New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Learn From Math Agent Trajectories

by morluto in morluto/jacobian

Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.

MITAuto-check passedResearch & Science

Install Learn From Math Agent Trajectories

skills CLI
$ npx skills add morluto/jacobian --skill learn-from-math-agent-trajectories -a claude-code

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

GitHub CLI
$ gh skill install morluto/jacobian learn-from-math-agent-trajectories --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/.agents/skills/learn-from-math-agent-trajectories .claude/skills/learn-from-math-agent-trajectories && 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
learn-from-math-agent-trajectories
GitHub stars
211
Token cost
~848 tokens
SKILL.md length
394 words
Files
3 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.

  • Tasks that involve Math and symbolic computation
  • SKILL.md covers Establish the evidence, Attribute the lesson and Report actionable learning
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Learn From Math Agent Trajectories is an agent skill from morluto/jacobian. Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/mathematical-evidence.md`).

It sits in Research & Science, covering Math and symbolic computation. 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

Example prompts

  • “/learn-from-math-agent-trajectories”

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

Learn From Math Agent Trajectories loads about 848 tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 35 tokens; SKILL.md has 394 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~848
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

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). 394 words, ~848 tokens.

Download SKILL.mdSave it as .claude/skills/learn-from-math-agent-trajectories/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
learn-from-math-agent-trajectories
description
Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.

Learn from Math Agent Trajectories

Extract reusable Jacobian lessons from a completed or paused investigation; do not resume solving the problem. A correct answer can expose workflow defects, and an unsuccessful search can reveal useful mathematical vocabulary.

Establish the evidence

Record the intended and actual outcome, stopping condition, transcript coverage, and available revision/catalog context. Use observable sources, calls, code, artifacts, corrections, and final claims. Narration alone is not execution evidence; current-main capabilities were not necessarily available in the trace.

Reconstruct decisions that changed correctness, cost, progress, or confidence. For a finding that depends on mathematical claims, numerical or symbolic work, solver semantics, or bespoke code, consult mathematical evidence. Preserve decisive claims and later corrections, with their hypotheses and evidence scope.

Attribute the lesson

Distinguish working capabilities, environment limitations, discovery/selection, execution friction, representation/interoperability, contract/scale defects, missing operations, handoff failures, and caller reasoning. Compare needed postconditions with the session-visible catalog when available; check current source before proposing new work. Handwritten code and tool non-use are leads, not automatic evidence of missing operations.

Separate a reusable operation gap from public-catalog admission. An existing postcondition with a narrow envelope is a scale/backend question. A convenience or theorem-specific assembly does not become a public operation solely because it occurred in the trace. Use the admission contract when proposing publication.

Route only when the requested follow-up needs a deeper workflow:

  • evaluate-mcp-tool-adoption for controlled availability, discovery, or selection;
  • audit-mcp-tool-friction for problems after selecting a tool;
  • audit-public-operation-contracts for a particular mathematical contract; or
  • recent-conjecture-evaluations for a new held-out reliability probe.

An unresolved conjecture is generally unsuitable as an evaluation oracle. Extract frozen, independently checkable finite obligations when proposing an evaluation, and preserve contamination boundaries.

Show full SKILL.md (118 more words)Show less

Report actionable learning

For each material finding, give the source evidence, implication, proportionate repair, and uncertainty. Include a compact claim/correction ledger when it helps explain a changed conclusion; include ownership and success criteria when proposing implementation. Search narrowly for an existing issue before suggesting a new one. External mutations require user authorization.

Prefer discovery, contract, representation, or scale repairs when they explain the failure. Update skills only for reusable decision guidance and product docs only for durable public behavior. An isolated agent slip may need no repository change. Stop when the requested trace is accounted for and the supported lessons and remaining proof gaps are clear; report coverage rather than implying that the underlying mathematical problem is solved.

© 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

SKILL.md and 2 other files (references) in .agents/skills/learn-from-math-agent-trajectories of morluto/jacobian.

  • SKILL.md
  • agents/openai.yaml
  • references/mathematical-evidence.md

Open the folder on GitHubat commit 9dc2aaf

Compare with similar skills

Learn From Math Agent Trajectories 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.

Learn From Math Agent Trajectories compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Learn From Math Agent Trajectories this skillmorluto/jacobian211—~848Automated safety check: PassMIT
Research RefinezjYao36/Auto-Research-Refine1286 repos~6.9kAutomated safety check: NotesNone
Read GitHubAgentTeam-TaichuAI/ScienceClaw6712 repos~638Automated safety check: PassNone
Proof Run Orchestratorwanshuiyin/Auto-claude-code-research-in-sleep17k1 repos~4.7kAutomated safety check: PassMIT
FirstdataMLT-OSS/FirstData183—~3.1kAutomated safety check: PassMIT
Fin Generate Ideacsmar432/finai-research109—~2.5kAutomated safety check: PassMIT

Similar skills

  • Research Refine

    zjYao36/Auto-Research-Refine

    Turns a vague research direction into a focused, problem-anchored method plan through up to five review rounds with a second model.

    128 GitHub starsUsed in 6 repos~6.9k tokens
    Research & ScienceAuto-check: notes

  • 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

  • Proof Run Orchestrator

    wanshuiyin/Auto-claude-code-research-in-sleep

    Runs a mathematical proof project as a stateful pipeline of run directories: a local attempt first, then a manual GPT Pro handoff package, with an optional DeepSeek audit.

    17k GitHub starsUsed in 1 repo~4.7k 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.).

    183 GitHub stars~3.1k tokensUpdated 6 days ago
    Research & ScienceAuto-check passed

  • Fin Generate Idea

    csmar432/finai-research

    针对经济金融研究方向的创意生成与评估。生成8-12个可发表的研究idea，过滤后在数据可行的情况下进行小规模实证验证，输出排序后的研究想法报告。

    109 GitHub stars~2.5k tokensUpdated 3 days ago
    Research & ScienceAuto-check passed

  • Math Proof Solo

    anthropics/claude-plugins-official

    Official

    Solves one hard mathematics problem in a single session without subagents, keeping settled steps in a notes file and ending with a self-contained proof.md.

    38k GitHub stars~1.5k tokensUpdated today
    Research & ScienceAuto-check passed

More from morluto/jacobian

All 11 skills in this repo

  • Recent Conjecture Evaluations

    morluto/jacobian

    Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.

    211 GitHub stars~816 tokensUpdated 4 days ago
    Auto-check passed

  • Harbor Benchmarks

    morluto/jacobian

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

    211 GitHub stars~690 tokensUpdated 4 days ago
    Auto-check passed

  • Audit Public Operation Contracts

    morluto/jacobian

    Design or audit a Jacobian operation’s mathematical contract, boundedness, exact results, and composition.

    211 GitHub stars~2k tokensUpdated 4 days ago
    Auto-check passed

  • Decompose Mathematical Solution Corpora

    morluto/jacobian

    Extract reusable Jacobian capabilities from a mathematical solution corpus, rather than one agent trajectory.

    211 GitHub stars~1.9k tokensUpdated 4 days ago
    Auto-check passed

  • Evaluate MCP Tool Adoption

    morluto/jacobian

    Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.

    211 GitHub stars~1k tokensUpdated 4 days ago
    Auto-check passed

  • Verifier Evaluations

    morluto/jacobian

    Design, audit, or repair mathematical benchmark verifiers, submission contracts, and scoring.

    211 GitHub stars~661 tokensUpdated 4 days ago
    Auto-check passed

Works with

Categories

Questions about Learn From Math Agent Trajectories

What does Learn From Math Agent Trajectories do?

Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving. Learn From Math Agent Trajectories is an agent skill from morluto/jacobian. Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.

When should I use Learn From Math Agent Trajectories?

Learn From Math Agent Trajectories fits situations like: tasks that involve Math and symbolic computation.

How do I install Learn From Math Agent Trajectories in Claude Code?

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

How do I install Learn From Math Agent Trajectories in Codex?

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

Can I use Learn From Math Agent Trajectories 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 learn-from-math-agent-trajectories -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learn-from-math-agent-trajectories, .gemini/skills/learn-from-math-agent-trajectories, .github/skills/learn-from-math-agent-trajectories and .opencode/skills/learn-from-math-agent-trajectories in your project.

What does Learn From Math Agent Trajectories need to run?

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

Does Learn From Math Agent Trajectories 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 Learn From Math Agent Trajectories 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 Learn From Math Agent Trajectories use?

Learn From Math Agent Trajectories 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 Learn From Math Agent Trajectories use?

About 848 tokens (SKILL.md is roughly 3.4k 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 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Learn From Math Agent Trajectories?

Skills that share tags, products or a category with Learn From Math Agent Trajectories: Research Refine (zjYao36/Auto-Research-Refine, 128 stars), Read GitHub (AgentTeam-TaichuAI/ScienceClaw, 671 stars), Proof Run Orchestrator (wanshuiyin/Auto-claude-code-research-in-sleep, 17k stars) and Firstdata (MLT-OSS/FirstData, 183 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Learn From Math Agent Trajectories?

morluto (a GitHub user) maintains it in morluto/jacobian, which has 211 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.