Agent skill

Jacobian Math

by morluto in morluto/jacobian

Use Jacobian's MCP operations for nontrivial mathematical computation, finite search, structural analysis, formal checking, probability, or optimization.

MITAuto-check passedResearch & Science

Install Jacobian Math

skills CLI
$ npx skills add morluto/jacobian --skill jacobian-math -a claude-code

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

GitHub CLI
$ gh skill install morluto/jacobian jacobian-math --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/morluto/jacobian.git skills-src && mkdir -p .claude/skills && cp -r skills-src/npm/skill/jacobian-math .claude/skills/jacobian-math && 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
jacobian-math
GitHub stars
220
Token cost
~286 tokens
SKILL.md length
124 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Use Jacobian's MCP operations for nontrivial mathematical computation, finite search, structural analysis, formal checking, probability, or optimization.

  • Tasks that involve Math and symbolic computation
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve MCP servers

What it does

Jacobian Math is an agent skill from morluto/jacobian. Use Jacobian's MCP operations for nontrivial mathematical computation, finite search, structural analysis, formal checking, probability, or optimization.

Its SKILL.md is about 290 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 Research & Science, covering Math and symbolic computation and MCP servers. It works with Model Context Protocol. The repository describes itself as: Composable mathematics tools for agents. The licence is MIT.

When your agent uses it

  • Tasks that involve Math and symbolic computation
  • Tasks that involve MCP servers

Example prompts

  • “/jacobian-math”

What it can do on your machine

Read from SKILL.md and the folder at commit 9dc2aaf. 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.

    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

Jacobian Math loads about 286 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 124 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~286

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 morluto/jacobian at commit 9dc2aaf, republished under its MIT licence (© morluto). 124 words, ~286 tokens.

Download SKILL.mdSave it as .claude/skills/jacobian-math/SKILL.md (or your agent's skills folder).
name
jacobian-math
description
Use Jacobian's MCP operations for nontrivial mathematical computation, finite search, structural analysis, formal checking, probability, or optimization.
<!-- Managed by Jacobian setup. -->

Jacobian mathematics

Use Jacobian when a mathematical task benefits from exact computation or a bounded check. Search with math.find, then execute a selected operation with math.run.

Keep the mathematical reasoning in the agent. Treat operations as atomic instruments: compose their typed results yourself rather than asking discovery to prescribe a proof strategy or workflow.

Before running an operation:

  • Inspect its exact request schema and mathematical scope with math.find.
  • Supply canonical mathematical values without backend-specific expressions or ambient contexts.
  • Respect the operation's declared bounds and distinguish exact results from incomplete, unknown, unavailable, or transport outcomes.

Use returned values and certificates only for the conclusion they establish. Absence of a witness, a timeout, or an incomplete search is not a proof of a global mathematical claim.

© morluto, 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 npm/skill/jacobian-math of morluto/jacobian.

Open the folder on GitHubat commit 9dc2aaf

Compare with similar skills

Jacobian Math 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.

Jacobian Math compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jacobian Math this skillmorluto/jacobian220—~286Automated safety check: PassMIT
Read GitHubAgentTeam-TaichuAI/ScienceClaw6712 repos~638Automated safety check: PassNone
FirstdataMLT-OSS/FirstData184—~3.1kAutomated safety check: PassMIT
Report Issue Frameworkcyanheads/pubmed-mcp-server158—~3.2kAutomated safety check: PassApache-2.0
Serply Search MCPsickn33/agentic-awesome-skills47k1 repos~1.5kAutomated safety check: PassMIT
Bgpt MCPClawBio/ClawBio1.2k1 repos~3.2kAutomated safety check: PassMIT

Similar skills

  • Read GitHub

    AgentTeam-TaichuAI/ScienceClaw

    Read and search GitHub repository documentation via gitmcp.io MCP service.

    671 GitHub starsUsed in 2 repos~638 tokens
    Research & ScienceAuto-check passed
  • Firstdata

    MLT-OSS/FirstData

    Find official portals, APIs, and download paths for authoritative primary data sources (governments, international organizations, research institutions, etc.).

    184 GitHub stars~3.1k tokensUpdated 7 days ago
    Research & ScienceAuto-check passed
  • Report Issue Framework

    cyanheads/pubmed-mcp-server

    File a bug or feature request against @cyanheads/mcp-ts-core when you hit a framework issue.

    158 GitHub stars~3.2k tokensUpdated today
    Research & ScienceAuto-check passed
  • Serply Search MCP

    sickn33/agentic-awesome-skills

    Search Google, Bing, Google News and Google Scholar, and read public pages, with the Serply MCP server.

    47k GitHub starsUsed in 1 repo~1.5k tokens
    Research & ScienceAuto-check passed
  • Bgpt MCP

    ClawBio/ClawBio

    Search scientific papers via the BGPT MCP server and retrieve structured experimental data — methods, results, conclusions, quality scores, and 25+ metadata fields per paper.

    1.2k GitHub starsUsed in 1 repo~3.2k tokens
    Research & ScienceAuto-check passed
  • Setup Medsci

    Aperivue/medsci-skills

    A skill your agent uses when a skill fails for a missing tool or the environment needs checking.

    333 GitHub stars~960 tokensUpdated 4 days ago
    Research & ScienceAuto-check passed

More from morluto/jacobian

All 11 skills in this repo
  • Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.

    220 GitHub stars~816 tokensUpdated 5 days ago
    Auto-check passed
  • Harbor Benchmarks

    morluto/jacobian

    Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.

    220 GitHub stars~690 tokensUpdated 5 days ago
    Auto-check passed
  • Design or audit a Jacobian operation’s mathematical contract, boundedness, exact results, and composition.

    220 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed
  • Extract reusable Jacobian capabilities from a mathematical solution corpus, rather than one agent trajectory.

    220 GitHub stars~1.9k tokensUpdated 5 days ago
    Auto-check passed
  • Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.

    220 GitHub stars~1k tokensUpdated 5 days ago
    Auto-check passed
  • Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.

    220 GitHub stars~848 tokensUpdated 5 days ago
    Auto-check passed

Questions about Jacobian Math

What does Jacobian Math do?

Use Jacobian's MCP operations for nontrivial mathematical computation, finite search, structural analysis, formal checking, probability, or optimization. Jacobian Math is an agent skill from morluto/jacobian. Use Jacobian's MCP operations for nontrivial mathematical computation, finite search, structural analysis, formal checking, probability, or optimization.

When should I use Jacobian Math?

Jacobian Math fits situations like: tasks that involve Math and symbolic computation; tasks that involve MCP servers.

How do I install Jacobian Math in Claude Code?

Run `npx skills add morluto/jacobian --skill jacobian-math -a claude-code`. Or copy the skill folder (npm/skill/jacobian-math in morluto/jacobian) into .claude/skills/jacobian-math in your project. Claude Code loads it when a task matches its description.

How do I install Jacobian Math in Codex?

Run `npx skills add morluto/jacobian --skill jacobian-math -a codex`. Or copy the skill folder (npm/skill/jacobian-math in morluto/jacobian) into .agents/skills/jacobian-math in your project. Codex loads it when a task matches its description.

Can I use Jacobian Math 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 morluto/jacobian --skill jacobian-math -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jacobian-math, .gemini/skills/jacobian-math, .github/skills/jacobian-math and .opencode/skills/jacobian-math in your project.

What does Jacobian Math need to run?

SKILL.md names no scripts, command-line tools or credentials: Jacobian Math is instructions for the agent only.

Does Jacobian Math 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 Jacobian Math 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 Jacobian Math use?

Jacobian Math 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 Jacobian Math use?

About 286 tokens (SKILL.md is roughly 1.1k 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 Jacobian Math?

Skills that share tags, products or a category with Jacobian Math: Read GitHub (AgentTeam-TaichuAI/ScienceClaw, 671 stars), Firstdata (MLT-OSS/FirstData, 184 stars), Report Issue Framework (cyanheads/pubmed-mcp-server, 158 stars) and Serply Search MCP (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jacobian Math?

morluto (a GitHub user) maintains it in morluto/jacobian, which has 220 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 5, 2026.

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