Paper Interpretation
digoal/blog
从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读，并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…
A skill your agent uses when structuring the appendix of a COLT (Conference on Learning Theory) submission — the unlimited-length proof appendix inside the single PDF — covering body/appendix…
Install Colt Supplementary
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-supplementary -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-supplementary --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/COLT-Skills/skills/colt-supplementary .claude/skills/colt-supplementary && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "colt-supplementary" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-supplementary into .claude/skills/colt-supplementary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-supplementary", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-supplementaryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-supplementary -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-supplementary --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/COLT-Skills/skills/colt-supplementary .agents/skills/colt-supplementary && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "colt-supplementary" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-supplementary into .agents/skills/colt-supplementary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-supplementary", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-supplementary -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-supplementary --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/COLT-Skills/skills/colt-supplementary .cursor/skills/colt-supplementary && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "colt-supplementary" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-supplementary into .cursor/skills/colt-supplementary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-supplementary", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/brycewang-stanford/Awesome-Journal-Skills.git --path COLT-Skills/skills/colt-supplementary--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-supplementary -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-supplementary --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/COLT-Skills/skills/colt-supplementary .gemini/skills/colt-supplementary && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "colt-supplementary" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-supplementary into .gemini/skills/colt-supplementary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-supplementary", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-supplementaryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-supplementary -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/COLT-Skills/skills/colt-supplementary .github/skills/colt-supplementary && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "colt-supplementary" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-supplementary into .github/skills/colt-supplementary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-supplementary", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-supplementary -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-supplementary --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/COLT-Skills/skills/colt-supplementary .opencode/skills/colt-supplementary && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "colt-supplementary" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-supplementary into .opencode/skills/colt-supplementary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-supplementary", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
colt-supplementary- GitHub stars
- 1.2k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 763 words
- Files
- 1
- Skills in repo
- 2,387
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when structuring the appendix of a COLT (Conference on Learning Theory) submission — the unlimited-length proof appendix inside the single PDF — covering body/appendix…
- Theorem restatement discipline
- SKILL.md covers Consequences of the single-PDF…, The 12-page split decision, Appendix architecture that… and Restatement discipline, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Notation tables
What it does
Colt Supplementary is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when structuring the appendix of a COLT (Conference on Learning Theory) submission — the unlimited-length proof appendix inside the single PDF — covering body/appendix splitting for a 12-page limit, theorem restatement discipline, lemma ordering, notation tables, and what referees expect to find where.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Documents & Office, covering PDF. The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的… The licence is MIT.
When your agent uses it
- Theorem restatement discipline
- Notation tables
- What referees expect to find where
Example prompts
- “/colt-supplementary”
What it can do on your machine
Read from SKILL.md and the folder at commit 932eb23. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are latex).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Colt Supplementary loads about 1.6k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 763 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 763 words, ~1,590 tokens.
Download SKILL.mdSave it as
.claude/skills/colt-supplementary/SKILL.md (or your agent's skills folder).- name
- colt-supplementary
- description
- Use when structuring the appendix of a COLT (Conference on Learning Theory) submission — the unlimited-length proof appendix inside the single PDF — covering body/appendix splitting for a 12-page limit, theorem restatement discipline, lemma ordering, notation tables, and what referees expect to find where.
COLT Supplementary
COLT's "supplementary material" is the appendix of the same PDF: the 2026 CFP (checked 2026-07-08) capped the main body at 12 PMLR-formatted pages excluding references and put no page limit on references and appendices, with the entire manuscript submitted as a single file. There is no separate upload, no later supplement deadline, and no distinction between "appendix" and "supplement" — which changes how you should architect the document compared to venues with detached supplements.
Consequences of the single-PDF model
- The appendix is unambiguously part of the reviewed record; referees are choosing to read it, not to download it. Lower the cost of that choice.
- Nothing can be added after the deadline. A proof hole discovered post-submission cannot be patched by a supplement upload the way an artifact fix sometimes can elsewhere.
- Length is free but attention is not: a 60-page appendix is normal at COLT, a disorganized one is a soft reject, because the referee's verification budget is the binding constraint.
The 12-page split decision
What must stay in the body:
- Formal problem setup: the model, the interaction protocol, the adversary or distributional assumptions, and the performance measure — complete, not "see Appendix A for the model."
- Every main theorem statement, with all hypotheses visible.
- A proof overview per main theorem: the decomposition, the key lemma, and the step where prior techniques fail. This is what earns the referee's appendix time.
- The comparison to nearest prior bounds (a small table often beats prose).
What belongs in the appendix: full proofs, auxiliary lemmas, generalized statements, deferred case analyses, extended related work, and any numerical-illustration details.
Appendix architecture that referees can verify
| Appendix section | Contents | Referee use pattern |
|---|---|---|
| A. Notation and preliminaries | Symbol table, standard inequalities used | Consulted repeatedly; keep to 2-3 pages |
| B. Proof of Theorem 1 | Restated theorem, roadmap paragraph, main lemmas, proof | Read linearly, checked line by line |
| C. Proof of Theorem 2 | Same pattern | Read only if Theorem 2 matters to the referee |
| D. Auxiliary lemmas | Technical facts shared across proofs | Jumped to via references |
| E. Deferred discussion / numerics | Extensions, illustration details | Skimmed |
Ordering rule: appendix sections mirror body theorem order, and each proof section is self-contained modulo Appendix A and D — a referee verifying Theorem 2 must never need to have read the proof of Theorem 1 unless the dependency is real and declared.
Restatement discipline
Restate every theorem and lemma before its appendix proof, with identical numbering, via a restatable environment rather than copy-paste (drift between two hand-maintained copies of a theorem is a notorious COLT embarrassment):
\usepackage{thmtools, thm-restate}
\declaretheorem[name=Theorem]{theorem}
% In the body:
\begin{restatable}{theorem}{mainregret}\label{thm:main}
Under Assumptions 1--2, ALG attains $R_T = O(\sqrt{dT\log K})$.
\end{restatable}
% In Appendix B:
\mainregret* % re-renders Theorem 1 verbatim, same number
\begin{proof}
We decompose the regret as ... (roadmap sentence first, then the argument).
\end{proof}Roadmap paragraphs are load-bearing
Open each major appendix proof with 4-6 sentences: the decomposition, what each lemma contributes, where the novelty sits, and which steps are routine. Referees use the roadmap to allocate verification effort; proofs without one get either shallow reads (bad for credit) or suspicious reads (bad for scores).
Show full SKILL.md (291 more words)Show less
Vignette: splitting a two-theorem online-learning paper
A draft proves an upper bound (algorithm + potential argument, 14 pages of proof) and a lower bound (instance family + information argument, 9 pages), plus one simulation. The COLT-shaped split:
- Body: protocol and definitions (2 pp), both theorem statements with remarks (2.5 pp), upper-bound overview with the potential function displayed and one key lemma proved in full (3 pp), lower-bound overview with the instance family drawn as a figure (2 pp), related-work table and discussion (1.5 pp), simulation figure with a two-sentence reading (0.5 pp), intro (1.5 pp) — twelve and a half, so the second remark and one corollary move to the appendix to make twelve.
- Appendix: A notation; B full upper-bound proof (restated theorem, roadmap, lemmas); C full lower-bound proof; D auxiliary facts; E simulation procedure.
- The key-lemma-in-body choice is deliberate: proving one central lemma completely in the body demonstrates the paper's proof standard where every referee will read it.
Common appendix defects at COLT
- Lemma used before it is stated anywhere, forcing a forward hunt.
- "By a standard argument" covering the one step that is actually new.
- Notation redefined locally inside an appendix section, colliding with Appendix A.
- Case analyses whose cases do not visibly exhaust the space.
- Cross-references into the body by page number instead of by label (page numbers shift when the class file changes at camera-ready).
- Illustration figures buried between proofs, breaking the verification flow — give numerics their own terminal section.
Cycle-volatility warnings
- The unlimited-appendix, single-PDF rule is the 2026 formulation; earlier cycles phrased limits differently and later ones may again (待核实 in each CFP).
- If a cycle ever adds a separate supplement channel or reviewable-code slot, its CFP will say so; do not assume either from this file.
Output format
[Split verdict] body self-contained / decision-critical material trapped in appendix
[Appendix map] <section -> theorem it serves>
[Restatement check] restatable environments / copy-paste risk
[Roadmaps] present for <k>/<n> major proofs
[Top structural fix] <one reorganization with highest referee payoff>© brycewang-stanford, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in COLT-Skills/skills/colt-supplementary of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Colt Supplementary next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Colt Supplementary this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Paper Interpretationdigoal/blog | 8.6k | — | ~1.5k | Automated safety check: Pass | GPL-2.0 | |
| Paper LensYSQ-boop/paper-lens | 101 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Paper ReviewRapidAI/MaClaw | 148 | — | ~1k | Automated safety check: Pass | MIT | |
| Ma Fulltext Managementhtlin222/meta-pipe | 139 | — | ~1.7k | Automated safety check: Notes | Custom licence | |
| Paper Interpreterchujianyun/skills | 742 | — | ~810 | Automated safety check: Pass | Custom licence |
Similar skills
Paper Lens
YSQ-boop/paper-lens
Read and critically analyze one academic paper from an arXiv URL/ID or a local PDF, producing a source-grounded Markdown report that can grow from a quick read into a reviewer-level deep review.
Paper Review
RapidAI/MaClaw
论文深度解读 Skill — 下载论文PDF → LLM深度解读（问题/创新点/方法原理/实验分析）→ PDF图片提取 → 生成组会PPT → 生成解读音频MP3。端到端学术论文解读工具。
Ma Fulltext Management
htlin222/meta-pipe
Collect and manage full-text PDFs for included studies, track provenance, and prepare documents for extraction.
Paper Interpreter
chujianyun/skills
论文解读助手。适用于用户发送 arXiv 论文链接，并希望下载论文、解读论文、生成读书笔记、做论文拆解或输出详细报告时使用。会在工作目录创建论文文件夹、下载 PDF 与 TeX Source（如有）、生成中文 Markdown 报告。默认先交付初稿，不自动复查；如果用户明确同意，再安排后续复查。不适用于只要简短推荐语的情况。
Mindmap Render
ai4s-research/ai4s-skills
Generate beautiful, high-resolution mindmaps from Markdown unordered lists.
More from brycewang-stanford/Awesome-Journal-Skills
All 2,387 skills in this repoAaag Data Analysis
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…
Aaag Literature Positioning
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…
Aaag Rebuttal
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…
Aaag Research Design
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…
Aaag Review Process
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…
Aaag Submission
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…
Related
Categories
Questions about Colt Supplementary
What does Colt Supplementary do?
A skill your agent uses when structuring the appendix of a COLT (Conference on Learning Theory) submission — the unlimited-length proof appendix inside the single PDF — covering body/appendix…. Colt Supplementary is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when structuring the appendix of a COLT (Conference on Learning Theory) submission — the unlimited-length proof appendix inside the single PDF — covering body/appendix splitting for a 12-page limit, theorem restatement discipline, lemma ordering, notation tables, and what referees expect to find where.
When should I use Colt Supplementary?
Colt Supplementary fits situations like: theorem restatement discipline; notation tables; what referees expect to find where.
How do I install Colt Supplementary in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-supplementary -a claude-code`. Or copy the skill folder (COLT-Skills/skills/colt-supplementary in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/colt-supplementary in your project. Claude Code loads it when a task matches its description.
How do I install Colt Supplementary in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-supplementary -a codex`. Or copy the skill folder (COLT-Skills/skills/colt-supplementary in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/colt-supplementary in your project. Codex loads it when a task matches its description.
Can I use Colt Supplementary in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-supplementary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/colt-supplementary, .gemini/skills/colt-supplementary, .github/skills/colt-supplementary and .opencode/skills/colt-supplementary in your project.
What does Colt Supplementary need to run?
SKILL.md names no scripts, command-line tools or credentials: Colt Supplementary is instructions for the agent only.
Does Colt Supplementary access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Colt Supplementary safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Colt Supplementary use?
Colt Supplementary is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Colt Supplementary use?
About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Colt Supplementary?
Skills that share tags, products or a category with Colt Supplementary: Paper Interpretation (digoal/blog, 8.6k stars), Paper Lens (YSQ-boop/paper-lens, 101 stars), Paper Review (RapidAI/MaClaw, 148 stars) and Ma Fulltext Management (htlin222/meta-pipe, 139 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Colt Supplementary?
brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,231 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.
Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.