Agent skill

Rhesis

by rhesis-ai in rhesis-ai/rhesis

Design, run, and analyze AI test suites on Rhesis — explore endpoints, build test foundations from a spec, create requirements and metrics, execute tests, and analyze results.

ProprietaryAuto-check passedProduct & Project Management

Install Rhesis

skills CLI
$ npx skills add rhesis-ai/rhesis --skill rhesis -a claude-code

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

GitHub CLI
$ gh skill install rhesis-ai/rhesis rhesis --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/rhesis-ai/rhesis.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/rhesis .claude/skills/rhesis && 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
rhesis
GitHub stars
397
Token cost
~1.2k tokens
SKILL.md length
420 words
Files
31 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
Proprietary

At a glance

Design, run, and analyze AI test suites on Rhesis — explore endpoints, build test foundations from a spec, create requirements and metrics, execute tests, and analyze results.

  • Testing an AI endpoint
  • SKILL.md covers Prerequisites, Shared skeleton, Context-aware intake and Four-path menu (ambiguous start), plus 4 more sections
  • Needs RHESIS_API_KEY
  • Pasting a Product Requirements Document (PRD)

What it does

Rhesis is an agent skill from rhesis-ai/rhesis. Design, run, and analyze AI test suites on Rhesis — explore endpoints, build test foundations from a spec, create requirements and metrics, execute tests, and analyze results. Use when testing an AI endpoint, pasting a Product Requirements Document (PRD) or product spec, or working with Rhesis via MCP.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 32 other files, including reference files (for example `.mcp.json`, `AGENTS.md` and `CLAUDE.md`).

It sits in Product & Project Management, covering PRD writing and Test generation. It works with Model Context Protocol. The repository describes itself as: The collaboration layer for AI teams: domain experts annotate and review agent behavior, engineers improve the agent from what they find.

When your agent uses it

  • Testing an AI endpoint
  • Pasting a Product Requirements Document (PRD)
  • Working with Rhesis via MCP

Example prompts

  • “/rhesis”

Requirements

  • A credential in RHESIS_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 1a2c578. 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

    Links to these hosts (documentation or services it may open):

    • docs.rhesis.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • RHESIS_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Rhesis loads about 1.2k tokens when it runs, and up to ~42k if it reads all its reference files. Until then it costs about 78 tokens; SKILL.md has 420 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~42k

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

Its licence (Proprietary) doesn't allow us to republish the file, so here is its outline and opening line. It has 420 words (~1,237 tokens).

“Platform operations use the rhesis MCP server. Read references/workflow-index.md first to route the request and load the right references. Do not answer platform mechanics from memory.”

— opening of SKILL.md by rhesis-ai, Proprietary
name
rhesis

Read the full SKILL.md on GitHub

Files

SKILL.md and 30 other files (references) in skills/rhesis of rhesis-ai/rhesis.

  • SKILL.md
  • .mcp.json
  • AGENTS.md
  • CLAUDE.md
  • LICENSE
  • README.md
  • references/definitions.md
  • references/entity-model.md
  • references/exploration-strategies.md
  • references/insights-summary.md
  • references/intents.yaml
  • references/metric-authoring.md
  • references/metric-scope.md
  • references/odata-patterns.md
  • references/phases/analysis.md
  • references/phases/creation.md
  • references/phases/direct-requests.md
  • references/phases/discovery.md
  • references/phases/execution.md
  • … and 12 more

Open the folder on GitHubat commit 1a2c578

Compare with similar skills

Rhesis 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.

Rhesis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rhesis this skillrhesis-ai/rhesis397—~1.2kAutomated safety check: PassProprietary
Ouroboros PM InterviewQ00/ouroboros6.2k1 repos~5.7kAutomated safety check: PassMIT
Produck Feedback To Buildtryproduck/produck-skills510—~1kAutomated safety check: PassApache-2.0
Generateanombyte93/prd-taskmaster6041 repos~3.8kAutomated safety check: NotesMIT
Execute Fleetanombyte93/prd-taskmaster604—~2.2kAutomated safety check: NotesMIT
Vscuse Scenario AuthoringOfficeDev/microsoft-365-agents-toolkit781—~4.3kAutomated safety check: PassCustom licence

Similar skills

  • Runs a guided product-manager interview that classifies each question automatically and produces a Product Requirements Document.

    6.2k GitHub starsUsed in 1 repo~5.7k tokens
    Product & Project ManagementAuto-check passed
  • Produck Feedback To Build

    tryproduck/produck-skills

    Pulls full in-context user feedback tickets through the Produck MCP server and turns them into an aligned product change instead of a guess.

    510 GitHub stars~1k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed
  • Generate

    anombyte93/prd-taskmaster

    Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing.

    604 GitHub starsUsed in 1 repo~3.8k tokens
    Product & Project ManagementAuto-check: notes
  • Execute Fleet

    anombyte93/prd-taskmaster

    Phase execution skill for licensed Atlas Fleet runs. An agent skill from anombyte93/prd-taskmaster.

    604 GitHub stars~2.2k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check: notes
  • Vscuse Scenario Authoring

    OfficeDev/microsoft-365-agents-toolkit

    A skill your agent uses when: reading a docs scenario, PRD, mockup, or user flow and using vscuse-ui/noVNC as the primary authoring surface to record, generate, replace, or update vscuse test plans…

    781 GitHub stars~4.3k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Tapd Product Discovery

    TencentBlueKing/bk-bcs

    A skill your agent uses when work starts before a complete PRD exists, including 产品前置, 产品调研, 用户调研, 竞品分析, PRD, 原型, 想法建单, 老板需求, 需求来源, 产品父单, 角色拆单, 设计子单, 前端子单, 后端子单, 页面原型 Spec, BKUI 原型, HTML 原型, 原型评审…

    840 GitHub stars~1.6k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

More from rhesis-ai/rhesis

All 12 skills in this repo
  • Worktree

    rhesis-ai/rhesis

    Manage git worktrees with their own dev ports, symlinked .env files, playground, and simulations.

    397 GitHub stars~627 tokensUpdated yesterday
    Auto-check: notes
  • Update Branch

    rhesis-ai/rhesis

    Rebase a feature branch onto main and force-push it safely. An agent skill from rhesis-ai/rhesis.

    397 GitHub stars~269 tokensUpdated yesterday
    Auto-check passed
  • Docs Design Tokens

    rhesis-ai/rhesis

    Colour, font and design-token rules for the docs site — when hex is banned, when it is correct, and which surfaces ignore the theme.

    397 GitHub stars~658 tokensUpdated yesterday
    Auto-check passed
  • Backend Testing

    rhesis-ai/rhesis

    Run the backend test suite correctly — working directory, Docker requirement, single-test vs full-suite commands.

    397 GitHub stars~400 tokensUpdated yesterday
    Auto-check passed
  • Pull Request

    rhesis-ai/rhesis

    Open a pull request in this repo — branch naming, title format, and the required description sections.

    397 GitHub stars~371 tokensUpdated yesterday
    Auto-check passed
  • Docs Social Images

    rhesis-ai/rhesis

    How the docs site generates per-page og:image cards, and the cache and font traps when changing them.

    397 GitHub stars~377 tokensUpdated yesterday
    Auto-check passed

Questions about Rhesis

What does Rhesis do?

Design, run, and analyze AI test suites on Rhesis — explore endpoints, build test foundations from a spec, create requirements and metrics, execute tests, and analyze results. Rhesis is an agent skill from rhesis-ai/rhesis. Design, run, and analyze AI test suites on Rhesis — explore endpoints, build test foundations from a spec, create requirements and metrics, execute tests, and analyze results.

When should I use Rhesis?

Rhesis fits situations like: testing an AI endpoint; pasting a Product Requirements Document (PRD); working with Rhesis via MCP.

How do I install Rhesis in Claude Code?

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

How do I install Rhesis in Codex?

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

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

What does Rhesis need to run?

Going by SKILL.md and its folder, Rhesis needs credentials named RHESIS_API_KEY. Our summary lists: A credential in RHESIS_API_KEY.

Does Rhesis access the network?

SKILL.md names 1 domain. As links in the text: docs.rhesis.ai. This is read from the text; nothing was executed.

Is Rhesis 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 Rhesis use?

Rhesis carries a proprietary licence (from the LICENSE file in the skill folder). It is published on GitHub, but it is not open source: read the licence file before using or sharing it.

How many tokens does Rhesis use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 41k tokens, read only when the agent opens those files.

What are the alternatives to Rhesis?

Skills that share tags, products or a category with Rhesis: Ouroboros PM Interview (Q00/ouroboros, 6.2k stars), Produck Feedback To Build (tryproduck/produck-skills, 510 stars), Generate (anombyte93/prd-taskmaster, 604 stars) and Execute Fleet (anombyte93/prd-taskmaster, 604 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Rhesis?

rhesis-ai (a GitHub organization) maintains it in rhesis-ai/rhesis, which has 397 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

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