Explore

Identify existing codebase patterns (naming conventions, architectural patterns, testing patterns) to maintain consistency. Use when generating code, reviewing changes, or understanding established practices.

RICE, MoSCoW, Kano, and value-effort prioritization frameworks with scoring methodologies and decision documentation. Use when prioritizing features, evaluating competing initiatives, creating roadmaps, or making build vs defer decisions.

Validate in any of six modes — spec quality, single-file review, spec-to-implementation drift, constitution rule enforcement, comparison between two artifacts, or sanity-checking your understanding. Use when checking a spec by ID, validating a file by path, detecting drift, enforcing constitution rules, comparing two sources ("$X against $Y"), or asking a freeform validation question.

Use when completing implementation, fixing bugs, refactoring code, or any time you need to verify the test suite passes. Also use when tests fail and you hear "pre-existing" or "not my changes" — enforces strict code ownership. Ensures MECE coverage (no overlap, no gaps) and that ALL test categories including E2E are executed.

Create and validate solution design documents (SDD). Use when designing architecture, defining interfaces, documenting technical decisions, analyzing system components, or working on solution.md files in .start/specs/.

Create and validate product requirements documents (PRD). Use when writing requirements, defining user stories, specifying acceptance criteria, analyzing user needs, or working on requirements.md files in .start/specs/.

Scaffold, status-check, and manage specification directories. Use when creating a new spec, reading spec status, transitioning between phases, or logging decisions on a spec in .start/specs/.

Decompose a single-feature specification into a linear, phase-by-phase implementation plan. Use this for medium-complexity work — single feature, one or two components — where transparent human-in-the-loop phase review is preferred over factory automation.

Decompose a multi-feature or multi-component specification into factory-consumable artifacts. Use this for high-complexity work — multiple features, three or more components, or parallel-eligible workstreams.

Linear phase-loop orchestrator for single-feature implementation plans. Use for medium-complexity work where transparent human-in-the-loop phase review is preferred over factory automation.

Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.

Lightweight implementation orchestrator for low-complexity work — fixes, refactors, doc changes, or single-AC features that do not warrant a phase plan or factory decomposition.

Create or update a project constitution with governance rules. Uses discovery-based approach to generate project-specific rules.

You MUST use this before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation.

When the user wants to write a multi-part thread or content series for Twitter/X, LinkedIn, Threads, Instagram (Reel/carousel/Story series), TikTok (multi-part videos), YouTube (video series, multi-Short series), or Facebook. Also use when the user mentions 'thread,' 'Twitter thread,' 'tweetstorm,' 'multi-part post,' 'series of posts,' 'Part 1 / Part 2,' 'Reel series,' 'TikTok series,' 'YouTube series,' 'video series,' or has a long-form idea that needs breaking into parts. For single posts, see post-writer-sms. For carousels, see carousel-writer-sms.

When the user wants to set up or update their social media profile, voice, audience, content pillars, or platform preferences. Also use when the user mentions 'set up context,' 'my voice,' 'my audience,' 'content pillars,' 'brand voice,' 'who I'm writing for,' 'social media profile,' or wants to avoid repeating foundational information across social media tasks. Use this at the start of any new project before using other social media skills — it creates .agents/social-media-context-sms.md that all other skills reference.

When the user wants to write a social media post for LinkedIn, Twitter/X, Threads, Bluesky, Facebook, Instagram, TikTok, Pinterest, or YouTube. Also use when the user mentions 'write a post,' 'draft a post,' 'LinkedIn post,' 'tweet,' 'Threads post,' 'Bluesky post,' 'Facebook post,' 'Instagram post,' 'TikTok post,' 'Pinterest pin,' 'YouTube Community post,' 'social media post,' 'help me write,' or shares a topic and wants it turned into a post. For deeper visual-platform caption writing, see caption-writer-sms. For multi-part content, see thread-writer-sms. For carousels, see carousel-writer-sms. For opening lines, see hook-writer-sms.

Use when the user says brain, project knowledge, what do we know about, open tasks, or recent decisions, or runs /brain or /brain-update. SQLite project_brain.db tracker for entities, relationships, tasks, threads, decisions, events.

把带时间戳的 narration.json 合成为中文解说音频。使用 MiMo TTS（mimo-v2.5-tts）或 Fish Audio（s2.1-pro-free）或显式配置的通用 IndexTTS HTTP 服务逐段生成语音， 按时间窗动态适配语速并处理响度；输入输出时间线上的旁白，产出 tts_segments 与 tts_meta.json。 外发说明：每段旁白文字会发给所选 TTS 服务（MiMo / Fish Audio / 用户自托管的 IndexTTS），--voice-ref 的参考音频会发给 MiMo。 另含实验性的英译中 dub 路径：只在显式选择 dub 模式并传 --confirm-voice-rights 时运行，会把源视频音频发到 MiMo ASR， 并以原说话人的声音为参考经 MiMo voiceclone 克隆配音；只可用于用户有权使用、且说话人同意被克隆声音的内容。 触发词：配音、语音合成、TTS、解说配音、 voiceover、text to speech、旁白配音。

把视频分析为结构化理解索引：场景检测、ASR 转写、逐场景 VLM 观察、静音窗口、融合时间线和写作 brief。 用于理解、索引或总结视频，也作为后续创作前的分析阶段。输入视频文件；输出 scenes.json、 asr_result.json、vlm_analysis.json、silence_periods.json、timeline_fusion.json、agent_narration_brief.md。 触发词：视频理解、视频分析、视频索引、video understanding、analyze video、看懂视频。

按需把一部成片拆成可复用的制作参考：测镜头节奏与响度，标注段落与音轨分工，把原片事实与可迁移方法分开， 导出不含原片人名台词的 production_reference.json 供下次制作参考。不在默认生产路径上。 触发词：拆片、拆解成片、制作参考、参考模板、production reference。

把长视频按 Agent 选择的原片区间剪成短片。作为两阶段创作流程中的剪辑环节，读取 clip_plan.json 与源视频， 输出 edited_source.mp4；随后 Agent 按输出时间线写 narration.json。支持单视频与多视频（sources manifest）拼剪， 本工具不读取、不映射旁白。 触发词：视频剪辑、剪辑式解说、video cut、clip plan、拼剪。

合成视频解说最终成片：把旁白音频铺到源视频上，按旁白窗口压低原声，生成 SRT / ASS 字幕并可烧录， 最后做响度标准化。作为最终合成阶段使用。输入源视频、tts_meta.json 与旁白位置； 输出 recap 成片和字幕。触发词：视频合成、混音、字幕、压字幕、assemble video、mux、ducking、subtitles、成片。

Turn a one-sentence startup idea into a structured product brief with problem, audience, value proposition, 5-7 MVP features, 90-day metrics, risks, and a go-to-market snapshot. Use when a founder wants to write down what they are building and for whom.

Design pricing for a product. Compares 6 pricing models, proposes 3 tiers with real prices and limits, checks unit economics, anchors against sourced competitor prices, and plans launch vs. scale pricing. Use when a founder asks what to charge or how to structure plans.

Pick the 5 metrics that matter at a startup's current stage, with definitions, targets, actions when below target, a minimal tracking setup, and a weekly review template. Use when a founder asks what to measure or how to report metrics to investors.

Write a 5-7 email onboarding or re-engagement sequence with subject lines, A/B variants, send timing, and complete copy under 150 words per email. Use when a founder needs lifecycle emails for a product.

Use for software supply-chain security assessment covering SBOM, SCA, CI/CD pipelines, container images, build integrity, dependency provenance, and vulnerability reachability.

Provides reverse engineering techniques. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.

主动渗透测试工具链。覆盖信息收集、端口扫描、漏洞扫描、Web 渗透、SQL 注入、目录爆破、密码破解等场景。 通过 MCP server（pentestMCP / mcp-security-hub）将 20+ 安全工具暴露给 AI agent。 触发关键词：渗透测试、端口扫描、Nmap、漏洞扫描、Nuclei、SQL 注入、SQLMap、目录爆破、FFUF、密码破解、Hashcat、信息收集、子域名、Web 渗透、ZAP、Burp。

Use when analyzing suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules, sandboxing, and anti-analysis behavior.

Use for authorized source-code security review and SAST workflows including Semgrep, CodeQL patterns, dangerous API hunting, and fix verification.

统一自动化入口。覆盖浏览器自动化（Playwright）和 Windows 桌面应用自动化（OpenReverse）。 浏览器场景：打开网页、点击、填表、爬取、截图、自动化登录、渗透页面交互。 桌面场景：操作 IDA/x64dbg 等 GUI 工具、Windows UI Automation、视觉驱动交互、桌面应用网络抓包。 触发关键词：浏览器自动化、桌面自动化、打开网页、填表、爬取、截图、自动化登录、Playwright、agent-browser、headless、OpenReverse、UIA、CUA、桌面操作、Windows 自动化。

Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication, authorization, rate-limit, and CI/CD testing.

Use when the user says m0 handoff, before I compact, end of session, save session state, resume where we left off, or continue in Cursor or Claude Code. Writes or reads a compact_checkpoint so a cold start becomes a continuation.

Package an existing talking-head / interview / podcast video with timed, designed GRAPHIC OVERLAY cards — kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to the transcript, on a 16:9 / 9:16 / 4:5 canvas of your choice; the clip plays untouched underneath. Trigger on "graphic overlays", "on-screen graphics", "package / dress up my video". Not plain subtitles (/embedded-captions). Unclear → /hyperframes.

Use when the user wants a short, design-led, unnarrated motion graphic: kinetic type, stat count-up, chart hit, logo sting, lower-third, animated map, or UI animation. Longer or narrated: /general-video. Unclear: /hyperframes.

Install, discover, and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add or hyperframes catalog, installing one item or every block matching a tag, wiring an installed item into index.html, or working with hyperframes.json. Covers discovery, install locations, block sub-composition wiring, component snippet merging, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

Use when a HyperFrames composition needs seek-safe 2D/3D keyframes, GSAP timelines, CSS keyframes, Anime.js, WAAPI, FLIP, paths, masks, SVG morph/draw, text trails, 3D depth, or `hyperframes keyframes` diagnostics. Don't use for broad scene strategy, brand design, media sourcing, captions, or general video planning.

Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.

Mandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or motion graphic, including a promo, explainer, captioned clip, title card, overlay, slideshow or interactive deck, Remotion port, or any HyperFrames HTML composition. Also use it to inspect, diagnose, validate, preview, publish, or batch-render an existing HyperFrames project. Inputs may be a website URL, GitHub PR, Figma design or URL, text or brief, existing footage, or music. It resumes project state, captures intent when applicable, selects and installs the owning workflow, and routes domain capabilities. HyperFrames is the default output framework unless the user explicitly chooses another framework for the deliverable or asks only to record a browser session.

Use when a phase plan should be peer-reviewed by other AI CLIs before execution, or the user asks for a cross-AI review. Invokes Gemini, Claude, Codex, or OpenCode and writes REVIEWS.md for /gsd-plan-phase --reviews.

Use when the user wants a dashboard of all phases or to run more than one phase in parallel. Shows phase status with recommended next actions, runs discuss inline, and dispatches plan and execute as background agents.

Use when .planning/ looks inconsistent, files are missing, or state seems wrong. Validates .planning/ integrity, reports missing files, bad config, and orphaned plans, and --repair fixes what it finds.

Use when the user wants to think through an idea before committing to a plan, e.g. /gsd-explore auth strategy. Runs a Socratic session, optionally spawns research, then routes output to notes, seeds, requirements, or new phases.

Use after a phase's code is written, or when the user asks to review changed files for bugs, security issues, or quality. Spawns the gsd-code-reviewer agent at quick, standard, or deep depth and writes the phase REVIEW.md.

Use when .planning/phases/ has accumulated directories from completed milestones. Shows a dry-run of what moves to .planning/milestones/v{X.Y}-phases/ and archives only after confirmation.

Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.

Measurement approaches, profiling patterns, bottleneck identification, and optimization guidance. Use when diagnosing performance issues, establishing baselines, identifying bottlenecks, or planning for scale. Always measure before optimizing.

Writing effective tests and running them successfully. Covers layer-specific mocking rules, test design principles, debugging failures, and flaky test management. Use when writing tests, reviewing test quality, or debugging test failures.

Create architectural decision records (ADRs), system documentation, API documentation, and operational runbooks. Use when capturing design decisions, documenting system architecture, creating API references, or writing operational procedures.

Context enrichment for frontend UI development using shadcn/ui and Tailwind CSS. Use when building component libraries, implementing UI designs, theming, or working with accessible React components.

Unified domain and data modeling for business entities, invariants, schema design, aggregate boundaries, and evolution strategy. Use when designing business models, schema changes, bounded contexts, or consistency rules.

Unified codebase discovery across structure navigation, tech-stack detection, and documentation extraction. Use when onboarding to a project, locating implementation paths, identifying frameworks/tooling, or validating docs against code reality.

Use when creating new skills, editing existing skills, auditing skill quality, converting skills to markdown conventions, or verifying skills before deployment. Triggers include skill authoring requests, skill review needs, or "the skill doesn't work" complaints.

Multi-agent code review with specialized perspectives (security, performance, patterns, simplification, tests)

Refactor, simplify, or clean up code for improved maintainability without changing business logic

Implementation entry point. Use to execute a completed specification. Auto-detects the decomposition tier (Direct, Incremental, or Factory) from spec artifacts and dispatches to the matching execution sub-skill.

Generate and maintain documentation for code, APIs, and project components

Systematically diagnose and resolve bugs through conversational investigation and root cause analysis