, imports, exports, batches, analytics, and zone transfers.
Ls Keepass Secrets
Use when validating logical secret-ID maps, config, and reference syntax for a KeePassXC integration; output is redacted and the fake backend is test-only.