Agent skill

Light Typesetting

by Light0305 in Light0305/Light-skills

Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11.

MITAuto-check passedDocuments & Office

Install Light Typesetting

skills CLI
$ npx skills add Light0305/Light-skills --skill light-typesetting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Light0305/Light-skills light-typesetting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Light0305/Light-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/light-typesetting .claude/skills/light-typesetting && rm -rf skills-src

Use ~/.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/

Facts

Skill name
light-typesetting
GitHub stars
640
Token cost
~3.3k tokens
SKILL.md length
1,412 words
Files
18 (incl. scripts, references)
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11.

  • Works in 9 steps: Freeze the input contract → Preflight before compilation → Select engine and bibliography backend → …
  • Receiving a paper-writing manuscript
  • SKILL.md covers Non-negotiable boundaries, Local LaTeX environment contract, Workflow and ACT / ASK / NEVER, plus 1 more section
  • Runs Python scripts from its folder; calls python

What it does

Light Typesetting is an agent skill from Light0305/Light-skills. Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11. Use when receiving a paper-writing manuscript, figure delivery, citation delivery.json/references.bib/citekey-audit.json, or a venue/template profile; when selecting pdfLaTeX/XeLaTeX/LuaLaTeX and BibTeX/Biber; when diagnosing LaTeX errors or unresolved references; when checking page limits, double-blind identity, PDF metadata, template, page box, embedded fonts, TODOs, figures, tables, labels and citations; or when producing a…

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 20 other files, including scripts and reference files (for example `references.md`, `references/build_contract.md` and `references/latex_errors.md`).

It sits in Documents & Office, covering LaTeX, Citation management and Scientific writing. It works with LaTeX. The repository describes itself as: An AI workflow skill pack for research, competitions, and innovation projects. The licence is MIT.

When your agent uses it

  • Receiving a paper-writing manuscript
  • Figure delivery
  • Citation delivery.json/references.bib/citekey-audit.json
  • A venue/template profile

Example prompts

  • “/light-typesetting”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Freeze the input contract
  2. Preflight before compilation
  3. Select engine and bibliography backend
  4. Compile and classify convergence
  5. Diagnose from the first root cause
  6. Run the profile-driven desk-reject gate
  7. Emit canonical artifacts
  8. Derive readiness without collapsing evidence
  9. Run stage 11 and hand off

What it can do on your machine

Read from SKILL.md and the folder at commit 6b44f57. 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

    Ships 6 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Light Typesetting loads about 3.3k tokens when it runs, and up to ~5.5k if it reads all its reference files. Until then it costs about 193 tokens; SKILL.md has 1,412 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~193
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.5k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from Light0305/Light-skills at commit 6b44f57, republished under its MIT licence (© Light0305). 1,412 words, ~3,277 tokens.

Download SKILL.mdSave it as .claude/skills/light-typesetting/SKILL.md (or your agent's skills folder). This skill also uses 17 other files; get the full folder from GitHub.
name
light-typesetting
description
Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11. Use when receiving a paper-writing manuscript, figure delivery, citation delivery.json/references.bib/citekey-audit.json, or a venue/template profile; when selecting pdfLaTeX/XeLaTeX/LuaLaTeX and BibTeX/Biber; when diagnosing LaTeX errors or unresolved references; when checking page limits, double-blind identity, PDF metadata, template, page box, embedded fonts, TODOs, figures, tables, labels and citations; or when producing a reproducible compile manifest, PDF, compliance report, failure bundle and venue-matching handoff. Distinguishes PASS, manuscript ERROR, toolchain UNAVAILABLE and convergence UNRESOLVED without redoing citation authenticity or figure scientific QA.

Typesetting · stage 11

Turn approved author artifacts into a reproducible PDF submission bundle. The job is not merely to make LaTeX compile: preserve provenance, select a coherent engine/backend, preflight dependencies, compile to convergence, locate the first root cause, run profile-driven desk-reject checks, and hand exact PDF/page facts to venue-matching.

Read typesetting-resource-map.md before running a real build. Read references/build_contract.md before writing or consuming machine artifacts. Use references/latex_errors.md only after the first source-located error is known. Use a venue template under templates/ only when it matches the current author kit; the bundled copy is a starting point, not current venue truth.

Non-negotiable boundaries

  • Consume citation delivery.json, references.bib and citekey-audit.json. Require delivery.status=DELIVERED, declared deliverable_hashes, empty citation failures and empty claim-review leftovers. Declared citation deliverables must be relative paths inside the citation delivery directory, and the build snapshot must preserve the audit, failure and claim-review sidecars under provenance. Check staged keys and compilation. Do not re-decide DOI existence, metadata conflicts, retractions or claim relevance.
  • Consume figure files, declared dimensions/DPI and source manifest. Require the manifest to be light.figure_delivery.v1 or light.figure_build.v1 and require the embedded file hash to match a declared output hash. For empirical figure deliveries, require confirmed result-analysis evidence binding. Check presence, embedding, float/layout and compilation. Do not redo visual honesty, scientific content or publication-size generation.
  • Consume the approved paper-writing manuscript. Do not invent claims, references, experiments or numbers to close a page budget.
  • Take page, anonymity, template, font and page-box rules only from user input or current authoritative instructions with URL/date provenance. Never embed a universal venue limit.
  • Keep tool/resource failure as UNAVAILABLE. Never call it manuscript ERROR, never call it PASS, and never mark the delivery DELIVERED.
  • Keep stage-11 critical scope to typesetting. Security/network/tool unavailability does not enlarge it. ROUTES has no key 11; repair failures inside stage 11 and never invent a back-edge.

Local LaTeX environment contract

For a real PDF build, detect the local toolchain before claiming success:

  • core: Python stdlib plus a LaTeX distribution such as TeX Live, MiKTeX, MacTeX or TinyTeX;
  • compile driver: prefer latexmk; use tectonic only when its supported backend matches the manuscript;
  • engines: pdflatex, xelatex and lualatex as selected from source/profile triggers;
  • bibliography: bibtex for traditional \bibliography{} and biber for biblatex unless explicitly declared otherwise;
  • PDF checks: pdfinfo and pdffonts when page box, page count or embedded font facts are required.

If the compiler, engine, backend, package or PDF inspector is missing, mark the state UNAVAILABLE, explain the missing component, and ask the user whether to install/configure it or switch toolchains. Never silently install system tools, never call a missing toolchain a manuscript error, and never report a PDF as delivered unless the build actually produced and checked that PDF.

Workflow

1. Freeze the input contract

Copy templates/typesetting_input.json. Record:

  • the paper-writing entrypoint plus every required source file;
  • each figure source, target relative path, dimensions/DPI and delivery/build manifest;
  • citation delivery.json and desired staged BibTeX filename; the delivery must be regenerated after citation edits so hashes match the referenced files;
  • light.typesetting_venue_profile.v1, including source kind, URL if any, check date and rules.

If a venue rule is unknown, keep it null, 0 or absent. Do not infer it from another venue or last year's template.

2. Preflight before compilation
powershell
python scripts/build_submission.py --spec typesetting-input.json --preflight-only

Require a provenance-preserving source/ snapshot. Check missing inputs, \input/\include, graphics, labels/refs, citation-delivery schema/status, deliverable hashes, delivered citekey audit, empty citation failure/review handoffs, live staged citekeys, figure manifest output hashes, empirical figure evidence binding, document class, required packages and local package availability. Use a new/empty output directory per iteration; the builder refuses stale run directories.

Classify:

EvidenceState
missing manuscript/figure/BibTeX/key/label, stale upstream hash, open citation review, unconfirmed empirical-figure evidence or backend conflictERROR
required engine/backend/package/tool absent or cannot executeUNAVAILABLE
no blockerPASS
3. Select engine and bibliography backend

Detect XeLaTeX for fontspec, xeCJK, ctex, unicode-math or polyglossia; LuaLaTeX for Lua triggers; otherwise pdfLaTeX. Detect traditional \bibliography as BibTeX and biblatex as Biber unless its backend= option says otherwise.

If the profile engine conflicts with a hard XeLaTeX/LuaLaTeX source trigger, or its backend differs from the source, stop with a root-cause ERROR; do not mix BibTeX and Biber. A profile may deliberately select XeLaTeX for otherwise pdfLaTeX-compatible source. Record the absolute executable path, version probe, working directory, command array and shell rendering.

4. Compile and classify convergence
powershell
python scripts/build_submission.py --spec typesetting-input.json

Prefer local latexmk; use Tectonic only when its supported backend matches. Compile from the snapshot's manuscript directory so relative inputs resolve. Save latexmk rule/run records, log/PDF SHA-256 and page count.

Use exactly four compile states:

  • PASS: return code zero, PDF exists, no remaining undefined cite/ref or rerun signal.
  • ERROR: manuscript/backend/input caused a nonzero build or no PDF.
  • UNAVAILABLE: required local tool/resource could not launch/finish.
  • UNRESOLVED: PDF exists but citation/reference convergence remains.

ERROR and UNRESOLVED exit 1. UNAVAILABLE exits 0 for the command-gate boundary but remains undelivered.

5. Diagnose from the first root cause

Read compile-report.json, then the full log. Report the first file.tex:line, compiler message and plain-language cause before secondary warnings. Fix the earliest error first; recompile after one minimal repair. Never silently rewrite prose, remove data or add fabricated bibliography.

When a fix loop repeats the same signature, stop and report UNRESOLVED instead of making speculative edits.

Show full SKILL.md (556 more words)Show less
6. Run the profile-driven desk-reject gate
powershell
python scripts/desk_reject_gate.py `
  --tex typesetting-build/source/paper.tex `
  --pdf typesetting-build/compile/paper.pdf `
  --bib typesetting-build/source/references.bib `
  --log typesetting-build/compile/paper.log `
  --profile venue-profile.json `
  --report desk-reject-findings.json

Objective profile breaches may be critical: over page limit, unanonymous author/PDF Author metadata, wrong document class, missing required package, wrong page size, or unembedded font. TODOs, acknowledgements, self-reference, links and box warnings stay warnings unless the current authoritative profile defines an objective hard rule.

Static checks cannot prove semantic anonymity, interpret ambiguous venue language or judge final visual quality. Inspect the rendered PDF and current official analyzer/instructions before submission.

7. Emit canonical artifacts

Require:

  • build-manifest.json;
  • compile-report.json and compile log;
  • compliance-report.json and desk-reject findings;
  • PDF when produced;
  • failure.json for failed/unavailable runs;
  • venue-handoff.json;
  • delivery.json.

Only compile=PASS, compliance=PASS and zero compliance critical may become DELIVERED. Preserve failed reports; they prove the fail→fix transition.

8. Derive readiness without collapsing evidence

Build a local readiness packet and run:

powershell
python scripts/submission_readiness.py `
  --input templates/submission-readiness.example.json --as-of YYYY-MM-DD `
  --out submission-readiness-report.json

The public template is intentionally UNKNOWN and must exit 1. The state chain is INVENTORIED → SOURCE_BUILDABLE → TECHNICALLY_CHECKED → VISUALLY_CHECKED → METADATA_MATCHED → VENUE_READY → USER_APPROVED. Compile exit 0 cannot skip unresolved references, compile page_count, same-PDF binding, per-page render/review, metadata anonymity, current official profile or exact article-type binding. visual.source_pdf_sha256, metadata.source_pdf_sha256, compliance.source_pdf_sha256 and any user_approval.pdf_sha256 must equal compile.pdf_sha256; visual.page_count must equal compile.page_count; each visual page row needs render_sha256, render_tool, review_status=PASS, reviewer/reviewer_id and non-future reviewed_at. The compliance row must also name the same venue and article_type as the profile. Artifact Available/Functional/Reusable/Reproduced/Replicated remain separate; the script records evidence and never awards an ACM or venue badge.

9. Run stage 11 and hand off

Run the compile command gate and desk_reject findings checkpoint:

powershell
python ../light-orchestrator/scripts/run_checkpoint.py `
  --file .light/passport.yaml --stage 11 `
  --gate "compile=python scripts/compile_driver.py --compile paper.tex --outdir build --json-out compile-report.json --quiet" `
  --findings desk-reject-findings.json --ts <ISO8601> --write

On critical fail, repair stage 11 and rerun to delivered. Hand venue-matching the venue-handoff.json PDF path/hash, page count, page size, profile source and compliance report. Do not claim ROUTES[11] or create a back-edge. --quiet keeps the Windows command gate locale-neutral; the full diagnostic record remains in compile-report.json.

ACT / ASK / NEVER

ACT:

  • Snapshot declared inputs before modification.
  • Run preflight, compile, rendered-PDF review, desk-reject gate and checkpoint.
  • Preserve exact commands, hashes, statuses and failure artifacts.

ASK:

  • Ask when a venue rule/source is missing or ambiguous.
  • Ask before scientific-content cuts, changing bibliography systems, or replacing the user's official template.
  • Ask for human confirmation of semantic anonymity and borderline layout.

NEVER:

  • Never claim a compile, convergence, page count or metadata check that did not run.
  • Never treat missing tools as a manuscript error or a successful delivery.
  • Never redo citation authenticity, figure scientific QA or paper-writing.
  • Never depend on paid Overleaf, private keys, browser plugins or npm-heavy tooling for the core path.

Delivery self-check

  • Input provenance and SHA-256 rows cover manuscript, figures, figure manifests, citation delivery/BibTeX/audit/failure/review artifacts and profile.
  • Citation delivery status is DELIVERED; deliverable hashes match staged files; citation failures and claim-review leftovers are empty.
  • Figure source manifests declare the embedded output hash; empirical figures carry confirmed result-analysis evidence binding.
  • Engine/backend selection agrees with source and profile.
  • Compile status is one of the four canonical states; PASS has a hashed PDF.
  • Root cause has file/line when the compiler exposes it; warnings are separate.
  • Citekeys, figures, labels and cross-references converge.
  • Desk-reject criticals are zero or delivery is not marked delivered.
  • Every visual/metadata/compliance/user-approval row is bound to the compiled PDF hash; every PDF page has a render hash, render tool, reviewer/date and review PASS row; profile is current and bound to the exact article type.
  • Author-team repeatability was not relabelled independent reproduction/replication.
  • Venue-matching receives real PDF/page/compliance facts.
  • Stage 11 uses only compile and desk_reject; no route/back-edge was added.

© Light0305, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 17 other files (scripts, references) in skills/light-typesetting of Light0305/Light-skills.

  • SKILL.md
  • references.md
  • references/build_contract.md
  • references/latex_errors.md
  • scripts/build_submission.py
  • scripts/compile_driver.py
  • scripts/desk_reject_gate.py
  • scripts/precheck_log.py
  • scripts/submission_check.py
  • scripts/submission_readiness.py
  • templates/acm_sigconf.tex
  • templates/ctex_chinese.tex
  • templates/elsevier_elsarticle.tex
  • templates/ieee_bare_conf.tex
  • templates/springer_llncs.tex
  • templates/submission-readiness.example.json
  • templates/typesetting_input.json
  • typesetting-resource-map.md

Open the folder on GitHubat commit 6b44f57

Compare with similar skills

Light Typesetting 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.

Light Typesetting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Light Typesetting this skillLight0305/Light-skills640—~3.3kAutomated safety check: PassMIT
Latex Setupfcakyon/phd-skills414—~1.1kAutomated safety check: NotesMIT
Academic Paperbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~7.3kAutomated safety check: PassCustom licence
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
Academic Paper Helpercnfjlhj/ai-collab-playbook452—~1.8kAutomated safety check: PassNone
Scholar Writingcatlog22/maestro-flow563—~3.3kAutomated safety check: NotesNone

Similar skills

  • Latex Setup

    fcakyon/phd-skills

    A skill your agent uses when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation.

    414 GitHub stars~1.1k tokensUpdated 21 days ago
    Documents & OfficeAuto-check: notes
  • Academic Paper

    brycewang-stanford/Auto-Empirical-Research-Skills

    Academic paper writing skill with 12-agent pipeline. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.5k GitHub stars~7.3k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Academic Paper Helper

    cnfjlhj/ai-collab-playbook

    Use only when the user explicitly asks for help drafting or revising an AI/ML research paper in LaTeX, including structure, BibTeX, formatting, or academic-writing checks.

    452 GitHub stars~1.8k tokensUpdated 23 days ago
    Research & ScienceAuto-check passed
  • Scholar Writing

    catlog22/maestro-flow

    End-to-end academic paper writing workflow. An agent skill from catlog22/maestro-flow.

    563 GitHub stars~3.3k tokensUpdated today
    Research & ScienceAuto-check: notes
  • Research Depth Control

    BingHanOfUESTC/open_agent_team

    A skill your agent uses when autoresearchteam needs deeper literature coverage, more citations in paper writing, stronger related-work synthesis, or a gate that prevents shallow research from…

    106 GitHub stars~989 tokensUpdated 3 mo ago
    Research & ScienceAuto-check passed

More from Light0305/Light-skills

All 23 skills in this repo
  • Citation Verification

    Light0305/Light-skills

    Verifies that every reference in a manuscript is real, correctly identified and actually supports its claim, and produces a citation registry for typesetting.

    640 GitHub stars~3.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Light Research Orchestrator

    Light0305/Light-skills

    Coordinates and recovers multi-stage Light research projects from a single passport file, with checkpoints, stale-work tracking and rerouting only when you approve.

    640 GitHub stars~3.8k tokensUpdated 3 mo ago
    Auto-check passed
  • Patent Disclosure Handoff

    Light0305/Light-skills

    Builds an evidence-backed invention disclosure packet from a project or research result for attorney or patent-agent review, without giving legal advice.

    640 GitHub stars~2k tokensUpdated 3 mo ago
    Auto-check passed
  • Light Project Structure

    Light0305/Light-skills

    Audits, scaffolds and safely migrates research project folder structures, keeping existing repositories read-only until you approve exact moves from a plan.

    640 GitHub stars~3k tokensUpdated 3 mo ago
    Auto-check: notes
  • Prepares draft materials for a China software copyright registration from a real project: application worksheet, source deposit plan, operation manual and consistency checks.

    640 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed
  • Light System Design

    Light0305/Light-skills

    Evidence-based workflow for designing or modernizing a software system: current-state inventory, options, API and schema contracts, migration plans, ADRs and verification.

    640 GitHub stars~3.6k tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Light Typesetting

What does Light Typesetting do?

Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11. Light Typesetting is an agent skill from Light0305/Light-skills. Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11.

When should I use Light Typesetting?

Light Typesetting fits situations like: receiving a paper-writing manuscript; figure delivery; citation delivery.json/references.bib/citekey-audit.json; A venue/template profile.

How do I install Light Typesetting in Claude Code?

Run `npx skills add Light0305/Light-skills --skill light-typesetting -a claude-code`. Or copy the skill folder (skills/light-typesetting in Light0305/Light-skills) into .claude/skills/light-typesetting in your project. Claude Code loads it when a task matches its description.

How do I install Light Typesetting in Codex?

Run `npx skills add Light0305/Light-skills --skill light-typesetting -a codex`. Or copy the skill folder (skills/light-typesetting in Light0305/Light-skills) into .agents/skills/light-typesetting in your project. Codex loads it when a task matches its description.

Can I use Light Typesetting 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 Light0305/Light-skills --skill light-typesetting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/light-typesetting, .gemini/skills/light-typesetting, .github/skills/light-typesetting and .opencode/skills/light-typesetting in your project.

What does Light Typesetting need to run?

Going by SKILL.md and its folder, Light Typesetting needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Light Typesetting 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 Light Typesetting 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Light Typesetting use?

Light Typesetting 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 Light Typesetting use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Light Typesetting?

Skills that share tags, products or a category with Light Typesetting: Latex Setup (fcakyon/phd-skills, 414 stars), Academic Paper (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars) and Academic Paper Helper (cnfjlhj/ai-collab-playbook, 452 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Light Typesetting?

Light0305 (a GitHub user) maintains it in Light0305/Light-skills, which has 640 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on July 6, 2026.

Source: Light0305/Light-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.