Skip to main content
Manusで任意のスキルを実行
ワンクリックで
SipengXie2024
GitHub クリエイタープロフィール

SipengXie2024

3 件の GitHub リポジトリにある 32 件の収集済み skills をリポジトリ単位で表示します。

収集済み skills
32
リポジトリ
3
更新
2026-07-18
リポジトリエクスプローラー

リポジトリと代表的な skills

scientific-schematics
特殊効果アーティスト・アニメーター

Generate scientific figures as raster PNG via Codex's native image_gen (collaborating-with-codex bridge). Two roles — (1) design exploration, generating several diverse direction drafts in parallel for the user to pick from; the chosen draft is either used directly (manuscript, slides/PPT rework) or handed to tikz-figures as a replication reference, at the user's choice; (2) final raster output for pictorial figures (lighting/texture/3D/hand-drawn concept art, graphical abstracts) or whenever the user prefers a polished PNG. Codex runs its imagegen-scientific-schematics skill for design and visual review; this skill supplies the writing-side entry point, prompt guidance, and publication checklist. Includes an opt-in pastel modern-ML style preset (ICLR/NeurIPS 2024-2025 airy look) for when the user asks for pastel / modern ML figure styling.

2026-07-18
claim-verification
編集者

Evidence-reliability check. Walks every % claim tag in LaTeX manuscript/*.tex, confirms \cite{} citekeys resolve against .writing/refs.bib (exported from Zotero), runs semantic match against network-fetched abstracts to catch hallucinated or mismatched citations, optionally checks numeric/table consistency, flags any [NEEDS-EVIDENCE] or draft-only markers. Run on demand or when the skeleton is ready for the human author.

2026-07-15
drafting
テクニカルライター

Use when turning an approved outline and its claim stubs into LaTeX manuscript prose, writing each section's paragraphs under the claim-first discipline (resolve evidence, then write `% claim: id`-tagged prose). Reads the per-section writing standards, style cautions, and terminology ledger. Trigger after outlining, when `.writing/manuscript/*.tex` is empty or a section still needs prose; before claim-verification and polish. Also trigger on "draft the paper", "write the Methods section", "turn the outline into prose".

2026-07-15
planning-foundation
テクニカルライター

Use whenever a writing task will span more than 5 tool calls, multiple sessions, or risks hitting context-window limits, writing a paper, a long literature thread, a multi-section revision, anything where losing mid-task state would hurt. Creates a persistent `.writing/` directory that acts as working memory on disk, so the outline, claims, findings, and progress survive context resets. Every other superpower-writing skill assumes this directory exists; initialize it first. Trigger even when the user does not explicitly ask for "planning".

2026-07-15
polish
編集者

Polish prose in three passes: strip AI-writing tells, apply Strunk's rules for clarity, then hold every research claim to its evidence. Two modes: edit in place, or diff-first where the original is untouched until the user approves each change. Use when the user asks to 润色 / 改写 / 精修 / 打磨 a draft, or says "polish", "refine", "tighten", or "improve". Preserves meaning, numbers, citations, and [NEEDS-EVIDENCE] markers; never smooths an unsupported claim into a supported-sounding one.

2026-07-15
rebuttal
編集者

Builds a grounded, venue-compliant response to reviewers for a CS/systems/ML paper. Atomizes every reviewer comment into an issue board with a fixed action vocabulary, enforces three finalize-blocking gates (provenance, commitment, coverage), drafts in strict R-A-C format with page cross-references, and wires every claimed change to a real manuscript location. Use when the user says "rebuttal", "reply to reviewers", "respond to reviews", "OpenReview response", or "ICML/NeurIPS rebuttal".

2026-07-15
tikz-figures
ソフトウェア開発者

Generate publication-quality LaTeX/TikZ figures for paper manuscripts: architecture diagrams, protocol/data-flow pipelines, sequence diagrams, geometry/math schematics. Compile-verified (xelatex + overlap checker + visual review loop) with a mandatory two-candidate preview for the user to pick from. Use when the user asks for: 论文配图、画架构图、画流程图、TikZ 图、复刻论文图、tikz/latex diagram、vector figure.

2026-07-15
citations
その他の高等教育教員

Generate and verify BibTeX. Adds a paper by DOI or arXiv id through the Zotero library (it fetches the metadata and open-access PDF), then emits the BibTeX. Verifies a citation's authors, title, venue, and year against the real record to catch hallucinated or misattributed references, and audits a .bib for missing fields, missing DOI or arXiv id, and duplicates. Use when managing citations, generating BibTeX, verifying references, or cleaning up a .bib. 中文触发:管理引用、生成 BibTeX、核验参考文献、整理 bib。

2026-07-15
このリポジトリの収集済み skills 20 件中、上位 8 件を表示しています。
brainstorming
ソフトウェア開発者

Use when designing complex multi-step features, building new components, or planning significant behavior changes that require design exploration before implementation.

2026-07-16
debugging
ソフトウェア開発者

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

2026-07-16
spec-interview
ソフトウェア開発者

Use when refining design docs and specs through deep questioning. Triggered when user says "help me refine this plan", "ask me about the project", "deep interview", or after brainstorming produces a design doc.

2026-07-16
tdd
ソフトウェア開発者

Use when implementing any feature or bugfix, before writing implementation code

2026-07-16
collaborating-with-codex
ソフトウェア開発者

Use when delegating coding work — prototyping, debugging, analysis, review, implementation, or generating publication-quality scientific/architecture diagrams — to Codex CLI. Supports multi-turn sessions via SESSION_ID.

2026-07-15
planning-foundation
プロジェクト管理専門家

Use when starting complex multi-step tasks, research projects, or anything needing >5 tool calls. Provides the persistent .planning/ directory used as on-disk working memory across sessions.

2026-07-15
stashing
プロジェクト管理専門家

Use when switching to another project, waiting on dependencies, or temporarily setting aside unfinished work.

2026-07-15
collaborating-with-hermes
ソフトウェア開発者

This skill should be used when the user asks to "ask Hermes", "get a second opinion", "consult another model", or needs independent analysis, research, or code review. It must also run in parallel with Codex for reasoning, analysis, research, and review consultations.

2026-07-12
このリポジトリの収集済み skills 11 件中、上位 8 件を表示しています。
3 件中 3 件のリポジトリを表示
すべてのリポジトリを表示しました