Not in the top 1,000 by GitHub stars
amelieloher/math-paper-skills
Agent skills for writing research mathematics in LaTeX and building audited visual companion websites for papers.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/latex-math-writing/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4ec9c7bf76f0
No earlier version was observed for comparison.
skills/math-figures/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4ec9c7bf76f0
No earlier version was observed for comparison.
skills/math-paper-campaign/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4ec9c7bf76f0
No earlier version was observed for comparison.
skills/visual-paper/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4ec9c7bf76f0
No earlier version was observed for comparison.
Heat
6.1- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- latex-math-writing
skills/latex-math-writing - math-figures
skills/math-figures - math-paper-campaign
skills/math-paper-campaign - visual-paper
skills/visual-paper
How it works
latex-math-writing
When your agent uses it
Draft, edit, refactor, and publication-polish research-level mathematical LaTeX with economical statements, complete proofs, stable notation, source fidelity, readable displays, and rendered-page verification. Use for notes, papers, slides, theorem and proof writing, display repair, or turning a mathematically checked manuscript into a clear publication-ready paper without changing its claims.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,618 tokensWhen the skill is activated
Reference documents
17,932 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Route the task
- Establish authority before editing
- Preserve the mathematical contract
- Write the mathematics artisanally
- Whole-paper rewrites
- Typeset and verify
Files
SKILL.mdcore8,593 bytesSKILL.mdcore8,593 bytesSKILL.mdcore8,593 bytesSKILL.mdcore8,593 bytesagents/openai.yamlasset296 bytesreferences/artisan-writing.mddoc40,541 bytesreferences/banned-words.mddoc3,009 bytesreferences/house-style.mddoc10,287 bytesreferences/writing-rules.mddoc9,669 bytes../math-paper-campaign/references/route-polish.mddoc27,130 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmath-figures
When your agent uses it
Design, build and review figures and animations for mathematical papers and their companion websites — editable TikZ figures in the paper's notation, interactive figures, and pedagogical animations — under one rule, that a visual earns its place only by expressing a mathematical idea or teaching one. Use when proposing, drawing, revising, reviewing or animating any figure for a mathematical manuscript, talk or visual paper, or when deciding whether a figure should exist at all.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
827 tokensWhen the skill is activated
Reference documents
3,860 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Non-negotiable rules
- When the paper changes
Files
SKILL.mdcore3,725 bytesagents/openai.yamlasset306 bytesreferences/animations.mddoc3,236 bytesreferences/review.mddoc2,265 bytesreferences/static-figures.mddoc2,237 bytesreferences/value-and-design.mddoc3,648 bytes../visual-paper/references/figures.mddoc5,584 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmath-paper-campaign
When your agent uses it
Run a careful, multi-step campaign on a complete mathematical LaTeX paper — either building it from a proof outline, notes, a formal (Lean) development, or an earlier draft, or taking an already checked manuscript through phased polishing (reduce, cite, linearise, rewrite, introduction, final audit) to a publication-ready paper. Use for whole-paper writing, rewriting, or "make this paper better" requests that need statement-by-statement control, independent reviews, ledgers, and rendered-page checks.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
1,033 tokensWhen the skill is activated
Reference documents
15,123 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Choose the route
- What both routes share
- Style
- Prohibited shortcuts
- Related skills
Files
../latex-math-writing/references/house-style.mddoc10,287 bytesSKILL.mdcore5,022 bytesSKILL.mdcore5,022 bytesSKILL.mdcore5,022 bytesagents/openai.yamlasset336 bytesreferences/control-artifacts.mddoc9,989 bytesreferences/from-formalization.mddoc5,604 bytesreferences/route-build.mddoc12,361 bytesreferences/route-polish.mddoc27,130 bytesreferences/shared-controls.mddoc11,944 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvisual-paper
When your agent uses it
Build an interactive, audited "visual paper" website from a mathematical LaTeX paper (optionally with a Lean formalisation) — a zoomable dependency graph of the proofs, exact statements and step-by-step proofs quoted from the source, audited summaries, clickable notation, interactive figures, Lean badges, and a public static deployment. Use when turning a finished or nearly finished paper into a companion website, re-syncing one to a revised paper, auditing its dependency links, or launching it alongside an arXiv posting.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
1,469 tokensWhen the skill is activated
Reference documents
8,174 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Lifecycle
- Non-negotiable controls
- Working rules
Files
SKILL.mdcore6,490 bytesSKILL.mdcore6,490 bytesSKILL.mdcore6,490 bytesagents/openai.yamlasset266 bytesreferences/architecture.mddoc5,504 bytesreferences/dependency-graph.mddoc4,038 bytesreferences/external-sources-and-lean.mddoc3,057 bytesreferences/figures.mddoc5,584 bytesreferences/integrity-and-audit.mddoc4,499 bytesreferences/orchestration.mddoc5,795 bytesreferences/site-and-launch.mddoc6,300 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- latex-math-writing
- math-figures
- math-paper-campaign
- visual-paper
Repository facts
- License
- No license detected
- Created
- Oct 6, 2026
- Last pushed
- Oct 24, 2026
- Forks
- 5
- Open issues
- 0
- Project activity
- Active
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 7 notes
skills/latex-math-writing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/latex-math-writing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/latex-math-writing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/math-paper-campaign/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/math-paper-campaign/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/visual-paper/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/visual-paper/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 8 network referencesin 3 files: visual-paper/SKILL.md:20 latex-math-writing/references/artisan-writing.md:252 math-paper-campaign/SKILL.md:55
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 8 signals by file
skills/latex-math-writing/references/artisan-writing.md
- Network accessline 252
- `math-paper-campaign` — whole-paper control: building a paper from notes (statement freezing, packets, reviews) or polishing a checked manuscript through phases - `visual-paper` — an interactive companion website built from the finished p - Network accessline 254
- For formalising the same mathematics in Lean, see [LeanAutoformalizationSkills](https://github.com/scottnarmstrong/LeanAutoformalizationSkills)
skills/math-paper-campaign/SKILL.md
- Network accessline 55
- `latex-math-writing` — prose, notation, displays, and rendered-page verification inside each packet - `visual-paper` — an interactive companion website built from the finished paper - For formalising the same mathematics in Lean, see [Lea - Network accessline 57
- For formalising the same mathematics in Lean, see [LeanAutoformalizationSkills](https://github.com/scottnarmstrong/LeanAutoformalizationSkills)
skills/visual-paper/SKILL.md
- Network accessline 20
Every rule below comes from building two such sites: [the companion](https://scottnarmstrong.github.io/hcp-visual-paper/) to - Network accessline 21
[the companion](https://scottnarmstrong.github.io/hcp-visual-paper/) to - Network accessline 22
Armstrong–Kuusi–Loher, *Homogenization at a polynomial scale in high contrast*, and [the companion](https://amelieloher.github.io/DF-visual-paper/) to Loher–Mooney–Mouhot, *Döblin–Fourier cancellation and kinetic Aleksandrov estimates*. - Network accessline 23
[the companion](https://amelieloher.github.io/DF-visual-paper/) to Loher–Mooney–Mouhot,
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 8 facts
- Network access in prose of documentationlatex-math-writing/references/artisan-writing.md:252Low confidence
- Network access in prose of documentationlatex-math-writing/references/artisan-writing.md:254Low confidence
- Network access in prose of the SKILL.mdmath-paper-campaign/SKILL.md:55Low confidence
- Network access in prose of the SKILL.mdmath-paper-campaign/SKILL.md:57Low confidence
- Network access in prose of the SKILL.mdvisual-paper/SKILL.md:20Low confidence
- Network access in prose of the SKILL.mdvisual-paper/SKILL.md:21Low confidence
- Network access in prose of the SKILL.mdvisual-paper/SKILL.md:22Low confidence
- Network access in prose of the SKILL.mdvisual-paper/SKILL.md:23Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/latex-math-writing/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/latex-math-writing/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/latex-math-writing/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/latex-math-writing/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/latex-math-writing/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/latex-math-writing/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
