Agent skill

Kitaru UI API Development

by zenml-io in zenml-io/kitaru

Add, reuse, or change a frontend-specific Kitaru REST response under /api/v1/ui and its OpenAPI contract in zenml-frontend-monorepo.

Apache-2.0Auto-check passedDevelopment

Install Kitaru UI API Development

skills CLI
$ npx skills add zenml-io/kitaru --skill kitaru-ui-api-development -a claude-code

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

GitHub CLI
$ gh skill install zenml-io/kitaru kitaru-ui-api-development --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/zenml-io/kitaru.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/kitaru-ui-api-development .claude/skills/kitaru-ui-api-development && 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
kitaru-ui-api-development
GitHub stars
301
Token cost
~1.6k tokens
SKILL.md length
862 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

Add, reuse, or change a frontend-specific Kitaru REST response under /api/v1/ui and its OpenAPI contract in zenml-frontend-monorepo.

  • A dashboard screen needs a purpose-built data shape
  • SKILL.md covers Decide whether the route…, Backend shape, Frontend consumer and Validation, plus 1 more section
  • Calls pnpm, just and uv
  • Not for ordinary reusable resources

What it does

Kitaru UI API Development is an agent skill from zenml-io/kitaru. Add, reuse, or change a frontend-specific Kitaru REST response under /api/v1/ui and its OpenAPI contract in zenml-frontend-monorepo. Use when a dashboard screen needs a purpose-built data shape, not for ordinary reusable resources or UI bundle releases.

Its SKILL.md is about 1.6k 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 Development, covering Monorepo tooling and OpenAPI specifications. It works with OpenAPI. The repository describes itself as: Agent traces you can run, not just read. The licence is Apache-2.0.

When your agent uses it

  • A dashboard screen needs a purpose-built data shape
  • Not for ordinary reusable resources
  • UI bundle releases

Example prompts

  • “/kitaru-ui-api-development”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 9d2df59. 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:

    • pnpm
    • just
    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm and uv, which can reach the network depending on how they are called.

    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

Kitaru UI API Development loads about 1.6k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 862 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 zenml-io/kitaru at commit 9d2df59, republished under its Apache-2.0 licence (© zenml-io). 862 words, ~1,648 tokens.

Download SKILL.mdSave it as .claude/skills/kitaru-ui-api-development/SKILL.md (or your agent's skills folder).
name
kitaru-ui-api-development
description
Add, reuse, or change a frontend-specific Kitaru REST response under /api/v1/ui and its OpenAPI contract in zenml-frontend-monorepo. Use when a dashboard screen needs a purpose-built data shape, not for ordinary reusable resources or UI bundle releases.

Kitaru UI API Development

Use this for changes that cross the Kitaru server API and the Kitaru UI in zenml-frontend-monorepo. Load the same-name kitaru-dev repo skill for the current host for general commands and PR guidance. Use FRONTEND-TESTING.md and the current host's kitaru-release repo skill only when the change also affects UI bundling, serving, selection, or publication.

These rules reflect the current UI endpoints, their frontend consumers, and frontend maintainer guidance.

Decide whether the route belongs under /api/v1/ui

Search the live routers, OpenAPI contract, and frontend modules for an existing route and consumer before designing another one. If they already satisfy the requested screen, verify that flow and do not add a duplicate endpoint.

Use a UI-specific endpoint when a frontend screen needs a response shape that the existing resource APIs do not provide. For example, /api/v1/sessions returns sessions without their evaluations, while /api/v1/ui/sessions returns sessions together with their evaluations for the sessions table. Another current endpoint aggregates evaluations across an experiment run for a frontend view.

Prefer the normal /api/v1/<resource> API when the behavior is a reusable domain operation or an external SDK consumer would reasonably need it. Do not add a UI endpoint merely to move ordinary presentation logic to the server.

Before implementation, state:

  • the concrete frontend consumer and the data shape it needs
  • why the contract is UI-specific rather than a reusable resource API
  • whether the response is a pageable collection, a singular resource, or a bounded aggregate, with its ordering, pagination, caps, missing-data, and empty-state semantics
  • whether the response can be assembled through current application services

There is no established precedent for frontend-only mutations. If the request adds one, stop and ask the maintainers to agree on its placement. New domain behavior and generally useful external APIs should go through the normal resource checklist instead.

Backend shape

Keep frontend-specific DTOs in src/kitaru/api_models/v1/ui.py and routes in src/kitaru/server/adapters/rest/routers/ui.py, registered under /api/v1/ui in src/kitaru/server/api/app.py.

Follow src/kitaru/server/adapters/rest/AGENTS.md:

  • use APIRouter(route_class=KitaruAPIRoute)
  • require authorize and pass the resulting actor to every application service
  • compose current service and repository interfaces instead of querying the database directly or bypassing application layers
  • use explicit response DTO mappings and let app-level handlers map domain errors
  • state client-visible statuses in route docstrings

Paginate a UI endpoint when it returns a collection that clients need to page through, using the same pagination contract as other collection endpoints. Do not add artificial pagination to singular resources or bounded aggregate responses.

UI read models may internally traverse all pages needed for correct joins or aggregates, but review the cost of that full traversal and define and test the response bounds. Treat result ordering, truncation, missing evaluations, duplicate names, type grouping, and null values as API contract, not implementation detail. The current experiment-run aggregate covers all replays and reads only the evaluations linked to those replays, so later evaluations cannot rewrite an existing run's statistics. It groups by evaluation name, data type, and evaluator version, excludes manual evaluations, and returns paired values for the 50 most recent replays. Keep frontend keys aligned with that grouping and preserve evaluator-version identity. Aggregate min_score, max_score, and target_score are non-null only when every row in that side of the group has the same value. Do not assume the current all-replay scope is correct for a comparison screen that may need a shared cohort or another subset.

Do not add SDK, CLI, or MCP parity automatically for a UI-only read model. If another consumer needs the same contract, stop and decide whether to promote it to a normal resource API.

Show full SKILL.md (278 more words)Show less

Frontend consumer

The generated frontend types live in zenml-frontend-monorepo/shared/kitaru/src/api/openapi.d.ts. Apply the same OpenAPI rules as for any other endpoint: regenerate the declarations when the endpoint adds or changes a response schema; no new frontend type is needed when it returns an existing schema. Regenerate from a server exposing the current openapi.json; never hand-edit that file.

Keep the transport call and API-to-domain mapping in the owning module under shared/kitaru/src/modules/. Add focused tests for the request, mapping, empty states, errors, and any cap or ordering that affects what the user sees. Treat backend and frontend delivery like any other cross-repository API change: verify compatibility and deployment order, but do not impose a blanket same-merge requirement.

The existing generation command is run from shared/kitaru/:

bash
pnpm generate:types -- http://localhost:8000

Validation

In Kitaru:

  • update tests/server/test_route_manifest.py when a route is added, removed, or renamed
  • add focused ASGI route tests beside tests/server/test_ui_api.py or tests/server/test_ui_experiment_runs_api.py
  • run the focused tests and just openapi-check
  • regenerate openapi/openapi.json with uv run python scripts/generate_openapi.py when a route or schema changes, then the generated TypeScript types with pnpm run generate
  • run just check and the relevant broader server tests

In zenml-frontend-monorepo, regenerate the OpenAPI declarations, then run the shared Kitaru package's typecheck and tests plus the affected Kitaru UI checks. Exercise the real UI flow against the changed backend when the environment is available.

Reviewer focus

Ask reviewers to verify that the response shape is genuinely specific to a frontend screen, that pageable collections use the normal pagination contract, and that caps, ordering, missing-data, and error semantics match what the UI should promise. Exercise the affected OSS or managed Pro flow when the endpoint changes one; there is no blanket requirement to test unrelated frontend deployments.

© zenml-io, Apache-2.0. 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 .agents/skills/kitaru-ui-api-development of zenml-io/kitaru.

Open the folder on GitHubat commit 9d2df59

Compare with similar skills

Kitaru UI API Development 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.

Kitaru UI API Development compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kitaru UI API Development this skillzenml-io/kitaru301—~1.6kAutomated safety check: PassApache-2.0
Cloud Agents Starterscalar/scalar16k—~1.4kAutomated safety check: PassMIT
Add Namespaceswagger-api/apidom100—~8.1kAutomated safety check: PassNone
Zodjasonjgardner/blockbench-mcp-plugin4913 repos~1.4kAutomated safety check: PassGPL-3.0
Dashclaw Shipucsandman/DashClaw310—~7.2kAutomated safety check: PassMIT
Dependabot Alerts Updatelivesession/xyd114—~2kAutomated safety check: PassMIT

Similar skills

  • Minimal starter runbook for cloud agents to install dependencies, run packages, execute tests, and troubleshoot the Scalar monorepo quickly.

    16k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Add Namespace

    swagger-api/apidom

    Creates a new namespace package for a new API specification version in the ApiDOM monorepo

    100 GitHub stars~8.1k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed
  • Zod

    jasonjgardner/blockbench-mcp-plugin

    Zod schema validation best practices for type safety, parsing, and error handling.

    491 GitHub starsUsed in 3 repos~1.4k tokens
    DevelopmentAuto-check passed
  • Dashclaw Ship

    ucsandman/DashClaw

    The single command that gets a DashClaw change ON MAIN AND LIVE — it resolves everything blocking production, never defers, and never hands back a checklist.

    310 GitHub stars~7.2k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Automatically fetch and fix Dependabot security alerts by querying GitHub REST API for open alerts, identifying vulnerable packages, researching secure versions, and updating package.json files…

    114 GitHub stars~2k tokensUpdated 15 days ago
    DevelopmentAuto-check passed
  • Official

    Bumps the databricks-sdk-go dependency in the Databricks CLI together with its pinned OpenAPI spec SHA, then regenerates the files that depend on them.

    404 GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check: notes

More from zenml-io/kitaru

  • Kitaru Docs

    zenml-io/kitaru

    Kitaru documentation surfaces, link rules, and accuracy rules.

    301 GitHub stars~936 tokensUpdated today
    Auto-check passed
  • Kitaru Release

    zenml-io/kitaru

    Discover dependencies and prepare or execute Kitaru core and plugin releases, including version proposals, Kitaru UI selection, release PRs, ordered tag commands, artifact verification, and recovery.

    301 GitHub stars~7k tokensUpdated today
    Auto-check passed
  • Kitaru Dev

    zenml-io/kitaru

    Kitaru just recipes, CLI structure and structured-output contract, analytics events, and PR-description conventions.

    301 GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Add or change a Kitaru framework adapter that records native agent runs or supports bounded replay.

    301 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Add or change a separately packaged Kitaru trace importer that normalizes provider exports into imported sessions.

    301 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Kitaru Tests Release

    zenml-io/kitaru

    Kitaru test layout, CI workflows, and release-workflow behavior.

    301 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

Works with

Questions about Kitaru UI API Development

What does Kitaru UI API Development do?

Add, reuse, or change a frontend-specific Kitaru REST response under /api/v1/ui and its OpenAPI contract in zenml-frontend-monorepo. Kitaru UI API Development is an agent skill from zenml-io/kitaru. Add, reuse, or change a frontend-specific Kitaru REST response under /api/v1/ui and its OpenAPI contract in zenml-frontend-monorepo.

When should I use Kitaru UI API Development?

Kitaru UI API Development fits situations like: A dashboard screen needs a purpose-built data shape; not for ordinary reusable resources; UI bundle releases.

How do I install Kitaru UI API Development in Claude Code?

Run `npx skills add zenml-io/kitaru --skill kitaru-ui-api-development -a claude-code`. Or copy the skill folder (.agents/skills/kitaru-ui-api-development in zenml-io/kitaru) into .claude/skills/kitaru-ui-api-development in your project. Claude Code loads it when a task matches its description.

How do I install Kitaru UI API Development in Codex?

Run `npx skills add zenml-io/kitaru --skill kitaru-ui-api-development -a codex`. Or copy the skill folder (.agents/skills/kitaru-ui-api-development in zenml-io/kitaru) into .agents/skills/kitaru-ui-api-development in your project. Codex loads it when a task matches its description.

Can I use Kitaru UI API Development 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 zenml-io/kitaru --skill kitaru-ui-api-development -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kitaru-ui-api-development, .gemini/skills/kitaru-ui-api-development, .github/skills/kitaru-ui-api-development and .opencode/skills/kitaru-ui-api-development in your project.

What does Kitaru UI API Development need to run?

Going by SKILL.md and its folder, Kitaru UI API Development needs the command-line tools its instructions call (pnpm, just and uv). Our summary lists: Python 3.

Does Kitaru UI API Development access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Kitaru UI API Development 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 Kitaru UI API Development use?

Kitaru UI API Development is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Kitaru UI API Development use?

About 1.6k tokens (SKILL.md is roughly 6.6k 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 Kitaru UI API Development?

Skills that share tags, products or a category with Kitaru UI API Development: Cloud Agents Starter (scalar/scalar, 16k stars), Add Namespace (swagger-api/apidom, 100 stars), Zod (jasonjgardner/blockbench-mcp-plugin, 491 stars) and Dashclaw Ship (ucsandman/DashClaw, 310 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kitaru UI API Development?

zenml-io (a GitHub organization) maintains it in zenml-io/kitaru, which has 301 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

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