voidful
- 54 skills
- 0 followers
- 8 hours ago last updated
- ▌ Paper Review · voidful bundle學術論文審稿技能 — 以結構化四步驟流程完成深度論文審查，涵蓋批判性審查、分數預測、要點精煉與正式審稿產出。當使用者需要 review 一篇論文、模擬 reviewer 反應、評估論文能否被接收、或幫助判斷論文優缺點時，一定要使用此技能。觸發詞包括：review 這篇、幫我審稿、reviewer 會怎麼說、這篇能上嗎、paper review、給分數、找 weakness。適用於任何學術論文的審稿模擬與評估。
- ▌ Proof Writer · voidful bundle數學證明撰寫技能 — 從主張提取到 LaTeX 排版的完整證明工作流。當使用者需要撰寫或驗證數學定理、引理、命題的形式證明，或需要推導公式、整理理論分析時，一定要使用此技能。觸發詞包括：數學證明、prove、theorem、lemma、proposition、推導、理論分析、寫 proof、LaTeX 數學、formal proof。適用於機器學習理論、統計學習理論、最佳化等需要嚴謹數學推導的場景。
- ▌ Paper Reading · voidful bundle太奶讀論文 — 一位百歲阿嬤用繁體中文、生活比喻和動漫梗，帶你讀懂學術論文。當使用者提供論文 PDF、arXiv 連結、或貼上論文文字，並想理解論文內容時，一定要使用此技能。觸發詞包括：讀論文、解釋論文、看不懂、幫我理解這篇、這篇在說什麼、paper reading、explain this paper。適用於任何學術論文的直觀導讀。
- ▌ Paper Writing · voidful bundle頂級會議論文寫作技能——以嚴格 reviewer 視角指導從草稿到終稿的完整寫作流程。當使用者要寫論文、改善論文草稿、修改特定章節（introduction、method、experiments、conclusion）、潤色學術英文、回應 reviewer 意見，或問「這段怎麼寫」時，一定要使用此技能。觸發詞包括：寫論文、paper writing、improve my paper、幫我修改、review comments、rebuttal、LaTeX、NeurIPS/ICLR/ACL 投稿。適用於所有學術論文寫作場景。
- ▌ Idea Generation · voidful bundle學術研究的 Idea 產生技能——從發散到收斂，系統化地產出高品質研究構想。當使用者想腦力激盪研究方向、找新 research idea、或問「我接下來可以做什麼研究」時，一定要使用此技能。觸發詞包括：brainstorm、想 idea、研究方向、下一步做什麼、有什麼可以研究的、找 gap、research proposal。適用於任何階段的學術研究構想生成。
- ▌ Experiment Design · voidful bundle學術研究實驗設計技能——從研究假設到可重現實驗計畫的完整流程。當使用者需要規劃實驗、設計 ablation study、選擇 baseline、確定評估指標，或問「我應該跑哪些實驗」時，一定要使用此技能。觸發詞包括：實驗設計、experiment design、ablation、baseline、跑什麼實驗、evaluation metric、如何驗證方法。適用於機器學習、NLP、CV 等領域的實驗規劃。
- ▌ Professor Fit Analyzer · voidful bundleanalyze a professor from google scholar, publication lists, personal websites, lab pages, and field-specific bibliographic databases (e.g., DBLP, PubMed, SSRN, PhilPapers, MathSciNet, arXiv, Scopus) to evaluate research strength, mentoring quality, collaboration network, lab resources, research taxonomy, future directions, applicant fit, outreach emails, and interview strategy. designed for students at all levels — PhD applicants, master's students, and undergraduate researchers (capstone/thesis/independent study) — across all academic disciplines. use when the user wants to assess whether a professor or lab is worth applying to, compare advisors, prepare a cold email, find a thesis or capstone advisor, infer future research openings, or build a structured dossier from public academic evidence.
- ▌ Troubleshoot · voidfulInvestigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files. Use when users ask why something happened, why a request was slow, why tools or subagents were used or skipped, or why instructions/skills/agents did not load.
- ▌ Anthropic Sdk Upgrader · voidfulUse this agent when the user needs to upgrade Anthropic SDK packages. This includes: upgrading @anthropic-ai/sdk or @anthropic-ai/claude-agent-sdk to newer versions, migrating between SDK versions, resolving SDK-related dependency conflicts, updating SDK types and interfaces, or asking about SDK upgrade procedures. Examples: 'Upgrade the Anthropic SDK to the latest version', 'Help me migrate to the latest claude-agent-sdk', 'What's the process for upgrading Anthropic packages?'
- ▌ HTML Report · voidful bundleGenerate a rich, INTERACTIVE HTML report (not markdown!) and publish it to GitHub Pages. Use when the user asks for a "report", "writeup", "summary page", "dashboard", "share link", or anything that benefits from interactivity, charts, sortable tables, tabs, search, syntax highlighting, math, diagrams, or visual polish that markdown cannot deliver. Returns a public URL the user can share.
- ▌ Hung Yi Lee · voidful bundleExplain machine learning, deep learning, generative AI, LLMs, AI agents, and speech modeling in a Hung-Yi Lee-inspired teaching style. Use this skill when the user wants 李宏毅式教學: roadmap-first structure, intuition before math, black-box-to-mechanism explanations, everyday analogies, anticipating student confusion, practical debugging, and research-grounded context.
- ▌ Life Design Compass · voidful bundle以正體中文（臺灣）進行多輪人生設計對話，協助使用者從「你在這裡」盤點、重構卡點、釐清工作觀與人生觀、辨認心流與能量模式，生成三個同等地位的五年奧德賽版本，並把其中一個落成低成本原型與《個人人生設計藍圖》。Use when the user says 人生迷惘、找方向、轉職但不知道要什麼、卡住、人生規劃、人生設計、Odyssey Plan、工作觀、人生觀、心流、能量盤點。不是職業測驗、心理治療或替使用者做決定；一次只問一個主問題，先理解再設計，以實驗而非預言推進。
- ▌ Mian Hun · voidful bundle台灣拉麵客製化推薦引擎與知識百科 — Taiwan Ramen AI Skill. 1069+ shops, 6 broth types, personalized recommendations. Triggers on: 拉麵/ramen/推薦/豚骨/雞白湯/味噌/鹽味/醬油/沾麵/ 拌麵/排隊拉麵/台北拉麵/台中拉麵/高雄拉麵/想吃拉麵/今天吃什麼/ 麵屋/湯頭/麵體/叉燒/溏心蛋 and any Taiwan ramen related query.
- ▌ Michelin · voidful bundleAudit, rewrite, redesign, and validate Traditional Chinese for Taiwan and English copy or visual design so the result feels specific, intentional, and authored rather than templated. Use for 去 AI 味, 說人話, 台灣用語, anti-slop, natural copy, design critique, redesign, voice calibration, or blind human-versus-AI validation. Diagnose the AI-flavor cues first, preserve facts and constraints, revise only the failed families, then run an independent validation loop.
- ▌ Taiwan Hand Shaken Drink Expert · voidful bundleAn AI expert on Taiwan's major 300 multi-store hand-shaken drink chains, providing recommendations, calories, and menu info for exactly 13,500 items.
- ▌ Tutorial Creator · voidful bundleBuild, study, audit, or redesign source-grounded interactive tutorials and web books from documents, source repositories, or learning sites. Not for plain summaries or marketing pages.
- ▌ Claw Eval Zh · voidful bundle執行 claw-eval-zh 中文 agent benchmark，評估 OpenClaw agent 在中文真實任務上的表現。可用於測試模型的中文 agentic 能力、比較模型、跑 Pass^k 一致性評估，或匯出 Claw-Eval 風格的中文任務集。改編自 PinchBench，任務格式參考 Claw-Eval 中文任務風格。
- ▌ Alchemist Playbook · voidful bundleEvidence-based training-recipe advisor (煉丹調參) distilled from published runs: LLaMA 1-3, OLMo 1-3, DeepSeek-V3, SmolLM2, MiniCPM5, Kimi K2, GLM-5, PivotRL, Agents-A1, OPD, SEED, EvoLM, LFM2, VibeThinker, OpenThoughts, GRAPE, FAC-Synthesis, Zephyr, Tulu 3, SimPO, ORPO, QLoRA, Whisper, OWSM, wav2vec 2.0, HuBERT. Use whenever the user asks about training hyperparameters (learning rate, batch size, warmup, scheduler, optimizer, beta, weight decay, epochs), debugging a training run (loss spike, NaN, divergence, overfitting), designing a pretraining/SFT/DPO/RLHF/RLVR/agentic-RL/LoRA/QLoRA/speech (ASR/TTS) recipe, compute or token budgets, SFT data curation, distillation/curriculum/merging, on-device models, what to monitor or which benchmarks/eval suite per stage, capability regression/forgetting, tracking/reporting training runs (實驗追蹤, HTML run reports), or mentions 煉丹, 調參, "training recipe", "fine-tuning settings", "what LR should I use", "eval suite", "release gate" — even if they never say "hyperparameter".
- ▌ Academic Research · voidful bundleComplete academic research skill suite covering the full pipeline: paper reading (read/explain papers with storytelling), idea generation (brainstorm research directions), experiment design (plan experiments, ablation, baselines), proof writing (mathematical proofs, LaTeX theorems), paper writing (draft to camera-ready for top venues like NeurIPS/ICLR/ACL), paper review (structured 4-step review with scoring), and professor fit analysis (evaluate advisors, cold emails, interview strategy). Trigger keywords: read paper, brainstorm, experiment design, prove, write paper, review, professor fit, advisor, cold email, LaTeX, research, NeurIPS, ICLR, ACL, arXiv, 讀論文, 寫論文, 審稿, 實驗設計, 數學證明, 研究方向, 教授分析, 選指導教授.
- ▌ Update Screenshots · voidfulDownload screenshot baselines from the latest CI run and commit them. Use when asked to update, accept, or refresh component screenshot baselines from CI, or after the screenshot-test GitHub Action reports differences. This skill should be run as a subagent.
- ▌ Agent Sessions Layout · voidfulAgents workbench layout — covers the fixed layout structure, grid configuration, part visibility, editor modal, titlebar, sidebar footer, and implementation requirements. Use when implementing features or fixing issues in the Agents workbench layout.
- ▌ Update Skills · voidfulCreate or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "learn!", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.
- ▌ Heap Snapshot Analysis · voidful bundleAnalyze V8 heap snapshots to investigate memory leaks and retention issues. Use when given .heapsnapshot files, asked to compare before/after snapshots, asked to find what retains objects, or investigating why objects survive GC. Provides snapshot parsing, comparison, retainer-path helpers, and scratchpad scripts.
- ▌ Act On Feedback · voidfulAct on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.
- ▌ Create Draft Pr · voidfulCreate a draft pull request for the current session. Use when the user wants to open a draft PR with the session's changes.
- ▌ Chat Customizations Editor · voidfulUse when working on the Chat Customizations editor — the management UI for agents, skills, instructions, hooks, prompts, MCP servers, and plugins.
- ▌
- ▌
- ▌
- ▌ Agent Customization · voidful bundle**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). USE FOR: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized workflows; packaging domain knowledge; fixing YAML frontmatter syntax. DO NOT USE FOR: general coding questions (use default agent); runtime debugging or error diagnosis; MCP server configuration (use MCP docs directly); VS Code extension development. INVOKES: file system tools (read/write customization files), ask-questions tool (interview user for requirements), subagents for codebase exploration. FOR SINGLE OPERATIONS: For quick YAML frontmatter fixes or creating a single file from a known pattern, edit the file directly — no skill needed.
- ▌ Tdd · voidfulUse when implementing any feature or bugfix. Enforces RED-GREEN-REFACTOR cycle with test-first approach.
- ▌ Code Review · voidfulUse when the user wants a code review instead of implementation. Prioritizes correctness bugs, behavioral regressions, missing tests, and risky assumptions.
- ▌ Refactoring · voidfulUse when improving code structure without changing behavior. Ensures each refactoring step preserves all existing tests.
- ▌ Git Workflow · voidfulUse when making changes that should be committed. Enforces atomic commits, meaningful messages, and clean history.
- ▌ Writing Plans · voidfulUse when you have a spec or requirements for a multi-step task. Creates implementation plans with bite-sized tasks, exact file paths, and verification steps.
- ▌ Security Audit · voidfulUse when reviewing code for security vulnerabilities. Covers prompt injection, path traversal, command injection, and agent-specific attack vectors.
- ▌ Launch · voidfulLaunch and automate VS Code (Code OSS) using agent-browser via Chrome DevTools Protocol. Use when you need to interact with the VS Code UI, automate the chat panel, test UI features, or take screenshots of VS Code. Triggers include 'automate VS Code', 'interact with chat', 'test the UI', 'take a screenshot', 'launch Code OSS with debugging'.
- ▌ Hygiene · voidfulUse when making code changes to ensure they pass VS Code's hygiene checks. Covers the pre-commit hook, unicode restrictions, string quoting rules, copyright headers, indentation, formatting, ESLint, and stylelint. Run the hygiene check before declaring work complete.
- ▌ Architecture Review · voidfulUse when evaluating whether a proposed change fits the existing architecture. Prevents layer violations, dependency cycles, and accidental coupling.
- ▌ Sessions · voidfulAgents window architecture — covers the agents-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development guidelines. Use when implementing features or fixing issues in the Agents window.
- ▌ Documentation Review · voidfulUse when reviewing documentation for accuracy, completeness, and alignment with source code. Catches doc-code drift before it confuses readers.
- ▌ Performance Analysis · voidfulUse when investigating slow execution, high memory usage, or excessive token consumption. Systematic measurement before optimization.
- ▌ Systematic Debugging · voidfulUse when encountering any bug, test failure, or unexpected behavior. Four-phase root cause investigation. No fixes without understanding the problem first.
- ▌ Add Policy · voidfulUse when adding, modifying, or reviewing VS Code configuration policies. Covers the full policy lifecycle from registration to export to platform-specific artifacts. Run on ANY change that adds a `policy:` field to a configuration property.
- ▌ Fix Errors · voidfulGuidelines for fixing unhandled errors from the VS Code error telemetry dashboard. Use when investigating error-telemetry issues with stack traces, error messages, and hit/user counts. Covers tracing data flow through call stacks, identifying producers of invalid data vs. consumers that crash, enriching error messages for telemetry diagnosis, and avoiding common anti-patterns like silently swallowing errors.
- ▌ Merge · voidfulMerge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.
- ▌ Commit · voidfulCommit staged or unstaged changes with an AI-generated commit message that matches the repository's existing commit style. Use when the user asks to 'commit', 'commit changes', 'create a commit', 'save my work', or 'check in code'.
- ▌ Azure Pipelines · voidful bundleUse when validating Azure DevOps pipeline changes for the VS Code build. Covers queueing builds, checking build status, viewing logs, and iterating on pipeline YAML changes without waiting for full CI runs.
- ▌ Fix CI Failures · voidfulInvestigate and fix CI failures on a pull request. Use when CI checks fail on a PR branch — covers finding the PR, identifying failed checks, downloading logs and artifacts, extracting the failure cause, and iterating on a fix. Requires the `gh` CLI.
- ▌ Integration Tests · voidfulUse when running integration tests in the VS Code repo. Covers scripts/test-integration.sh (macOS/Linux) and scripts/test-integration.bat (Windows), their supported arguments for filtering, and the difference between node.js integration tests and extension host tests.
- ▌ Create Pr · voidfulCreate a pull request for the current session. Use when the user wants to open a PR with the session's changes.
- ▌ Update Pr · voidfulUpdate the pull request for the current session. Use when the user wants to push new changes to an existing PR.
- ▌ Auto Perf Optimize · voidful bundleRun agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
- ▌ Component Fixtures · voidfulUse when creating or updating component fixtures for screenshot testing, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, and common pitfalls.