fudesign2008

@fudesign2008 source repo

78 skills
0 followers
5 hours ago last updated

▌
Openspec Archive Change · fudesign2008
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

0
installs
▌
Fangirl · fudesign2008 bundle
当用户说彩虹屁、夸夸我、鼓励一下、迷妹模式、恋爱模式、御姐模式、知音模式、父王英明、父王驾到、温柔姐姐、治愈模式、极简模式、帝王模式、帝王、陛下驾到、陛下、吾皇万岁、霸总模式、霸总、霸道总裁、总裁模式、总裁、CEO模式、CEO、天外天模式、天外天、天外、突破模式，或说切换模式、列出模式、可用模式、查看模式，或说 rainbow vibes、cheer me up、hype me up、praise me、fangirl mode、love mode、onee-san mode、gentle sister、comfort me、zen mode、emperor mode、your majesty、bixia mode、CEO mode、boss mode、bazong mode、beyond mode、beyond、horizon mode、break through、go beyond、list modes、switch mode、exit companion，或 Hook 在里程碑完成、情绪感知时触发。技术小迷妹编码陪伴，提供情绪价值与个性化赞美；多模式定义见 skills/fangirl/modes/ 与 _index.json。

0
installs
▌
Zhetian · fudesign2008 bundle
当用户说黑皇、大黑狗、姬紫月、段德、庞博、叶凡、姜太虚、狠人大帝、老疯子、无始大帝、安妙依、遮天、切换人物、列出人物、有哪些人、换个人、谁在、退出遮天、关闭遮天、正常模式时触发。遮天小说人物陪伴，10 位精选人物以各自独特的方式陪伴使用者编码与工作。

0
installs
▌
Task Router · fudesign2008
Auto-activated at the start of every non-trivial conversation. Parses true intent before classifying, enforces the pre-flight checks that weaker models skip, and routes to the correct workflow. Trigger: always — no keyword required.

0
installs
▌
Debug Workflow · fudesign2008
Systematic debugging protocol: root-cause identification before any fix, hypothesis-driven investigation, and structured failure recovery. Prevents the most common failure mode of weaker models — applying random fixes and hoping something works. Trigger: bug, error, crash, broken, wrong output, not working, unexpected behavior. Also invoked automatically by task-router.

0
installs
▌
Coding Workflow · fudesign2008
Four-phase gated coding workflow (Explore → Plan → Execute → Verify). Encodes the actual reasoning discipline of top-tier models, not the idealized version. Trigger: any task involving code creation, modification, or refactoring. Also invoked automatically by task-router.

0
installs
▌
Distill Session · fudesign2008
Structured extraction of implicit reasoning from top-tier model sessions into explicit, reusable rules for weaker models. Use when a weaker model fails a task, when you want to mine a successful session for transferable patterns, or when you notice a gap between what you did and what you could explain. Trigger: "distill", "extract pattern", "why did opus do that", "learn from", "what did I do differently".

0
installs
▌
Go Deploy · fudesign2008
Open the project's deployment platform link. Triggers when user says 「去部署」「部署平台」「准备部署」 (go deploy / deploy platform / prepare to deploy) — even without explicitly saying "open link", as long as the intent is to access a deployment console or release platform. The skill reads docs/deploy.md for deployment links; if absent, scans project docs to extract and generate config; if nothing found, prompts user to provide. Supports multiple deployment links per project.

0
installs
▌
Jira Read · fudesign2008 bundle
Read Jira issue data from local cache or API, and download attachments via script (never into context). Triggers when user says "jira-read [JIRA-ID]", 「读取 Jira」「查看 Jira」「下载 Jira」「下载附件」 (read/view/download Jira / download attachments), or needs to fetch Jira issue data. Requires $JIRA_CACHE_DIR (e.g. ~/.cache/jira).

0
installs
▌
Think Big · fudesign2008
Strategic thinking framework — analyze whether something is worth doing, what the risks are, and what the long-term impact will be. Use when user says 「战略思考」「战略分析」「从战略角度看」「战略视角」「帮我想清楚这件事」「这件事值不值得做」「从更高视角分析」 / think-big, strategic thinking, strategy. Not for execution-level planning (that's tactical).

0
installs
▌
Git Commit · fudesign2008
Git commit unified entry point. Triggers when user says 「提交代码」「git commit」「帮我提交」「写 commit message」「生成 commit」「提交一下」「git-commit」「自动提交代码」「git-commit-auto」 (commit code / help me commit / write commit message / generate commit / auto commit), or when invoked by jira-fix-workflow phase 7.

0
installs
▌
Hybrid Debug · fudesign2008 bundle
Hybrid app (native shell + WebView/WKWebView/Electron + H5) full-stack debugging methodology — forces analysis across four layers (web runtime, native-web bridge, native config, platform runtime) instead of stopping at a single layer, preventing whack-a-mole surface fixes. Use when debugging hybrid app UI/theme/behavior issues, especially platform discrepancies (one platform reproduces, the other does not), repeated single-end fix failures, or silent failures involving native-H5 communication, theme switching, or platform runtime behavior. Triggers — 「hybrid 调试」「跨端调试」「全链路调试」「平台差异调试」「WebView 问题」「WKWebView 问题」「native 和 H5 交互问题」「单端修复失败」「跨端主题问题」「跨端样式不一致」 / hybrid debug, cross-platform debug, webview issue, native-web bridge, full-stack debugging, RN/Electron debugging.

0
installs
▌
Analysis Core · fudesign2008 bundle
Shared analysis-stage methodology for PDCA fix workflows: temporary-change permission and rollback gate, red-capable reproduction loop before hypothesis lists (user-pasted evidence excluded), instrumentation-debug with runtime-evidence-debug as default entry, analysis step skeleton (existence → research routing → phenomenon/locate/root-cause/upstream-eval/impact), mandatory analysis gate output block, and debug-verify loop. Parameterizes the post-analysis exit as {next-stage}. Referenced by PDCA hosts via frontmatter dependencies. Triggers — 「分析阶段核心」「分析核心」「临时改动门控」「红环门控」「打点调试门控」「调试验证闭环」「分析门控」 / analysis stage core, red-capable loop gate, temp-change gate, instrumentation debug gate, analysis gate output block, debug-verify loop.

0
installs
▌
Article Writer · fudesign2008
Use when 用户想写公众号、知乎技术文章、自媒体内容，或基于已有技术文档改写为可发布文章时。

0
installs
▌
Explain Simply · fudesign2008 bundle
Make hard concepts easy to grasp — dual-track explanation: a rational track that goes deep (one-sentence definition → why it exists → concrete shape in the user's codebase with real file/line evidence → key design implication) and an intuitive track that keeps it simple (everyday analogy + one-line memory anchor); the simple output is earned by the deep process. Use whenever the user asks 「X 是什么」「为什么需要 X」「A 和 B 能不能/怎么通信」「给我讲讲 X」「用大白话解释 X」「帮我理解 X」, "what is X", "how does X work", "why does X exist", "explain X", "teach me X" about mechanisms, architecture, protocols, or processes — even if they never say "explain". Analogies must not introduce wrong intuitions; code evidence must be real, never invented. Do NOT use for hands-on tool tutorials or onboarding walkthroughs (use teach), marketing articles (article-writer), or design-doc rewriting (tech-review-doc).

0
installs
▌
Jira Fix Queue · fudesign2008
Triggers when the user says「批量修复」「批量 jira-fix」「jira-fix-queue」「jira-fix-batch」「批量修复多个 Jira」「批量修复以下 bug」/ batch fix, batch jira-fix, jira-fix-queue, jira-fix-batch. Thin trigger shell: parse Jira IDs/URLs and enqueue them into goal-driven-queue with Engine jira-fix-workflow. Does not run fixes or merge. Do NOT use for a single issue (jira-fix-workflow) or a non-Jira queue (goal-driven-queue).

0
installs
▌
Pr Code Review · fudesign2008 bundle
Dual-axis (Standards∥Spec) multi-perspective PR review with confidence ≥80 filtering, severity calibration, plan alignment, and optional GitHub/GitLab review comment. Best-of: Claude /code-review pipeline + mattpocock dual-axis + Superpowers plan/severity habits. Triggers — 「PR 代码审查」「审查这个 PR」「code-review」「/code-review」「审 PR」「pull request review」「双轴审查 PR」 / pr code review, review this PR. Do NOT use as a name alias for mattpocock code-review or Superpowers requesting-code-review.

0
installs
▌
Solve Workflow · fudesign2008 bundle
Eight-stage PDCA workflow for systematically solving bugs, refactors, and feature-development tasks: clarify → analyze → explore solutions → review → plan → execute → verify → retrospect. Manual mode (default) pauses for user confirmation at each stage exit; auto mode runs end-to-end; ai-proxy overlay (thin freeze then occupy) is available independently. Triggers — 「明确问题」「分析问题」「探索方案」「审查方案」「制定计划」「执行计划」「检查验证」「复盘改进」(alias「回顾总结」)；「继续分析」「深入分析」「修改方案」「完善方案」「优化方案」「更新计划」「修订计划」「修改计划」；「自动模式」「自动分析」「自动解决」；「ai-proxy 模式」「AI 代理模式」「切换 ai-proxy」 / clarify problem, analyze problem, explore solutions, review solution, make plan, execute plan, verify, retrospective, auto mode, ai-proxy mode, switch to ai-proxy.

0
installs
▌
Unbox Anything · fudesign2008 bundle
Universal file/container unpacker for AI agents. Use whenever the user has a specific named file that is secretly a container of other files (an installer, document, app bundle, disk image, or any archive) and wants to extract or inspect its inner contents — even when they don't say 'unbox' explicitly. Cracks ~30 'box-like' formats into clean directories with a manifest: standard archives (zip/tar/7z/rar), ZIP containers (docx/xlsx/pptx/jar/apk/whl), system packages (deb/rpm/msi), installers & disk images (exe/dmg/iso/pkg), and chained nested containers. Cross-platform (mac/linux/windows) via 7z as primary tool with graceful fallbacks. Triggers: 「拆箱」「开箱」「解压文件」「拆包」「解压任意文件」「提取容器内容」「拆开[文件]」「看[文件]里面」 / unbox, unpack any file, extract container, what's inside this file. Do NOT use for: writing extraction code/scripts, creating or editing Office documents, installing software, comparing archive formats, or merging files.

0
installs
▌
Write Workflow · fudesign2008 bundle
Eight-stage document-writing host: clarify → analyze sources → explore → review → outline → execute writer → verify → retrospect. In-repo writer: tech-review-doc. External strong deps: humanizer, humanizer-zh. Auto mode never skips tech-review §1. Triggers — 「写文档」「写技术评审」「去AI痕迹」「人性化改写」「自动写文档」「write workflow」「humanize」. Do NOT use for code PDCA (solve-workflow), performance (perf-optimize-workflow), or marketing articles (article-writer).

0
installs
▌
Astrill Control · fudesign2008 bundle
Control Astrill VPN on macOS through its menu-bar GUI: status (app / tunnel / GUI menu / exit IP), connect, disconnect — all idempotent, verified by dual probes (tunnel process + exit IP) plus GUI menu state. Use whenever the user mentions Astrill, asks to turn the VPN on or off, connect or disconnect the VPN, check VPN status or exit IP, or needs to switch VPN state around network-sensitive steps where one platform requires the proxy and another requires a direct connection. Prerequisite (one-time): the app hosting the agent holds the macOS Accessibility permission. Do NOT use for other VPN clients or general network debugging. Triggers — 「Astrill」「打开 VPN」「连接 VPN」「VPN 开」「VPN on」「断开 VPN」「关掉 VPN」「VPN 关」「VPN off」「查 VPN 状态」「VPN 状态」「切换 VPN」「VPN 出口 IP」 / Astrill, turn on VPN, connect VPN, disconnect VPN, turn off VPN, check VPN status, toggle VPN, VPN exit IP.

0
installs
▌
Solution Review · fudesign2008 bundle
Authoritative framework for reviewing any proposed solution (code, config, process, tooling, or architecture decision) before implementation. Covers four core dimensions (effectiveness, side-effects/risks, feasibility, spec compliance) plus five strategic dimensions that catch decision-level failures the core four miss: reversibility calibration (Bezos one-way/two-way doors), failure-mode analysis (FMEA), operability (SRE Production Readiness Review), cost-vs-value (CBAM/WSJF), and team cognitive fit (Team Topologies). Use this skill whenever you need to review, validate, stress-test, or approve a proposed solution, plan, design doc, or approach — before any code is written or change is applied. Triggers — 「审查方案」「方案审查」「评估方案」「方案评估」「review proposal」「方案可行吗」「这个方案靠谱吗」「方案有没有风险」「方案评审」「设计评审」「决策评审」 / solution review, proposal review, design review, decision review, stress-test a plan, validate an approach.

0
installs
▌
Tech Review Doc · fudesign2008 bundle
Turn a technical design doc into a product/QA-readable technical review markdown (business language + Mermaid). Hard-gates §1 background/goals until the user explicitly approves before writing the file. Triggers — 「技术评审文档」「生成评审文档」「design to review」「tech review doc」「写技术评审」. Do NOT use for marketing articles (article-writer), code PDCA (solve-workflow), or AI de-slop rewriting (humanizer).

0
installs
▌
Merge Discipline · fudesign2008 bundle
Hard gate before merging into a protected branch: run Parts A→B→C→R→D (OpenSpec archive association, rebase/conflict pre-check, coverage preference, pr-code-review with content-matched depth via pr-review-gate (unset ≡ auto), squash decision from commit quality + tip-pin merge). Do NOT merge while an associated OpenSpec change is still active; do NOT skip on a direct "merge MR" command; do NOT auto-select squash when two viable strategies exist — ask with a commit-quality recommendation; a single-commit or single-permitted-strategy MR concludes without prompting; after merging, sync the local workspace onto the resolved target branch. Triggers — 「合并 tip」「merge tip」「合并纪律」「push 后合并」「archive 合入」「合并前门控」「rebase 检查」「冲突预检」「合并前 rebase」「先 archive 再 merge」「合并前 code-review」 / merge discipline, archive-before-merge, rebase pre-check, coverage gate, pr code review before merge.

0
installs
▌
Typescript Check · fudesign2008
TypeScript type-checking workflow. Use this skill whenever the user works with TypeScript and mentions type errors, type checking, or says "类型检查" (type check), "type-check", "tsc", "检查类型" — even if they don't explicitly ask for a "type check" but are encountering compilation or type issues in a TypeScript project.

0
installs
▌
Essence Diagnosis · fudesign2008 bundle
Use when a complex problem seems unsolvable and needs digging to the essence — diagnosis only, not fixing. Symptoms include massive logs with no root cause surfaced, complex crashes, architectural essence analysis, requirement authenticity verification, systemic chronic issues, information overload, disconnect between symptoms and essence, multiple intertwined factors, or premature-convergence tendencies — even when the user never explicitly says "diagnose". Also triggers on 本质诊断, 根因诊断, 深度诊断, 诊断问题本质, 梳理问题逻辑, 证据链分析, 逻辑链分析, essence-diagnosis.

0
installs
▌
Git Release Start · fudesign2008
Use when a version iteration starts and a release branch must be created — handles inconsistent branch-naming conventions across repos, multi-repo synchronized creation, and ensuring local tracking correctly points to origin/release/X.Y.Z rather than the base branch. Works with GitLab, GitHub, and other Git hosting platforms; single-repo or multi-repo. Triggers — 「创建release分支」「开release分支」「开分支」「迭代分支」 / create release branch.

0
installs
▌
Goal Driven Queue · fudesign2008 bundle
Queue orchestrator over child engines (goal-driven / solve / opsx-solve / jira-fix / opsx-jira-fix). Triggers when the user says「goal 批量」「跑队列」「任务队列」「无人值守队列」「把需求加入队列」「空闲时段跑任务」/ goal-driven-queue, goal-driven-batch, goal batch, run queue, unattended task queue. Each conversation auto-isolates its backlog under .goal-driven/queues/; intake pre-approval, serial consumption, caps, acceptance. Jira lists enqueue here (also via jira-fix-queue / opsx-jira-fix-queue; legacy triggers jira-fix-batch / opsx-jira-fix-batch). Use to enqueue now and run later, or to start/inspect/review this conversation's queue. Do NOT use for a single ad-hoc long run (goal-driven-workflow), a single Jira issue (jira-fix-workflow / opsx-jira-fix-workflow), or setting up cron/schedulers themselves.

0
installs
▌
Jira Fix Workflow · fudesign2008 bundle
End-to-end Jira bug-fix workflow (stages 0-10), driven by a single Jira link, from intake through PR/MR merge and Jira writeback. Manual mode (default) pauses for confirmation between stages; auto/force modes run end-to-end; ai-proxy overlay (thin freeze then occupy) is available independently. Triggers — 「修复这个 bug [URL]」「帮我修复 [URL]」「jira-fix [URL]」「自动修复 [URL]」「强制修复 [URL]」「继续修复」「从上次继续」；「ai-proxy 模式」「AI 代理模式」「切换 ai-proxy」 / fix this bug, jira-fix, auto fix, force fix, resume fix, ai-proxy mode, switch to ai-proxy. Do NOT use for batch fixes across multiple issues — use jira-fix-queue instead (it enqueues into goal-driven-queue; confirm, then run the queue).

0
installs
▌
Learn And Improve · fudesign2008 bundle
Structured retrospective and knowledge sediment for completed work (the Act phase of PDCA). Run a disciplined post-work review (Keep-Problem-Try / Stop-Start-Continue / After-Action Review by context), judge which lessons are worth solidifying, pick the right carrier, validate the sediment gets reused, and feed improvements back. Use whenever finished work needs reflection — as a PDCA host closeout/review stage via frontmatter dependencies, or standalone on any completed task. Triggers — 「回顾总结」「复盘」「经验沉淀」「总结经验教训」「改进闭环」「沉淀规则」「项目复盘」 / learn and improve, lessons learned, retrospective, post-mortem, debrief.

0
installs
▌
Test Suite Ensure · fudesign2008
Ensure the current project has a proper test suite — detect tech stack & framework, scaffold if needed, generate unit tests (required, logic code only), and optionally generate/run E2E tests. Triggers when user says "test-suite-ensure", 「补全测试」「生成测试」「确保测试」「补充单元测试」「添加单元测试」「检查测试覆盖」 (complete tests / generate tests / ensure tests / add unit tests / check test coverage). Also callable by solve-workflow and opsx-solve-workflow in their execution-stage test steps.

0
installs
▌
Xquik Social Data · fudesign2008
Use when 用户需要从 Xquik 获取公开 X/Twitter 数据、搜索推文、查账号、看趋势、导出样本、整理社媒证据，或说 xquik、Xquik、X/Twitter data、tweet search、social evidence、社媒证据、推文搜索。

0
installs
▌
Code Design Review · fudesign2008 bundle
Authoritative framework for reviewing the design quality of proposed code changes — before implementation. Evaluates architecture-level quality attributes (testability, modularity, reliability, scalability, dependency direction via ISO 25010 + Clean Architecture + SDP) and code-level metrics (accidental complexity, coupling via Myers/Connascence, cohesion, change amplification, tech debt, cyclomatic/cognitive complexity, Law of Demeter) plus a security pass (OWASP Top 10). Use this skill whenever a proposed solution involves code changes and you need to assess whether the code is well-designed — not just whether it works, but whether it is maintainable, testable, and does not introduce design debt. Triggers — 「代码审查」「代码设计审查」「代码设计质量」「审查代码设计」「代码架构审查」「设计质量评估」「代码质量评审」「这个代码设计合理吗」「耦合度审查」「代码可维护性」 / code design review, code architecture review, design quality assessment, coupling analysis, maintainability review.

0
installs
▌
Figma Pixel Verify · fudesign2008 bundle
Measure whether a running UI matches a Figma design-spec table (computed styles / box metrics + optional screenshots). Use when checking pixel alignment / 对照 Figma 验收 after implement, including light/dark or multi-theme scope (switch theme, measure per-mode rows separately, report per theme). Bounded loop; honest residuals if no JS-eval channel. Triggers — 「检查像素对齐」「对照 Figma 验收」「设计保真检查」「是否对齐稿面」「figma 保真检查」「暗黑模式验收」「多主题保真检查」 / verify Figma fidelity, pixel check, dark mode fidelity check, multi-theme verify. Do NOT use as the primary implement workflow (use figma-pixel-implement) or for code→Figma.

0
installs
▌
Git Release Finish · fudesign2008 bundle
Use when releasing a Git repository version — tagging, merging release branches into main, resolving conflicts, or syncing changes between release branches. Handles ambiguous tag naming (v-prefix vs plain), unknown main branch (master/main/develop), ff-only merge method (forces cherry-pick strategy), protected-branch rules, cross-release hash-sensitive sync, and MR/PR extra-file cleanup. Single or multi-repo. Triggers — 「发版」「打tag」「发布版本」「版本发布」「release流程」「git-release」「multi-repo release」「release同步到另一个release」 / release a version, tag and merge, finish release branch.

0
installs
▌
Multi Agent Debate · fudesign2008 bundle
Stress-test a crash analysis, hypothesis, or technical conclusion by launching three adversarial agents in parallel — one defends, one attacks, one hunts new evidence — and resolving disputes with physical proof instead of argument. Always use this skill when the analysis has 2+ competing explanations that both seem plausible, when a conclusion relies on a single log sample or inferred chain longer than 3 steps, or when someone says "are you sure?", "that doesn't sound right", or challenges an assumption. Triggers: 辩论、求真、挑战假设、质疑分析、multi-agent-debate, "debate this", "challenge my analysis", "find holes in", "I'm not sure this is right", "verify this".

0
installs
▌
Staged Review Flow · fudesign2008
Shared review-stage flow for PDCA hosts: full decision review, code-design review for code-affecting solutions, Standards∥Spec dual-axis verdicts (no cross-axis merge rank), binary pass/fail, bounded auto optimization, design summary, and verification-report honesty composed with completion-evidence-discipline. Used by PDCA workflows. Triggers — 「阶段审查流程」「方案审查编排」「审查闭环」「验证报告诚实」「双轴审查」 / staged review flow, dual-axis review, verification honesty. Do NOT use as a standalone task workflow.

0
installs
▌
AI Proxy Discipline · fudesign2008 bundle
Bounded-authority AI proxy that occupies the human seat at interactive checkpoints of unattended runs: answers intake questions, picks among pre-approved approaches, grants bounded pre-authorization approvals, and adversarially checks completion reports — fresh context, artifact-only inputs, evidence-tagged verdicts, every decision ledger-marked and human-overturnable. Reserved for real humans: irreversible actions, over-budget, protected-branch merges, outcome acceptance, high-impact gates. Referenced by hosts via frontmatter dependencies; activated per-run by Stage-exit policy: ai-proxy. Triggers — 「AI 代理」「模拟人把关」「代理质询」「无人值守交互核对」 / AI proxy, simulated reviewer, bounded proxy. Do NOT use as a substitute for a present human who has not explicitly opted in and completed thin freeze; for auto-mode stage advancement (workflow-mode-lifecycle owns that); or as approval authority for the reserved list.

0
installs
▌
Brainstorm Workflow · fudesign2008 bundle
Design-to-plan host: thin wrap of Superpowers brainstorming, then hard handoff to solve-workflow Make a Plan. Use for new features and fuzzy design before coding. Triggers — 「头脑风暴」「设计头脑风暴」「brainstorm」「brainstorm workflow」「先设计再计划」「头脑风暴工作流」. Do NOT use for bug root-cause PDCA (solve-workflow / opsx-solve-workflow) or when you only need a one-line edit.

0
installs
▌
Delivery Discipline · fudesign2008
Optional code-delivery discipline: decide whether this run needs commit + PR/MR, then commit/push via git-commit and create or update the PR/MR. Use after verification (and OpenSpec archive when the host requires it) and before feature-branch-closeout. Do NOT use for protected-branch merge (merge-discipline) or release→main shipping (git-release-finish). Triggers — 「提交并开PR」「提交并开MR」「代码交付」「开PR」「开MR」「delivery-discipline」 / deliver code, commit and open PR, open merge request.

0
installs
▌
Opsx Jira Fix Queue · fudesign2008
Triggers when the user says「opsx 批量修复」「批量 opsx-jira-fix」「opsx-jira-fix-queue」「opsx-jira-fix-batch」「批量 OpenSpec Jira 修复」/ opsx batch fix, batch OpenSpec Jira fix, opsx-jira-fix-queue, opsx-jira-fix-batch. Thin trigger shell: parse Jira IDs/URLs and enqueue them into goal-driven-queue with Engine opsx-jira-fix-workflow. Does not run fixes or merge. Do NOT use for a single issue (opsx-jira-fix-workflow) or a non-Jira queue (goal-driven-queue).

0
installs
▌
Opsx Solve Workflow · fudesign2008 bundle
Eight-stage PDCA problem-solving workflow that persists analysis, proposal, design review, plan, execution, and verification into OpenSpec artifacts (openspec/changes/<name>/, archived into openspec/specs/) instead of leaving them only in chat context. Use for feature work, bug fixes, refactors, and complex engineering tasks that need long-term behavioral-contract traceability, team review, or auditability. Do NOT use for a quick one-off edit with no traceability need — use solve-workflow instead. Triggers：「opsx解决」「OpenSpec解决」「规范化解决」「创建OpenSpec变更」「创建opsx变更」「用OpenSpec分析」「用OpenSpec修复」「opsx自动解决」「OpenSpec自动解决」「opsx-solve」「opsx-solve-workflow」；「ai-proxy 模式」「AI 代理模式」「切换 ai-proxy」 / opsx solve, OpenSpec solve workflow, create an OpenSpec change, ai-proxy mode, switch to ai-proxy.

0
installs
▌
Opsx Workspace Gate · fudesign2008
Shared OpenSpec workspace gate for OPSX workflows: locate project root, verify openspec/, and require exact native OPSX skills before delegation. Triggers — 「OpenSpec 工程门禁」「OPSX 工程定位」「OpenSpec 原生技能检查」 / OPSX workspace gate, OpenSpec project root, native skill gate. Do NOT use for Jira, Git, retry binding, or implementation orchestration.

0
installs
▌
Design Approval Gate · fudesign2008
Hard gate before production implementation: do not write behavior/production code until the chosen solution/design is approved; named escapes for auto mode, Jira auto/force, and lean hotfix require short 留痕. Referenced by PDCA hosts before execution stages. Triggers — 「设计批准门禁」「方案批准后才能写码」「实现前批准」「design approval gate」 / design approval gate, pre-impl approval. Do NOT use as a name alias for brainstorming.

0
installs
▌
Git Conflict Resolve · fudesign2008 bundle
Use when a Git merge or rebase produces code conflicts, especially when AI-automated conflict resolution is error-prone (picking the wrong side, losing a refactor, reverting to an older version) and semantic analysis plus logic verification is needed. Also applies when a multi-round rebase stops repeatedly and conflict files need to be aggregated across rounds. Triggers — 「解冲突」「处理冲突」「git-conflict-resolve」「解决 merge 冲突」「解决 rebase 冲突」「冲突解决」 / conflict resolve, resolve merge conflict, resolve rebase conflict.

0
installs
▌
Goal Driven Workflow · fudesign2008 bundle
Goal-Driven long-run workflow: run an agent autonomously for hours toward a verifiable goal. Five stages — ① deep intake interview & output contract (approach frozen before launch) ② layer acceptance criteria + design the /goal condition (measurable end state, stated check, constraints, turn/time cap) ③ sub-agent division & context management (context-rot mitigation) ④ launch the long run (/goal, claude -p non-interactive, or manual-loop fallback) ⑤ completion report & human acceptance. Built on top of Claude Code's native /goal harness, with a generic fallback for environments without /goal. Triggers — 「goal 长跑」「goal run」「goal-driven」「目标驱动长跑」「一个 goal 下去跑」「长跑目标」「无人值守跑任务」「goal-run」 / goal run, goal-driven, long-run goal, autonomous run, run until done.

0
installs
▌
Known Issue Research · fudesign2008 bundle
External-research routing for confirmed code problems: triage whether the root cause is internal / external / hybrid, run a known-issue quick search before deep root-causing (platform silent failures, nested host runtimes, no code-level suspects), and evaluate industry-wide hard limits. Delegates all WebSearch discipline to effective-web-research. Referenced by PDCA hosts via frontmatter dependencies; load during the technical-analysis stage.

0
installs
▌
Test Guide From Code · fudesign2008 bundle
Generate a manual test guide for human testers from code changes (diff, commit, MR/PR). Triggers when user says 「生成测试指南」「测试指南」「人工测试指南」「测试指引」「test guide」「根据代码生成测试」「从 MR 生成测试指南」「从 PR 生成测试指南」 (generate test guide / manual test guide / test guide from code / from MR / from PR), or provides a diff/MR/PR link and asks for a test guide.

0
installs
▌
Android Webview Debug · fudesign2008
Unified WebView remote debugging toggle for Android projects. `android-webview-debug-enable` sets all `setWebContentsDebuggingEnabled` calls to `true` and records modified locations with their original content; `android-webview-debug-revert` restores from the record, listing any mismatched entries at the end for manual confirmation. Triggers: 「开启 WebView 调试」「恢复 WebView 调试」 / android-webview-debug-enable, android-webview-debug-revert. Suitable for Android projects that need to uniformly enable or restore WebView debugging.

0
installs
▌
Browser Debug Toolkit · fudesign2008 bundle
Browser runtime debugging toolkit — prioritize browser DevTools and CDP tools for runtime inspection and control when debugging UI/CSS/DOM layout, frontend interaction, and rendering issues. Default channel: ego-browser (macOS, runtime-checked) — full interaction, js(), raw cdp(), inherited login state, isolated task space, human-AI handoff. On unavailability or failure degrade along: playwright-mcp → agent-browser (non-macOS); web-access CDP Proxy (lightweight control + login state, curl-parallel); chrome-devtools-mcp (DevTools panels: computed style, network, perf trace). Triggers: 「浏览器调试」「UI 调试」「DOM 检查」「CSS 调试」「页面布局问题」「前端运行时调试」「chrome devtools」「CDP 调试」「登录态调试」 / browser debug, devtools, dom inspect, css debug, runtime debugging, login-state debug.

0
installs
▌
Figma Pixel Implement · fudesign2008 bundle
Implement Figma UI with export-faithful assets and a design-spec table for later measured verify. Use when implementing from Figma URLs/nodes or user asks pixel-level restore / 按稿实现, including explicit light/dark or multi-theme scope (theme detection, per-mode spec values, per-theme assets). Prerequisite: a working Figma design-context channel (MCP or equivalent)—not a Cursor-only skill name. Does NOT claim pixel alignment complete—hand off to figma-pixel-verify. Triggers — 「像素级还原」「按稿实现」「Figma 对齐实现」「还原 Figma」「figma 保真实现」「暗黑模式还原」「多主题保真实现」 / implement from Figma, pixel restore, dark mode implement, multi-theme fidelity. Do NOT use for code→Figma canvas writes, no-design creative UI, or post-impl alignment checking alone (use figma-pixel-verify).

0
installs
▌
Jira Status Writeback · fudesign2008
Post-merge Jira writeback SOP: transition only to「已修复」, then independent jira_add_comment with body. Triggers — 「Jira 状态回写」「回写已修复」「合并后写 Jira」「jira writeback」「jira status writeback」. Do NOT use for reading issues, creating issues, or pre-merge comments. Loaded by Jira fix hosts after merge via frontmatter dependencies.

0
installs
▌
Test First Discipline · fudesign2008
Hard discipline for behavior-changing work: write a failing test first, observe the failure, then write minimal production code; delete production code written before a failing test was observed. Distinct from test-suite-ensure (post-hoc coverage/scaffold). Referenced by PDCA execution stages. Triggers — 「测试先行」「先写失败测试」「红绿重构」「TDD 铁律」「test-first」 / test-first discipline, failing test first. Do NOT use as a name alias for tdd or test-driven-development.

0
installs
▌
Effective Web Research · fudesign2008 bundle
Effective web research discipline for AI agents — route first, then research with rigor. Step 0 triages whether a question needs external web lookup vs is answerable from the internal codebase/docs; when external, default mode auto-applies 4 maxims; on explicit 'strict/deep research' requests it runs a 7-dimension source-credibility evaluation (CRAAP + E-E-A-T) with an auditable report. When the static layer (WebSearch/WebFetch/curl) can't reach content (login-required / JS-rendered / anti-scraping like 小红书·公众号), it escalates to the real browser via the web-access skill (CDP, carries login state). Triggers: 「web 调研」「外部调研」「查资料」「有效调研」「严格调研」「深度调研」「严格查证」「登录态访问」「动态页面」「反爬」「这个库/框架怎么用」「有没有漏洞」「best practice 是什么」 / web research, look up, investigate, strict research, deep research, fact-check, login-state access, dynamic page, anti-scraping. Do NOT use for: searching the local codebase, reading repo files, grepping code.

0
installs
▌
Opsx Jira Fix Workflow · fudesign2008 bundle
OpenSpec-flavored end-to-end Jira bug-fix workflow that persists root cause, behavior change, fix plan, verification, and archive into OpenSpec artifacts (openspec/changes/<name>/, archived into openspec/specs/) instead of leaving them only in chat context or Jira comments. Use when a Jira issue needs long-term behavioral-contract traceability, team review, or auditability. Do NOT use for a quick fix needing no traceability — use jira-fix-workflow instead. Triggers：「opsx-jira-fix」「OpenSpec Jira 修复」「规范化修复 Jira」「opsx修复Jira」「Jira OpenSpec 修复」「opsx自动修复Jira」「用OpenSpec修复Jira」「opsx-jira-fix-workflow」；「ai-proxy 模式」「AI 代理模式」「切换 ai-proxy」 / opsx jira fix, OpenSpec Jira fix workflow, ai-proxy mode, switch to ai-proxy.

0
installs
▌
Perf Optimize Workflow · fudesign2008 bundle
Performance optimization paradigm workflow, proven across stacks: benchmark harness → evidence-validity gate (ten in-file disciplines: measurement artifacts, caliber pollution, device/profile mismatch, comparison environment state) → attribution → one-target-per-iteration optimization → A/B cross-run statistical verification → benchmark-log sediment, on an environment-gated iteration loop (no loop runner ⇒ honest stop). Seeds per-project code-insight/code-optimizer skills with probe scripts and evolves them every campaign (stack corpus in reference.md). Triggers — 「性能分析」「性能证据」「性能定位」「性能假设」「性能监控」「性能优化」「性能验证」「性能深入」「性能问题」「卡顿」「很慢」「前端性能」「Electron 性能」「伪影排查」「口径校准」「设备画像」 / performance analysis, perf evidence, locate bottleneck, perf optimization, perf verification, measurement artifact check. Do NOT use for non-performance bugs (solve-workflow) or trivial single-line edits.

0
installs
▌
Runtime Evidence Debug · fudesign2008 bundle
Default entry of the debug skill family when runtime observation is needed: static analysis stalled, a fix did not work, logs look correct but behavior is wrong, or fix verification needs before/after evidence. Covers escalation decision, targeted instrumentation (not shotgun logging), MRE reproduction, evidence tiers, confidence gating, escape hatches, and fix verification; composes with browser-debug-toolkit / hybrid-debug / channel enablers without demoting them. Triggers — 「打点调试」「打日志调试」「运行时调试」「运行时验证」「复现验证」「日志分析根因」「根因置信度不足」「静态分析碰壁」「修了还是不行」「日志正常但行为不对」「偶现」「调试默认入口」 / runtime evidence debugging, instrumentation debugging, escalate to runtime, evidence-driven debugging, fix didn't work, intermittent bug.

0
installs
▌
Tech Research Workflow · fudesign2008 bundle
End-to-end technology and competitor research workflow that turns a design-shaping question into a decision-ready, evidence-bound report family: self business audit (asset/hazard inventory with file:line), competitor first-hand runtime testing (five-step evidence method, evolution curves, same-track incident search), three-tier design mapping (copy / copy-the-idea / explicitly-not-copy), reflux loop (first version as constraint probe), layered reports, plus a lean path for single-question research. Triggers — 「技术调研」「竞品调研」「竞品分析」「技术调研报告」「调研报告」「竞品实测」 / tech research workflow, competitor research, competitive analysis, technology research report. Do NOT use for single-question web lookup without design output (use research / effective-web-research), known-bug upstream research routing (known-issue-research), or rewriting an existing design doc into a review doc (tech-review-doc).

0
installs
▌
Decision Fog Discipline · fudesign2008
Hard discipline when the path is still foggy: state destination, maintain decision tickets, graduate fog before solution exploration or OpenSpec proposal; ask humans one ticket at a time via clarifying-question-discipline. Triggers — 「决策雾」「决策票」「清雾再方案」「目的地未清」「decision fog」 / decision fog discipline, decision tickets. Do NOT use as a name alias for wayfinder.

0
installs
▌
Feature Branch Closeout · fudesign2008
Post-verification feature-branch closeout menu: after verify (and archive when applicable), and after optional delivery-discipline when code delivery is needed, present PR / merge / keep / continue options; optional worktree cleanup; selecting merge MUST load merge-discipline Parts A→B→C→R→D; keep/continue MUST NOT trigger merge gates. Open/update PR delegates to delivery-discipline. Triggers — 「分支收尾」「feature 收尾菜单」「合入或保留分支」「branch closeout」 / feature branch closeout, post-verify branch menu. Do NOT use as a name alias for finishing-a-development-branch.

0
installs
▌
Git Worktree Discipline · fudesign2008 bundle
Pre-write (docs or code) git/native worktree isolation with worktree-gate (always|never|ask; unset≡ask): detect reuse (incl. submodule guard), recommend suitability, create (native then ignored .worktrees/), setup+baseline, or decline/lean with 留痕; cleanup via feature-branch-closeout. Triggers — 「git worktree」「工作区隔离」「隔离工作区」「执行前隔离」「worktree 门控」 / git worktree discipline. Do NOT use as Superpowers using-git-worktrees alias or for closeout destroy.

0
installs
▌
Node Version Discipline · fudesign2008 bundle
Node version discipline — before running tsc / eslint / build / test / install in any Node project, align the Node version to the project's declared version (.nvmrc / .node-version / .tool-versions / volta / engines.node) and disclose it in the verification report, preventing false-pass / false-fail when the host default Node mismatches the project-pinned version; when the project declares no Node version at all, ask the user for the version and offer to persist a declaration file so future sessions/CI auto-align. Use this skill whenever the user is about to run a version-sensitive Node command, or mentions Node version mismatch / wrong Node / version conflict. 中文触发词「node 版本对齐」「nvm 对齐」「.nvmrc」「Node 版本纪律」「对齐 Node 版本」「切换 node 版本」「版本不匹配」「初始化 node 版本管理」「为工程增加 node 版本声明」「给工程加 .nvmrc」「无 .nvmrc 时补一个」「工程没有 node 版本管理」, English aliases node version discipline, nvm use, align node version, switch node version, add nvmrc, initialize node version.

0
installs
▌
Workflow Mode Lifecycle · fudesign2008
Shared lifecycle contract for manual/auto control-flow plus optional ai-proxy overlay recognition in workflow skills: auto and overlay always revert to manual on completion or interruption; re-entry needs an explicit trigger; implicit continuation never re-activates them; batch orchestrators pass Stage-exit policy explicitly. Overlay maps to auto carrier + policy; charter stays in ai-proxy-discipline. Hosts that omit ai-proxy triggers ignore overlay. Referenced via frontmatter dependencies. Triggers — 「模式生命周期」「切换自动模式」「切换 ai-proxy」 / workflow mode lifecycle. Do NOT use as the proxy charter or as a third control-flow enum.

0
installs
▌
Openspec Explore · fudesign2008
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

0
installs
▌
Openspec Onboard · fudesign2008
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.

0
installs
▌
Upstream Dependency Debug · fudesign2008 bundle
When a bug involves a named third-party library/framework, or symptoms correlate strongly with a platform/library-specific behavior, evaluate 'upgrade the dependency' BEFORE piling on local workarounds. Walks through a 4-step decision (is it upstream? → check Changelog/Release Notes → upgrade at low semver risk → only workaround if upgrade is infeasible), the upgrade engineering discipline (package-manager consistency, post-upgrade verification chain, semver risk, dedup check), and a result table. Use this skill whenever a bug smells like an upstream library issue — symptoms tied to a specific framework version, silent failures where code looks correct, workarounds that keep growing, or platform-specific rendering bugs that CSS cannot fix. Triggers — 「升级依赖」「依赖升级修复」「这个 bug 升级依赖能解决吗」「查 changelog 修复」「优先升级依赖」「升级依赖还是堆 workaround」 / dependency upgrade, upgrade to fix bug, changelog fix, avoid workaround, upgrade library to fix.

0
installs
▌
Openspec Ff Change · fudesign2008
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.

0
installs
▌
Domain Language Discipline · fudesign2008
Hard discipline for project domain language: maintain a pure glossary in CONTEXT.md (no implementation details), challenge fuzzy or conflicting terms in-session, create files lazily, keep orthogonal to OpenSpec behavioral contracts. Referenced by PDCA hosts during clarify/analyze when domain terms matter. Triggers — 「领域语言」「CONTEXT.md」「术语表」「统一语言」「领域词汇」 / domain language discipline, project glossary, CONTEXT.md. Do NOT use as a substitute for OpenSpec specs.

0
installs
▌
Openspec New Change · fudesign2008
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

0
installs
▌
Openspec Sync Specs · fudesign2008
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.

0
installs
▌
Intake Interview Discipline · fudesign2008 bundle
Deep intake discipline for unattended long-run hosts: interview with interactive-workflow depth while the human is present (destination → fog tickets → one-per-turn resolution → approach comparison), freeze the chosen approach plus open assumptions into the run contract with a bounded pre-launch self-review, self-answer mid-run decisions with recorded assumptions (clean stop + ticket report when the frozen approach is falsified — never a silent pivot), and roll the decision/assumption ledger into human acceptance. Referenced by goal-driven hosts via frontmatter dependencies. Triggers — 「深谈入库」「入库深谈」「前置深谈」「无人值守深谈」「决策冻结」「冻结方向」「自答留痕」「票台账」「方向证伪」 / deep intake interview, freeze the approach, runtime self-answer ledger, falsified-approach clean stop. Do NOT use as a name alias for clarifying-question-discipline or decision-fog-discipline, or for interactive attended workflows (solve-workflow owns those pauses).

0
installs
▌
Openspec Apply Change · fudesign2008
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

0
installs
▌
Openspec Verify Change · fudesign2008
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

0
installs
▌
Clarifying Question Discipline · fudesign2008
Hard discipline for clarifying with the user: one question per turn until shared understanding; walk the decision tree by dependencies; recommend an answer; look up facts, ask only decisions; explore context before asking; do not act until the user confirms clarity (or skips). Referenced by PDCA and perf hosts via frontmatter dependencies. Triggers — 「一次一问」「多轮问清」「澄清提问纪律」「推荐答案提问」「决策树追问」 / clarifying question discipline, decision-tree grilling.

0
installs
▌
Completion Evidence Discipline · fudesign2008
Hard discipline for verification and completion claims: do NOT claim tests passed, a fix works, or a task is complete without fresh evidence from commands or checks run in the CURRENT turn; label unavailable checks as pending with the exact action required. Referenced by PDCA verification stages via staged-review-flow and host workflows. Triggers — 「完成须有证据」「验证证据纪律」「宣称完成前验证」「completion evidence」 / completion evidence discipline, fresh verification evidence. Do NOT use as a standalone product workflow.

0
installs
▌
Runtime Verification Discipline · fudesign2008 bundle
Hard discipline for runtime verification in PDCA workflows: the AI executes verification itself in an environment — real preferred over simulated, subject to determinism + safety — never defaulting to a human checklist. Attempt-first, resolve a pluggable provider (project script/skill → shared capability skill), and hand to a human only at a true hard boundary with a stated reason. Use at any workflow verify/check stage (bug fix or feature) to decide WHERE verification runs, WHO runs it, WHETHER it suffices. Referenced by PDCA hosts via frontmatter dependencies. Triggers — 「环境验证」「真实环境验证」「真机验证」「真机测试」「模拟环境验证」「AI 验证」「验证分层」「验证充分性」 / runtime verification, environment verification, real vs simulated. Do NOT alias completion-evidence-discipline (evidence freshness) or runtime-evidence-debug (debug instrumentation).

0
installs
▌
Openspec Continue Change · fudesign2008
Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

0
installs
▌
Openspec Bulk Archive Change · fudesign2008
Archive multiple completed changes at once. Use when archiving several parallel changes.

0
installs

78 published skills