Coding & Dev Tools

gurudevvv Bundle

Validate a product idea or feature before building it — 5 JTBD questions (customer's job, current workaround, why switch, adoption barriers, success metric), then a readiness score with risks and a next step. Use when an idea already exists and the question is whether it is worth building: «стоит ли делать», «нужна ли эта фича», «проверь идею», «есть идея — оцени», «а что если добавить», «имеет смысл?», «зайдёт ли», «оценить гипотезу», «валидировать идею», validate this idea, is this worth building, should we build this, sanity-check this feature. Also use before writing a spec for a new product or a large feature. Do NOT use for: generating or exploring ideas from scratch (that is brainstorming), writing the spec itself (that is spec-first), technical design decisions, bug fixes, or small mechanical changes.

gurudevvv Bundle

Edit a vertical reel (Reels, Shorts, TikTok) out of one static take — entirely in the console, no CapCut. Cuts pauses by speech, slices a single fixed shot into different crop levels anchored to the face, adds push-ins and a motion-blurred punch zoom, drops in B-roll, burns three-level captions from speech recognition, ducks music under the voice. Use when asked to «смонтируй ролик», «собери рилс», «сделай видео динамичным», «нарежь дубль», «поставь субтитры на видео», «убери паузы из видео», edit my talking head video, make this reel dynamic, cut the silences.

gurudevvv Bundle

Multi-layer technical review for specs, ТЗ, and implementation plans using up to five independent reviewer perspectives (architecture, code-level, user POV, robustness, goals). Use when reviewing specs or technical designs before coding, or when user mentions "multi-layer review", "four reviewers", "несколько ревьюеров", "devil's advocate", "codex reviewer", "отдай на проверку", "проверь ТЗ", "review the spec", "review this design". Do NOT use for reviewing finished code or general Q&A.

gurudevvv Bundle

Download YouTube videos and HLS streams (m3u8) from platforms like Mux, Vimeo, etc. using yt-dlp and ffmpeg. Use this skill when users request downloading videos, extracting audio, handling protected streams with authentication headers, or troubleshooting download issues like nsig extraction failures, 403 errors, or cookie extraction problems.

gavishap Skill

Hand work between Claude Code and Codex (or any two agents) with zero copy-paste, via the _relay/STATE.md baton. Use at the start of a session ("catch up", "resume", "where were we") and at the end ("save", "hand off", "wrap up"), or whenever the user says they're switching agents.

gavishap Bundle

Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.

gavishap Bundle

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.

rosslevinsky Skill

Work breakdown for a superseded v1 plan — it writes phases.md, not execution.md. Use when the user invokes /plan-phase-v1, or is continuing an existing v1 plan produced by /plan-init-v1; a plan carrying the `Format: v2` marker belongs to /plan-phase. Reads the plan document and breaks it into ordered phases, proposes the phase structure to the user for approval, then creates a phase document (with checklist) for each phase and writes a new phases.md execution tracker alongside the plan. The original plan document is never modified.

thiagon1 Skill

Creates Loaders for deco.cx — server-side data fetching functions with configurable Props for the Admin. Use when fetching data from external APIs, creating inline loaders in sections, building reusable loader blocks, optimizing data payloads, or connecting sections to data sources.

thiagon1 Skill

VTEX IO Workspace — abrir, esperar login e debugar no navegador

totvs Skill

Gera o esqueleto de um Layout WCM do Fluig — a view FreeMarker (.ftl) que define as regiões/áreas onde os widgets são posicionados, usando o grid responsivo do Style Guide. Use quando o desenvolvedor pedir para criar/iniciar um novo layout (template de página) do Fluig a partir de um nome ou propósito.

totvs Skill

Gera o esqueleto de um Widget WCM do Fluig usando SuperWidget.extend (view FreeMarker + JS com init() e bindings), aplicando as convenções oficiais de customização. Use quando o desenvolvedor pedir para criar/iniciar um novo widget client-side do Fluig a partir de um nome ou descrição de propósito.

vikast908 Bundle

Help the user run design as cross-functional learning loops driven by outcomes and hypotheses. Ground every recommendation in named principles from Lean UX by Jeff Gothelf and Josh Seiden (cite concept + section only if present in references/book-passages.md). Use when the user runs /lean-ux, or discusses: Lean UX, hypothesis, MVP, design sprint-ish learning, outcomes over outputs.

vikast908 Bundle

Help the user give and solicit guidance that cares personally and challenges directly. Ground every recommendation in named principles from Radical Candor by Kim Scott (cite concept + section only if present in references/book-passages.md). Use when the user runs /radical-candor, or discusses: feedback, hard conversation, radical candor, ruinous empathy, performance talk.

vikast908 Bundle

Help the user make pages self-evident for scanners; validate with cheap usability tests. Ground every recommendation in named principles from Don't Make Me Think by Steve Krug (cite concept + section only if present in references/book-passages.md). Use when the user runs /dont-make-me-think, or discusses: usability, Krug, scan, navigation, landing friction, usability test.

vikast908 Bundle

Help the user manage as a multiplier via purpose, people, and process. Ground every recommendation in named principles from The Making of a Manager by Julie Zhuo (cite concept + section only if present in references/book-passages.md). Use when the user runs /making-of-a-manager, or discusses: new manager, 1:1, feedback, hiring, delegation, Zhuo, management.

vikast908 Bundle

Help the user design and interpret controlled experiments that are trustworthy. Ground every recommendation in named principles from Trustworthy Online Controlled Experiments by Ron Kohavi, Diane Tang, and Ya Xu (cite concept + section only if present in references/book-passages.md). Use when the user runs /ab-test or /trustworthy-experiments, or discusses: A/B test, experiment design, OEC, SRM, statistical significance, false wins.

vikast908 Bundle

Help the user lead product people by coaching and strategic context, not by assigning feature tickets. Ground every recommendation in named principles from Empowered by Marty Cagan (cite concept + section only if present in references/book-passages.md). Use when the user runs /empowered or /empowered-product-leadership, or discusses: coaching PMs, product leadership, empowered teams, strategic context, Cagan Empowered.

xiwan Bundle

AI 图片生成。支持豆包 Seedream（火山方舟）和 Pollinations（免费备选）。文生图、图生图、组图生成。

xiwan Bundle

Generate, cover, transcribe, and edit songs with YuE2 and SheetSage2/MERT2. Use for YuE2 full/melody/off generation, audio-to-ABC covers, style or lyric changes, score editing, agentic reharmonization, melody preservation, singable lyric adaptation, and reproducible listening comparisons; also for YuE2 生成、翻唱、改编、改谱、换词和智能体编辑.

xiwan Bundle

游戏剧本创作方法论与体检工具。用于：(1) 从主题推导故事、设计角色与角色定位、构建世界， (2) 用开端/过程/高潮/结局四要素搭剧本结构并设计选项与分支， (3) 写台词/旁白/指示，产出程序和美术能直接执行的开发向剧本， (4) 用 scripts/script_lint.py 对已写好的剧本做机械体检（台词过长、说明文倾向、缺动作、无意义选项等）。 触发词：游戏剧本、剧情策划、game script、narrative design、写台词、角色设定、 角色定位、剧本结构、分支剧情、选项设计、多结局、剧本体检。

xiwan Bundle

监控宿主机的 CPU、内存、磁盘使用情况。在资源紧张时主动告警。用于：(1) 检查系统资源状态 (2) 设置资源告警阈值 (3) 在 heartbeat 中定期监控。触发词：系统资源、CPU、内存、磁盘、硬盘、监控、告警。

xiwan Bundle

给万物打品味分。基于 Rubrics+ 评分体系，从设计(Design)、原创性(Originality)、工艺(Craft)、功能性(Functionality) 四个维度为任何事物评分（1-4分）。支持动态权重调整。适用于：评价网站、App、产品设计、代码架构、穿搭、家居、食物摆盘、海报、PPT、任何你想打分的东西。触发词：品味打分、taste score、打个分、评分、品味评价、rubrics。

xiwan Bundle

AI写作痕迹深度自检工具。基于 claudisms.ai 禁词表，扫描文稿中的 AI 味词汇、结构和语气问题。用于：(1) 播客口播稿自检 (2) 知乎/小红书文案去AI感 (3) 任何正式输出前的最后一道防线。支持中英文检测。触发词：去AI味、claudisms、写作自检、AI痕迹、deai、文风检查。

xiwan Bundle

Compress files and directories into ZIP archives. Use when the user asks to compress, zip, or archive files or folders. Supports excluding patterns like .git, node_modules, or specific file types.

xiwan Bundle

Analyze and restructure bloated SKILL.md files into a lean three-layer architecture (必读/按需/示例). Use when (1) a SKILL.md exceeds 150 lines or feels cluttered, (2) designing a new skill and wanting the right structure from the start, (3) auditing all skills for context efficiency. Triggers on：skill 瘦身、skill 太长、精简 skill、slim skill、optimize skill structure.

xiwan Bundle

小宇宙播客数据监控。获取播放量、完播率、订阅变化、评论。 支持 Token 自动刷新。需要主播账号登录凭据。 Triggers on: "小宇宙数据", "播客数据", "播放量", "完播率", "订阅者"

zamesin Skill

Update an installed Next Move Theory setup to the latest published canon + skills by re-running the official one-command installer straight from the public GitHub repo (zamesin/Next-Move-Theory-Canon-and-Skills, branch main). It refreshes the canon, the nmt-* skills (both Codex and Claude), the marked rules block in AGENTS.md / CLAUDE.md, and the README in place. Idempotent and safe: it never touches your own files and never deletes unrelated skills. Use when the user says "update NMT", "update the skills", "get the latest canon", runs $nmt-update, or when another skill reports that a newer version is available. Defaults to English.

zamesin Skill

Update an installed Next Move Theory setup to the latest published canon + skills by re-running the official one-command installer straight from the public GitHub repo (zamesin/Next-Move-Theory-Canon-and-Skills, branch main). It refreshes the canon, the nmt-* skills (both Claude and Codex), the marked rules block in CLAUDE.md / AGENTS.md, and the README — all in place. Idempotent and safe: it never touches your own files and never deletes unrelated skills. Use when the user says "update NMT", "update the skills", "get the latest canon", runs /nmt-update, or when another skill reports that a newer version is available. Defaults to English.

mxrsv Bundle

Review a spec or a plan before implementation starts — completeness, ambiguity, feasibility, executable steps, missing dependencies. For reviewing the project itself (code, UX, architecture, deps, docs) use the /review-change, /review-experience, /review-health and /review-release commands instead.

mxrsv Skill

Explain concepts, bugs, or design decisions in a deliberately chosen teaching style. Use when the user invokes the skill by name, says "explain", or wants to understand *why* (not just a fix). Honors flags `--story` (Journey + Analogy for bugs), `--why` (First principles + Counterfactual for design decisions), and `--diff` (Compare + Layered onion for X vs Y). Auto-picks style if no flag. Output in Vietnamese.

mxrsv Skill

Capture knowledge vào Tolaria wiki từ mốc lastLoggedAt — cook gợi nhớ (Claude/Codex/Cursor + git), hỏi người kể, soạn entry, xin duyệt rồi ghi qua record-capture.js. Dùng khi người dùng nói "log-wiki", "ghi wiki", "capture wiki", "tổng kết knowledge wiki", hoặc gọi /log-wiki.

mxrsv Skill

Turn an approved spec (the Linear issue's description) into an implementation plan — a `## Plan` checklist in the issue for small work, sub-issues for work that spans several commits or sessions. Use after "what to build" is clear. Trigger phrases - "plan this", "break into tasks". Not for vague requests - go back to `brainstorm` first.

mxrsv Skill

Brainstorm

mxrsv Skill

Đối chiếu tài liệu sống với code thật để tìm chỗ tài liệu mô tả hành vi code không có. Mặc định là scan READ-ONLY, không ghi file nào. Chỉ ghi khi chạy với --apply và sau khi người dùng duyệt diff. Fires ONLY when the user types /docs-drift.

mxrsv Skill

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.