Product & Planning

sym01 Skill

Reviews and hardens an engineering plan against a standard checklist before any code is written. Use whenever the user enters plan mode, asks to "make a plan", "plan this out", "outline an approach", "break this down", "draft a roadmap", "how should we build X", or otherwise drafts multi-step engineering work — even if they never ask for a review. Also use before starting a complex coding task (3+ files, a new service, a cross-module refactor) that has no plan yet. Checks dependency and runtime currency, whether to parallelise across agents, a formatter/linter/type-check completion gate, an API contract when more than one module speaks HTTP, design tokens for UI work, and a tracked task file for long plans. DO NOT use for single-file edits, bug fixes, code review, questions that want an answer rather than a plan, or work already under way under an agreed plan.

sixz-ai Bundle

Triggers when: user says "start executing PRD", "start development", "execute breakdown", "implement REQ", or a Dev Agent is assigned to a breakdown directory under docs/. Use this skill to guide the execution of a prd_decomposer breakdown from start to finish, enforcing hard gates on requirements confirmation, TDD workflow, and git commit/push discipline.

sixz-ai Bundle

Triggers when: user mentions "PRD", "requirements", "break down requirements", "split PRD", or provides a long feature document. Use this skill to first clarify ambiguous requirements, confirm business logic and boundaries, and then decompose the finalized PRD into atomic frontend tasks focusing purely on BUSINESS LOGIC.

claude-world Skill

Full-autopilot trend discovery, deep research, and social publishing pipeline. Uses trend-pulse (20 sources), cf-browser (headless Chrome), and notebooklm (research + artifacts) MCP servers. Generates algorithm-optimized content based on Meta's 7 patent-based ranking algorithms. Use when user mentions trending topics, content creation, social media publishing, trend analysis, research pipeline, viral content, content scoring, or Threads posting.

cleardry Bundle

Academic paper writing skill with 12-agent pipeline. v2.4: LaTeX output formatting hardening — mandatory apa7 class, text justification fix, table column width formula, bilingual abstract centering, standardized font stack, PDF must compile from LaTeX. Supports IMRaD, literature review, theoretical, case study, policy brief, and conference paper structures. APA 7.0 (default), Chicago, MLA, IEEE, Vancouver citation formats. Bilingual abstracts (zh-TW + EN). Multi-format output (LaTeX, DOCX, PDF, Markdown). Triggers on: write paper, academic paper, paper outline, write abstract, revise paper, check citations, convert to LaTeX, guide my paper, parse reviews, revision roadmap, 寫論文, 學術論文, 論文大綱, 寫摘要, 修改論文, 檢查引用, 引導我寫論文, 帶我規劃論文, 逐章規劃, 論文架構, 審查意見, 修訂路線圖.

dsebban Skill

Coordinate OMP subagents on substantial work. Use when parallel discovery, specialist review, or clearly partitioned implementation will shorten or strengthen the result; skip trivial tasks.

lidge-jun Bundle

Design direction discovery and UX judgment for ima2 users. Use for UI/UX direction and design judgment — vague visual briefs, onboarding, empty/error/loading states, layout vocabulary, typography breaks, favicons, logos, and brand identity choices. Pairs with ima2-front: this skill decides the design direction, then load ima2-front to implement it. Triggers: make it look good, modern, clean, aesthetic, onboarding, empty state, error state, favicon, logo, design system, 깔끔하게, 모던하게, 감성적으로.

stotihv Bundle

Generate comprehensive plans for new features by exploring the codebase, synthesizing approaches, validating with spikes, and decomposing into beads. Use when asked to plan a feature, create a roadmap, or design an implementation approach.

qiaokes Skill

Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.

julianromli Skill

Generate structured task lists from specs or requirements. IMPORTANT: After completing ANY spec via ExitSpecMode, ALWAYS ask the user: "Would you like me to generate a task list for this spec?" Use when user confirms or explicitly requests task generation from a plan/spec/PRD.

nixihz Bundle

Draft, update, review, and maintain product requirement documents (PRD, user stories, scope statements, acceptance criteria) in Markdown. Triggered when the user needs to structure scattered requirements, refresh an existing PRD, review a requirement doc for gaps, or align documentation with Atlassian-style best practices.

awarexone Bundle

Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability hunting (IDOR, SSRF, XSS, auth bypass, CSRF, race conditions, SQLi, XXE, file upload, business logic, GraphQL, HTTP smuggling, cache poisoning, OAuth, timing side-channels, OIDC, SSTI, subdomain takeover, cloud misconfig, ATO chains, agentic AI), LLM/AI security testing (chatbot IDOR, prompt injection, indirect injection, ASCII smuggling, exfil channels, RCE via code tools, system prompt extraction, ASI01-ASI10), A-to-B bug chaining (IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth), bypass tables (SSRF IP bypass, open redirect bypass, file upload bypass), language-specific grep (JS prototype pollution, Python pickle, PHP type juggling, Go template.HTML, Ruby YAML.load, Rust unwrap), and reporting (7-Question Gate, 4 validation gate

oekazuma Skill

Survey a whole SvelteKit codebase as a senior Svelte/SvelteKit engineer, using svelte-vitals' scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve this SvelteKit app", "audit this codebase", "make this app more SEO/performance/security solid", or wants a roadmap of fixes rather than a review of a single diff. For routine regression checks while writing code, use the `svelte-vitals` skill instead.

redhat-developer Bundle

Author and validate RHDH Software Templates (Scaffolder) with AI-guided workflows. Use when asked to "create software template", "templatize a codebase", "convert repo to template", "write template.yaml", "location.yaml for templates", "scaffolder template", "golden path template", "parameterize skeleton files", "fix template gotchas", "validate template", "dry-run template", "list scaffolder actions", "explain scaffolder action", "Nunjucks in template", "template best practices", "reference templates", "example templates", "what templates are commonly used", "Template Editor", or mentions RHDH template authoring, Software Catalog templates, or /rhdh-templates commands. Covers setup, templatize (highest value), from-scratch create, reference example discovery, incremental parameter/step/skeleton authoring, location.yaml generation, common convention fixes, local validation, and live Scaffolder API dry-run/action discovery.

wxkingstar Bundle

Use when YOU are producing a structured, scannable artifact for humans rather than a paragraph of prose. Covers weekly / monthly / quarterly / daily reports (周报/月报/季报/日报/汇报/business review), dashboards & status sync (状态同步/盘点/概览/总结/小结/scorecard), postmortems & retros (复盘), code reviews & audits (代码审查/安全审计/审查/审计), KPI / OKR attainment (达成率/进度), financial analysis (财务分析/经营分析/P&L bridge/waterfall/variance), sales funnels & conversion (销售漏斗/转化分析), inventory / logistics / operations / customer / cohort analytics (库存/物流/运营/客户/复购分析), trend & period-over-period analysis (趋势分析/同比/环比/WoW/MoM/YoY), comparisons & selection (对比/方案选型/竞品比较/vendor evaluation/RFP), risk assessment & 2×2 matrices (风险评估/风险矩阵/RICE/BCG/likelihood × impact), heatmaps (热力图), action items & next steps (行动项/待办), and explicit mentions of AIO / AI Output Runtime / aio:name@major — plus validating or rendering AIO Markdown via the CLI. Skip for one-paragraph chat replies, code snippets, debugging help, or when the user explicitly asks for plain prose. Co

jy0xlu Bundle

Use when a task needs controlled capability discovery and adoption across official plugins, local skills, and trusted GitHub projects.

finos Skill

Manages intent — features, enhancements, bugs and the reasoning behind them — recorded as prose in the knowledge base with a lifecycle. Use when capturing new work, moving work through backlog, refinement or implementation, releasing or cancelling work, or asking what is pending, in flight, or no longer valid.

nibzard Skill

Manage project task lists stored in to-do.json and to-do.schema.json, including bootstrapping a backlog, selecting the highest priority task with jq, and updating task statuses. Use when Codex needs to read or update a JSON task list.

drhelius Bundle

Hack, modify, and translate Game Boy / Game Boy Color ROMs using the Gearboy emulator MCP server. Provides workflows for memory searching, value discovery, cheat creation, data modification, sprite/text finding, and translation patching. Use when the user wants to create cheats, find game values in memory, modify ROM data, translate a Game Boy game, patch game behavior, create ROM hacks, discover hidden content, change sprites or graphics, find text strings, apply Game Genie or GameShark codes, do infinite lives or health hacks, search for score or item counters, or reverse engineer data structures in Game Boy or Game Boy Color games. Also use for any ROM hacking, memory poking, or game modification task involving Gearboy.

drhelius Bundle

Hack, modify, and translate ColecoVision and Super Game Module ROMs using the Gearcoleco emulator MCP server. Provides workflows for memory searching, value discovery, cheat creation, data modification, sprite/text finding, translation patching, and rewind-assisted experimentation. Use when the user wants to create cheats, find game values in memory, modify ROM data, translate a ColecoVision game, patch game behavior, create ROM hacks, discover hidden content, change sprites or graphics, find text strings, do infinite lives or health hacks, search for score or item counters, inspect SGM RAM, or reverse engineer data structures in ColecoVision or Super Game Module games. Also use for any ROM hacking, memory poking, or game modification task involving Gearcoleco.

drhelius Bundle

Hack, modify, and translate TurboGrafx-16 / PC Engine / SuperGrafx ROMs using the Geargrafx emulator MCP server. Provides workflows for memory searching, value discovery, cheat creation, data modification, sprite/text finding, and translation patching. Use when the user wants to create cheats, find game values in memory, modify ROM data, translate a PC Engine game, patch game behavior, create ROM hacks, discover hidden content, change sprites or graphics, find text strings, do infinite lives or health hacks, search for score or item counters, or reverse engineer data structures in TurboGrafx-16 or PC Engine games. Also use for any ROM hacking, memory poking, or game modification task involving Geargrafx.

drhelius Bundle

Hack, modify, and translate Atari Lynx ROMs using the Gearlynx emulator MCP server. Provides workflows for memory searching, value discovery, cheat creation, data modification, sprite/text finding, and translation patching. Use when the user wants to create cheats, find game values in memory, modify ROM data, translate a Lynx game, patch game behavior, create ROM hacks, discover hidden content, change sprites or graphics, find text strings, apply Game Genie style codes, do infinite lives or health hacks, search for score or item counters, or reverse engineer data structures in Atari Lynx games. Also use for any ROM hacking, memory poking, or game modification task involving Gearlynx.

drhelius Bundle

Hack, modify, and translate Sega Master System, Game Gear, and SG-1000 ROMs using the Gearsystem emulator MCP server. Provides workflows for memory searching, value discovery, cheat creation, data modification, sprite/text finding, translation patching, and rewind-assisted experimentation. Use when the user wants to create cheats, find game values in memory, modify ROM data, translate an SMS/GG game, patch game behavior, create ROM hacks, discover hidden content, change sprites or graphics, find text strings, apply Game Genie or Pro Action Replay codes, do infinite lives or health hacks, search for score or item counters, or reverse engineer data structures in Sega Master System, Game Gear, or SG-1000 games. Also use for any ROM hacking, memory poking, or game modification task involving Gearsystem.

echohello-dev Skill

Guide Claude on complex, multi-step tasks by enforcing structured discovery, scoped planning, and verification before delivery.

echosell Bundle

Route natural-language TikTok commerce intelligence requests into authenticated EchoTik API workflows. Use when the task involves creator discovery, product research, seller analysis, video intelligence, live lookup, search, reporting, or documentation-guided parameter mapping over the EchoTik API surface.

echoyu1025-a11y Bundle

AI 产品架构正向设计 — 基于"四层骨架 + 数据流转"方法论,把一个 AI 产品想法推导成完整的文字版产品架构方案。当用户说"帮我设计 XX 的产品架构""我想做 XX,帮我搭骨架""给 XX 写一份立项方案""帮我准备 PRD 前期架构""帮我把 XX 的产品方案理出来""帮我面试答题 XX 产品架构""设计一个 AI 产品方案"等触发。适用于产品立项、PRD 前期规划、AI 产品方案设计、面试案例分析。不用于逆向拆解已有产品的架构(那是 product-architecture skill)。

edwardyen724-g Bundle

Close a work session safely — work out which dirty files are actually this session's, drive the loose ends (commit, push, merge, deploy, tests) to done one confirmation at a time, write the record the next session will read (memory always, CLAUDE.md/backlog when a standing fact changed, a handoff doc when it earns one), then archive the tab. Use when finishing or archiving a session, handing off because context is filling up, or asking whether it is safe to close this session.

ekuris-repos Skill

Use YAML frontmatter fields (title/description/tags/related/links_from) to traverse docs and pull the minimum relevant context into the session. Supports tag-based discovery for multi-concept queries and configurable traversal depth.

ellyseum Skill

Autonomous looped repo work. For each work unit (phase, bucket, item, whatever the user calls them): plan → peer-review council → revise (≤2 rounds) → implement → test → diff council → commit. Background-ping wake-up between iterations. Repeat until the user's roadmap is exhausted or a halt trigger fires. PERSISTENCE: Claude Code's task tool is the primary state — work units and per-unit grinder steps are TaskCreate'd at run start, TaskUpdate'd on every transition. Tasks survive auto-compact, so wake-up reads the task list to find where it left off. ACTIVATE on: "grind the backlog", "grind through this", "auto-grind <X>", "run the grinder on <X>", "go autonomous on <X>", "continue with the <buckets|phases|items>", "use the auto repo grinder". REQUIRES: `cordy` on PATH and at least 2 peer drivers reachable. Refuses to start with fewer drivers — single-peer "council" defeats the diversity benefit. Auto mode (or equivalent permission-bypass) must be active; the loop cannot pause for permission prompts. NOT for o

enulus Skill

A test skill for resource discovery

cawcut Bundle

Generate images or videos via CawCut official node capabilities using the local `cawcut` CLI. Defaults: gpt-image-2 for image/edit; Seedance 2.0 for video when live discovery is unavailable. Use when: "generate an image", "make a video", "text-to-image", "text to image", "text-to-video", "text to video", "image-to-image", "image to image", "edit/stylize/remix this image", "image-to-video", "image to video", "animate this photo", "omni-to-video", "omni to video", "/cawcut-generate", or free-form content descriptions (e.g. "a cute little hedgehog"). Supports text-to-image, text-to-video, image-to-image, image-to-video, and omni-to-video. Checks the App catalog first; hands off to cawcut-app-run on a similar App match. Requires `cawcut` installed and `cawcut auth login` completed. NOT for: running an App already chosen (use cawcut-app-run), app discovery/browsing ("what apps are there", "what can an app generate"), OAuth setup alone, or Web UI-only flows without the CLI.

chainreactors Skill

本项目的 OKR 目标和关键结果。每次开始新任务前参考此 OKR 确保工作方向一致。生成时间：2026-03-17。基于项目诊断 + 用户意图共同生成。

chainreactors Bundle

为任何项目生成定制化 OKR skill。分析项目内容、文档、结构、历史，在目标项目 .claude/skills/okr/ 下生成可加载的 SKILL.md 并部署每日追踪 Action。

andreijirohdev-labs Skill

Runs Andrei's cross-project memory/backlog audit — reconciling dev work (GitLab.com projects, Alpine Linux aports on gitlab.alpinelinux.org, GitHub), Leaflet.pub blog drafts, Obsidian notes, and Google Drive into a single status report + prioritized action list. Trigger this whenever Andrei explicitly says "run memory audit" (or close variants like "audit my backlog", "memory check-in"), whenever a monthly or quarterly check-in is due or requested, and whenever Andrei mentions specific tracked projects or drafts by name (nixops-config, aports/gh package, Recap Time Squad, Leaflet.pub drafts, homelab/NixOS config work) in a way that implies "where did I leave this?" Do not wait for Andrei to spell out the full routine each time — this skill already knows the sources, the staleness rules, and the output format.

andresd Skill

Capture, triage, and plan work on GitHub issues from natural language, across one or many repos. Auto-triggers on phrases like "capture this:", "what should I work on next", "what's on my plate today", "tidy the backlog", "find duplicate issues", "all <X> bugs to @<user>", and explicit `/jot-gh <cmd>`, `jot:`, or `jot-gh:` prefixes. Use when the user wants to turn brain-dump text into a well-formed GitHub issue, decide what to work on next, run dedup/stale passes, or bulk-edit issues by natural-language intent. Requires the `gh` CLI authenticated via `gh auth login`.

andresd Skill

Capture, triage, and plan work on Linear issues from natural language, across one or many teams. Auto-triggers on phrases like "capture this in Linear:", "what should I work on next in Linear", "what's on my plate in Linear", "tidy the Linear backlog", "find duplicate Linear issues", "all <X> Linear bugs to @<user>", references to Linear issue keys (e.g. "ENG-123"), and explicit `/jot-linear <cmd>`, `linear:`, or `jot-linear:` prefixes. Use when the user wants to turn brain-dump text into a well-formed Linear issue, decide what to work on next in Linear, run dedup/stale passes, or bulk-edit Linear issues by natural-language intent. Requires the Linear MCP server to be configured in Claude Code (`https://mcp.linear.app/sse`).