Setup Medsci
Aperivue/medsci-skills
A skill your agent uses when a skill fails for a missing tool or the environment needs checking.
Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.
Install Harbor Benchmarks
$ npx skills add morluto/jacobian --skill harbor-benchmarks -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install morluto/jacobian harbor-benchmarks --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/morluto/jacobian.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/harbor-benchmarks .claude/skills/harbor-benchmarks && 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 "harbor-benchmarks" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/harbor-benchmarks into .claude/skills/harbor-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harbor-benchmarks", 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/morluto/jacobian/tree/main/.agents/skills/harbor-benchmarksType 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 morluto/jacobian --skill harbor-benchmarks -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install morluto/jacobian harbor-benchmarks --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/harbor-benchmarks .agents/skills/harbor-benchmarks && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harbor-benchmarks" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/harbor-benchmarks into .agents/skills/harbor-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harbor-benchmarks", 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 morluto/jacobian --skill harbor-benchmarks -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install morluto/jacobian harbor-benchmarks --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/harbor-benchmarks .cursor/skills/harbor-benchmarks && 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 "harbor-benchmarks" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/harbor-benchmarks into .cursor/skills/harbor-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harbor-benchmarks", 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/morluto/jacobian.git --path .agents/skills/harbor-benchmarks--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 morluto/jacobian --skill harbor-benchmarks -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install morluto/jacobian harbor-benchmarks --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/harbor-benchmarks .gemini/skills/harbor-benchmarks && 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 "harbor-benchmarks" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/harbor-benchmarks into .gemini/skills/harbor-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harbor-benchmarks", 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 morluto/jacobian harbor-benchmarksInstalls 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 morluto/jacobian --skill harbor-benchmarks -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/harbor-benchmarks .github/skills/harbor-benchmarks && 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 "harbor-benchmarks" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/harbor-benchmarks into .github/skills/harbor-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harbor-benchmarks", 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 morluto/jacobian --skill harbor-benchmarks -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install morluto/jacobian harbor-benchmarks --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/harbor-benchmarks .opencode/skills/harbor-benchmarks && 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 "harbor-benchmarks" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/harbor-benchmarks into .opencode/skills/harbor-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harbor-benchmarks", 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
harbor-benchmarks- GitHub stars
- 205
- Token cost
- ~690 tokens
- SKILL.md length
- 288 words
- Files
- 3 (incl. references)
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.
- Tasks that involve Math and symbolic computation
- SKILL.md covers Choose the artifact and Package and validate
- Calls make
What it does
Harbor Benchmarks is an agent skill from morluto/jacobian. Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.
Its SKILL.md is about 690 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/packaging.md`).
It sits in Research & Science, covering Math and symbolic computation. It works with Model Context Protocol and Python. 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
- “/harbor-benchmarks”
Requirements
- Python 3
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
Shell commands in SKILL.md call:
make
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
Harbor Benchmarks loads about 690 tokens when it runs, and up to ~1k if it reads all its reference files. Until then it costs about 26 tokens; SKILL.md has 288 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 morluto/jacobian at commit 9dc2aaf, republished under its MIT licence (© morluto). 288 words, ~690 tokens.
Download SKILL.mdSave it as
.claude/skills/harbor-benchmarks/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- harbor-benchmarks
- description
- Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.
Harbor Benchmarks
Build a bounded mathematical experiment with a hidden, replayable verifier. Jacobian availability is an experimental condition, not a prerequisite for task admission. Task correctness depends on the submitted mathematics, not the agent's tool choices or transcript.
Choose the artifact
- Put meaningful agent-facing mathematical tasks with replayable outcomes in Harbor, including capability gaps and tool-free baselines.
- Put provider/environment feasibility spikes under
tests/fixtures/providers/. - Keep public known-answer regressions and human-reviewed proof corpora separate from held-out comparative scoring.
For submission design, mathematical predicates, scoring, or verifier repairs,
use verifier-evaluations. Ordinary packaging and execution do not require that
skill. A task's instruction and schema must expose its complete protocol while
keeping solutions, Oracle fixtures, verifier code, and host caches hidden.
Package and validate
Each task is a direct dataset child with one member record:
benchmarks/datasets/<dataset>/<task-id>/
benchmarks/datasets/<dataset>/members/<task-id>.tomlUse frozen offline inputs, pinned images and dependencies, and an explicit
execution profile. Verifier Dockerfiles build from tests/; avoid parent
COPY, host paths, floating tags, and symlinks. For the affected contract, use
benchmark contracts.
For local commands and planner selection, use the Harbor section of
CONTRIBUTING.md.
make harbor-plan BASE=origin/main
make harbor-prepare-task DATASET=<dataset> TASKS="<task-id>"
make harbor-validate-task DATASET=<dataset> TASKS="<task-id>"Preparation formats selected task Python and refreshes contracts/checksums; validation runs the selected static, host, and Oracle checks without a model agent. Run the selected verifier's behavioral attacks when its contract changes. Report any deferred affected Oracle coverage.
For task-local support migrations, older contracts, checksum updates, or an intentional snapshot, read packaging details. Do not create a snapshot merely because a task contract changed.
Complete the requested task preparation and validation, repairing failures caused by the change within the authorized scope. Report the command, task digest, selected scope, Oracle result, and remaining evidence gaps. Distinguish local validation from a causal model comparison; model calls and external publication require the applicable user authorization.
© 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/harbor-benchmarks of morluto/jacobian.
- SKILL.md
- agents/openai.yaml
- references/packaging.md
Open the folder on GitHubat commit 9dc2aaf
Compare with similar skills
Harbor Benchmarks 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 |
|---|---|---|---|---|---|---|
| Harbor Benchmarks this skillmorluto/jacobian | 205 | — | ~690 | Automated safety check: Pass | MIT | |
| Setup MedsciAperivue/medsci-skills | 329 | — | ~960 | Automated safety check: Pass | MIT | |
| Deep Research MCP Guidepminervini/deep-research-mcp | 112 | — | ~5.8k | Automated safety check: Pass | MIT | |
| Aer Statspaibrycewang-stanford/Auto-Empirical-Research-Skills | 4.5k | — | ~3k | Automated safety check: Pass | Custom licence | |
| SympyzLanqing/codex-claude-academic-skills | 4.6k | 16 repos | ~3.4k | Automated safety check: Pass | MIT | |
| Edu Analytic Geometrywy51ai/edulab | 1.4k | 1 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Deep Research MCP Guide
pminervini/deep-research-mcp
Explains how to run, integrate and debug the deep-research-mcp project through its CLI, Python API or MCP server, with OpenAI, Gemini and DR-Tulu backends.
Aer Statspai
brycewang-stanford/Auto-Empirical-Research-Skills
A skill your agent uses when aer-identification has fixed the design, after methodology choice and before aer-robustness or aer-tables-figures, to run an AER-track analysis with StatsPAI — the…
Sympy
zLanqing/codex-claude-academic-skills
A skill your agent uses when working with symbolic mathematics in Python.
Edu Analytic Geometry
wy51ai/edulab
把一道解析几何题解成一个自包含的交互教学网页：左栏题面 + 动态控制台（一个 可变参数滑块驱动实时重算的几何量 + 理论范围/定值指示），中栏 KaTeX 分步解析，右栏 2D Canvas 动态几何画板（椭圆/双曲线/抛物线/圆 + 动直线/动点 + 向量 + 标注 + 画笔涂鸦）。
NSFC Literature Review Writer
HuiyuLi-2000/Chinese-Grant-Writer-Skills
Writes the research-status literature review and critique section of an NSFC grant proposal, backed by a bundled multi-source literature search.
More from morluto/jacobian
All 11 skills in this repoRecent Conjecture Evaluations
morluto/jacobian
Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.
Audit Public Operation Contracts
morluto/jacobian
Design or audit a Jacobian operation’s mathematical contract, boundedness, exact results, and composition.
Decompose Mathematical Solution Corpora
morluto/jacobian
Extract reusable Jacobian capabilities from a mathematical solution corpus, rather than one agent trajectory.
Evaluate MCP Tool Adoption
morluto/jacobian
Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.
Learn From Math Agent Trajectories
morluto/jacobian
Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.
Verifier Evaluations
morluto/jacobian
Design, audit, or repair mathematical benchmark verifiers, submission contracts, and scoring.
Related
Works with
Categories
Questions about Harbor Benchmarks
What does Harbor Benchmarks do?
Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets. Harbor Benchmarks is an agent skill from morluto/jacobian. Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.
When should I use Harbor Benchmarks?
Harbor Benchmarks fits situations like: tasks that involve Math and symbolic computation.
How do I install Harbor Benchmarks in Claude Code?
Run `npx skills add morluto/jacobian --skill harbor-benchmarks -a claude-code`. Or copy the skill folder (.agents/skills/harbor-benchmarks in morluto/jacobian) into .claude/skills/harbor-benchmarks in your project. Claude Code loads it when a task matches its description.
How do I install Harbor Benchmarks in Codex?
Run `npx skills add morluto/jacobian --skill harbor-benchmarks -a codex`. Or copy the skill folder (.agents/skills/harbor-benchmarks in morluto/jacobian) into .agents/skills/harbor-benchmarks in your project. Codex loads it when a task matches its description.
Can I use Harbor Benchmarks 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 harbor-benchmarks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harbor-benchmarks, .gemini/skills/harbor-benchmarks, .github/skills/harbor-benchmarks and .opencode/skills/harbor-benchmarks in your project.
What does Harbor Benchmarks need to run?
Going by SKILL.md and its folder, Harbor Benchmarks needs the command-line tools its instructions call (make). Our summary lists: Python 3.
Does Harbor Benchmarks 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 Harbor Benchmarks 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 Harbor Benchmarks use?
Harbor Benchmarks 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 Harbor Benchmarks use?
About 690 tokens (SKILL.md is roughly 2.8k 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 343 tokens, read only when the agent opens those files.
What are the alternatives to Harbor Benchmarks?
Skills that share tags, products or a category with Harbor Benchmarks: Setup Medsci (Aperivue/medsci-skills, 329 stars), Deep Research MCP Guide (pminervini/deep-research-mcp, 112 stars), Aer Statspai (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars) and Sympy (zLanqing/codex-claude-academic-skills, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Harbor Benchmarks?
morluto (a GitHub user) maintains it in morluto/jacobian, which has 205 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.