Auto tmux Operator
tradecatlabs/vibe-coding-cn
Operates tmux sessions like an administrator: reads pane output, sends keys, inspects many panes at once, and coordinates multiple AI terminals through a swarm state script, built on oh-my-tmux.
Add or change a separately packaged Kitaru trace importer that normalizes provider exports into imported sessions.
Install Kitaru Importer Development
$ npx skills add zenml-io/kitaru --skill kitaru-importer-development -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zenml-io/kitaru kitaru-importer-development --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/zenml-io/kitaru.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/kitaru-importer-development .claude/skills/kitaru-importer-development && 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 "kitaru-importer-development" agent skill from https://github.com/zenml-io/kitaru/tree/develop/.agents/skills/kitaru-importer-development into .claude/skills/kitaru-importer-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kitaru-importer-development", 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/zenml-io/kitaru/tree/develop/.agents/skills/kitaru-importer-developmentType 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 zenml-io/kitaru --skill kitaru-importer-development -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zenml-io/kitaru kitaru-importer-development --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenml-io/kitaru.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/kitaru-importer-development .agents/skills/kitaru-importer-development && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "kitaru-importer-development" agent skill from https://github.com/zenml-io/kitaru/tree/develop/.agents/skills/kitaru-importer-development into .agents/skills/kitaru-importer-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kitaru-importer-development", 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 zenml-io/kitaru --skill kitaru-importer-development -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zenml-io/kitaru kitaru-importer-development --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenml-io/kitaru.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/kitaru-importer-development .cursor/skills/kitaru-importer-development && 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 "kitaru-importer-development" agent skill from https://github.com/zenml-io/kitaru/tree/develop/.agents/skills/kitaru-importer-development into .cursor/skills/kitaru-importer-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kitaru-importer-development", 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/zenml-io/kitaru.git --path .agents/skills/kitaru-importer-development--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 zenml-io/kitaru --skill kitaru-importer-development -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zenml-io/kitaru kitaru-importer-development --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenml-io/kitaru.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/kitaru-importer-development .gemini/skills/kitaru-importer-development && 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 "kitaru-importer-development" agent skill from https://github.com/zenml-io/kitaru/tree/develop/.agents/skills/kitaru-importer-development into .gemini/skills/kitaru-importer-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kitaru-importer-development", 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 zenml-io/kitaru kitaru-importer-developmentInstalls 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 zenml-io/kitaru --skill kitaru-importer-development -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zenml-io/kitaru.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/kitaru-importer-development .github/skills/kitaru-importer-development && 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 "kitaru-importer-development" agent skill from https://github.com/zenml-io/kitaru/tree/develop/.agents/skills/kitaru-importer-development into .github/skills/kitaru-importer-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kitaru-importer-development", 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 zenml-io/kitaru --skill kitaru-importer-development -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zenml-io/kitaru kitaru-importer-development --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenml-io/kitaru.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/kitaru-importer-development .opencode/skills/kitaru-importer-development && 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 "kitaru-importer-development" agent skill from https://github.com/zenml-io/kitaru/tree/develop/.agents/skills/kitaru-importer-development into .opencode/skills/kitaru-importer-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kitaru-importer-development", 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
kitaru-importer-development- GitHub stars
- 302
- Token cost
- ~1.9k tokens
- SKILL.md length
- 945 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Add or change a separately packaged Kitaru trace importer that normalizes provider exports into imported sessions.
- Importer packages under plugins/packages
- SKILL.md covers Implement the parser contract, Importer-backed adapter, Package, register, and version and Core boundary, plus 1 more section
- Calls just
- Not recording adapters
What it does
Kitaru Importer Development is an agent skill from zenml-io/kitaru. Add or change a separately packaged Kitaru trace importer that normalizes provider exports into imported sessions. Use for importer packages under plugins/packages, not recording adapters or unrelated SDK, API, or server work.
Its SKILL.md is about 1.9k 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 DevOps & Cloud. The repository describes itself as: Agent traces you can run, not just read. The licence is Apache-2.0.
When your agent uses it
- Importer packages under plugins/packages
- Not recording adapters
Example prompts
- “/kitaru-importer-development”
What it can do on your machine
Read from SKILL.md and the folder at commit e7e55f7. 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:
just
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
Kitaru Importer Development loads about 1.9k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 945 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 zenml-io/kitaru at commit e7e55f7, republished under its Apache-2.0 licence (© zenml-io). 945 words, ~1,922 tokens.
Download SKILL.mdSave it as
.claude/skills/kitaru-importer-development/SKILL.md (or your agent's skills folder).- name
- kitaru-importer-development
- description
- Add or change a separately packaged Kitaru trace importer that normalizes provider exports into imported sessions. Use for importer packages under plugins/packages, not recording adapters or unrelated SDK, API, or server work.
Kitaru Importer Development
Read AGENTS.md, plugins/AGENTS.md, plugins/DEVELOPMENT.md, and src/kitaru/task/importer.py. Treat the task module as the executable importer contract. Read the JSONL importer first for the smallest example, then the closest provider importer and its fixtures. Load the same-name kitaru-dev repo skill for the current host for the general command and PR workflow. When an importer version or another release unit changes, also load the kitaru-release skill before opening or updating the PR. State whether each changed distribution will ship in the next applicable release or be deferred past it; attach its exact release-unit label when publication is deferred past that release.
First decide whether the request needs a reusable package. A one-off conversion to Kitaru JSONL or a self-contained registered script may be smaller. Registration stores source metadata; it does not upload or vendor a package.
Implement the parser contract
Implement parse(payload: bytes, params: dict[str, Any]) as an iterator of ImportedSession or ImportFailure.
- Choose and document the source-to-session boundary.
- Derive a stable source
external_id; Kitaru deduplicates using the importer provider and this ID. - Preserve source inputs and outputs. Populate selectors, models, tokens, costs, reasoning selectors, framework, attributes, and metadata only when the export supports them without guessing.
- Yield
ImportFailurefor an isolated bad record. An exception raised while starting or advancing the parser ends the import task. - Preserve valid node ordering and graph relationships. Use either nested nodes or the flat indexed form accepted by
flatten_nodes; follow that function's validation rules. - Validate provider parameters and keep normalization or grouping provenance in metadata when it changes how the source is interpreted.
Use representative provider exports as fixtures. Cover malformed records, missing or duplicate IDs, grouping, ordering, parent links, model and tool normalization, reasoning selectors, selector escaping, and stable re-import behavior as applicable.
Importer-backed adapter
An importer package for a provider with a live read API can also ship an importer-backed adapter: a class subclassing kitaru.importer_adapter.ImporterBackedAdapter that wraps the user's agent entrypoint, waits for the provider to ingest the trace, fetches it, and imports it through the package's own parser. Read src/kitaru/importer_adapter.py and the langfuse importer package as the reference implementation before adding one.
- Split the code into
adapter.py(the subclass: trace pinning, SDK buffer flush, per-run cache) andapi.py(the provider read layer: credential and client resolution, the completeness poll, single fetch, serialization to parser payload bytes). Keepapi.pyadapter-free so future direct-from-API imports can reuse it. - Run blocking SDK calls inside the async hooks via
asyncio.to_thread, never inopen_trace()teardown. - Provider SDK dependencies belong in the importer package's
adapterextra. Users import the adapter from theadaptersubmodule, never from the package__init__, soparsenever loads the SDK. Adapter tests live underplugins/tests/adapters/<slug>/and run the real parser against a faked provider SDK. - Agent versions whose run spec command uses such an adapter must declare
runtime_capabilitieswithoverrides: falseandtool_policies: false, since the runtime cannot intercept model or tool calls. Replay and experiment run creation reject configs the declaration cannot apply, and the adapter raises on such configs as a backstop.
Show full SKILL.md (442 more words)Show less
Package, register, and version
For feature PRs, follow the version and dependency ownership rules in plugins/AGENTS.md. Leave existing package versions and default pins unchanged. Record unreleased core requirements with the exact development dependency described in plugins/DEVELOPMENT.md; release prep selects and replaces release versions.
An importer distribution lives under plugins/packages/<slug>-importer/, with its source, pyproject.toml, changelog, and focused tests under plugins/tests/importers/. Export parse through the package __all__. Add the package to plugins/README.md, release/release-units.toml, the exact inventory in tests/scripts/test_release_units.py, and plugins/uv.lock. A non-default package also declares tool.kitaru.artifact.import-module so artifact smoke can import it without a default-catalog entry.
For a new distribution, complete the new-distribution integration review in the kitaru-dev skill. In particular, include the worker's first-party package list even when this importer will not be in the default server catalog.
Use kitaru importer scaffold and kitaru importer test for bounded local scripts. Register an in-progress self-contained implementation with kitaru importer register ... --script ... --entrypoint .... Use an exact package requirement when validation must cover wheel installation. Registration creates remote state, is not idempotent, and needs an explicit server plus a worker that can resolve the source. Do not run it without authorization. The package's PyPI version and Kitaru's server-assigned importer version are separate: use kitaru importer version register for each new immutable registered implementation, and never mutate the behavior behind an existing version.
A default importer additionally needs:
default-catalog = trueinrelease/release-units.toml- a matching
DEFAULT_PLUGIN_DEFINITIONSentry insrc/kitaru/server/api/bootstrap.py - catalog coverage in
tests/server/test_default_plugins.py
Do not make an importer a server default merely because its package exists. Default-catalog inclusion is a separate product and deployment decision.
Document only shipped importers. Update the relevant guide under docs/book/guides/, the importing overview, and docs/book/toc.md when the provider is actually available.
Core boundary
An importer normally adapts provider data to the existing contract without changing Kitaru core. Stop and surface the missing contract before changing any of these areas merely to complete an importer:
openapi/src/kitaru/api_models/src/kitaru/client/src/kitaru/server/, except an explicitly approved default-catalog entrysrc/kitaru/worker/- CLI or MCP code
Explain which source fact cannot be represented, why metadata or the current node/session models are insufficient, and the smallest separate contract decision that would unblock it. Continue only when that broader change is explicitly in scope.
Validation
Run the focused importer tests and plugins/tests/importers/test_normalization.py when shared normalization semantics are involved. Then run the plugin workspace format, lint, typecheck, and test commands from plugins/AGENTS.md.
Run just plugin-artifact-smoke after package metadata, default definitions, requirement pins, entrypoints, or release installation paths change. Run tests/scripts/test_release_units.py after adding or changing a release unit. Include tests/server/test_default_plugins.py for default-catalog changes. Use the candidate-server procedure in plugins/DEVELOPMENT.md whenever package registration or task execution changes, whether or not the importer is a default.
© 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-importer-development of zenml-io/kitaru.
Open the folder on GitHubat commit e7e55f7
Compare with similar skills
Kitaru Importer 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Kitaru Importer Development this skillzenml-io/kitaru | 302 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Auto tmux Operatortradecatlabs/vibe-coding-cn | 17k | — | ~4.7k | Automated safety check: Pass | MIT | |
| Myclaw BackupLeoYeAI/openclaw-backup | 659 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Trigger.dev Cost Savings Auditpapermark/papermark | 9.2k | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| OpenRig Upgrade Proceduremvschwarz/openrig | 6.2k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Docs Corpus Auditmicrosoft/apm | 4k | — | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Myclaw Backup
LeoYeAI/openclaw-backup
Backup and restore all OpenClaw configuration, agent memory, skills, and workspace data.
Trigger.dev Cost Savings Audit
papermark/papermark
Audits Trigger.dev tasks, schedules and run history for wasteful machine sizes, retries, polling and cron frequency to cut spend.
OpenRig Upgrade Procedure
mvschwarz/openrig
Walks an agent through upgrading the OpenRig CLI and daemon one observed step at a time, keeping live seats alive and reconciling managed plugin files.
- Official
Docs Corpus Audit
microsoft/apm
A skill your agent uses to run a holistic regrounding pass on the entire microsoft/apm documentation corpus against current source code, page-by-page, and emit surgical fixes for stale claims.
Thememoria
matrixorigin/memoria
Use Memoria as OpenClaw's durable memory slot. An agent skill from matrixorigin/memoria.
More from zenml-io/kitaru
Kitaru Docs
zenml-io/kitaru
Kitaru documentation surfaces, link rules, and accuracy rules.
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.
Kitaru UI API Development
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.
Kitaru Dev
zenml-io/kitaru
Kitaru just recipes, CLI structure and structured-output contract, analytics events, and PR-description conventions.
Kitaru Adapter Development
zenml-io/kitaru
Add or change a Kitaru framework adapter that records native agent runs or supports bounded replay.
Kitaru Tests Release
zenml-io/kitaru
Kitaru test layout, CI workflows, and release-workflow behavior.
Related
Categories
Questions about Kitaru Importer Development
What does Kitaru Importer Development do?
Add or change a separately packaged Kitaru trace importer that normalizes provider exports into imported sessions. Kitaru Importer Development is an agent skill from zenml-io/kitaru. Add or change a separately packaged Kitaru trace importer that normalizes provider exports into imported sessions.
When should I use Kitaru Importer Development?
Kitaru Importer Development fits situations like: importer packages under plugins/packages; not recording adapters.
How do I install Kitaru Importer Development in Claude Code?
Run `npx skills add zenml-io/kitaru --skill kitaru-importer-development -a claude-code`. Or copy the skill folder (.agents/skills/kitaru-importer-development in zenml-io/kitaru) into .claude/skills/kitaru-importer-development in your project. Claude Code loads it when a task matches its description.
How do I install Kitaru Importer Development in Codex?
Run `npx skills add zenml-io/kitaru --skill kitaru-importer-development -a codex`. Or copy the skill folder (.agents/skills/kitaru-importer-development in zenml-io/kitaru) into .agents/skills/kitaru-importer-development in your project. Codex loads it when a task matches its description.
Can I use Kitaru Importer 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-importer-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-importer-development, .gemini/skills/kitaru-importer-development, .github/skills/kitaru-importer-development and .opencode/skills/kitaru-importer-development in your project.
What does Kitaru Importer Development need to run?
Going by SKILL.md and its folder, Kitaru Importer Development needs the command-line tools its instructions call (just).
Does Kitaru Importer Development 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 Kitaru Importer 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 Importer Development use?
Kitaru Importer 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 Importer Development use?
About 1.9k tokens (SKILL.md is roughly 7.7k 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 Importer Development?
Skills that share tags, products or a category with Kitaru Importer Development: Auto tmux Operator (tradecatlabs/vibe-coding-cn, 17k stars), Myclaw Backup (LeoYeAI/openclaw-backup, 659 stars), Trigger.dev Cost Savings Audit (papermark/papermark, 9.2k stars) and OpenRig Upgrade Procedure (mvschwarz/openrig, 6.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Kitaru Importer Development?
zenml-io (a GitHub organization) maintains it in zenml-io/kitaru, which has 302 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 8, 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.