How do I install the Validate Kata Code Nightly Release skill?

Run npx skillmds@latest add gannonh/validate-kata-code-nightly-release in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Validate Kata Code Nightly Release safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Validate Kata Code Nightly Release?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Validate Kata Code Nightly Release free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Validate Kata Code Nightly Release?

gannonh (@gannonh) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Validate Kata Code Nightly Release by gannonh

Name: Validate Kata Code Nightly Release
Author: gannonh

Validate Kata Code Nightly Release

Validate Kata Code nightly releases on macOS with the @Computer plugin. Start and update the nightly app, use its New Project flow to create a timestamp-suffixed nightly UAT project under `/Volumes/EVO/dev`, then execute explicit acceptance criteria for a Codex GPT-5.4-Mini chat, Browser and Files panels, and git commit flow; capture criterion-level screenshots and write an evidence-linked report in the created project. Use when validating or documenting the Kata Code nightly release flow.

gannonh 7cff4b0 3 files · 6.1 KB Updated Sep 17, 2026

File contents

Validate Kata Nightly

Workflow

Use @Computer (or equivalent "computer-use" capability) for every Kata Code UI action and visual check. Capture screenshots and/or video and copy each capture into the created project immediately.

Launch /Applications/Kata Code (Nightly).app. If the bundle is missing, download the latest nightly from the GitHub tags page.
Use Check for Updates… in the app menu and complete the update flow.
Use the app's New Project flow to create a new project at /Volumes/EVO/dev/nightly-uat/nightly-uat-<timestamp> (or a temp location such as /tmp/nightly-uat-<timestamp>) if not running locally. Use the exact project name nightly-uat-<timestamp> and a timestamp unique to this run.
Copy assets/report.md to the created project as report.md. Save all screenshots and any video recording in the created project.
Evaluate every acceptance criterion below. Capture a screenshot for each criterion, even when it fails, and save it as AC##-<short-name>.png in the created project.
Complete report.md. Mark each criterion Pass, Fail, or Blocked, include the exact evidence filename, and list all failures and blockers in the final summary.

Acceptance Criteria

ID	Criterion	Required screenshot
AC01	Kata Code (Nightly) opens successfully.	`AC01-app-launched.png` shows the running nightly app.
AC02	`Check for Updates…` completes and the app reports the latest nightly is installed or restarts after installing it.	`AC02-update-check.png` shows the update result.
AC03	The New Project flow creates and opens `/Volumes/EVO/dev/nightly-uat-<timestamp>`.	`AC03-new-project.png` shows the created project name or path.
AC04	A new chat uses Codex with `GPT-5.4-Mini` and receives a response.	`AC04-codex-response.png` shows the selected model and response.
AC05	The right-panel Browser loads "Pair with this environment" modal at `http://127.0.0.1:3774`.	`AC05-browser.png` shows the loaded local page.
AC06	The right-panel Files view shows the created UAT project tree.	`AC06-files-panel.png` shows the project files.
AC07	`nightly-uat.txt` appears as an untracked change before commit.	`AC07-untracked-file.png` shows the file in Files or Changes.
AC08	The new file is committed and `git status` is clean.	`AC08-commit-clean.png` shows the commit result and clean status in Changes.

Notes

Refresh Computer state after every UI change before selecting the next element.
Use osascript for the app menu when needed.
Use open -n for the nightly bundle if another Kata Code app is already running.
Use the required filename for every acceptance-criteria screenshot.
Save all evidence files and report.md inside the created nightly-uat-<timestamp> project.
Record video only when the Computer plugin supports it for the active environment; save it in the created project.

---name: validate-kata-code-nightly-releasedescription: Validate Kata Code nightly releases on macOS with the @Computer plugin. Start and update the nightly app, use its New Project flow to create a timestamp-suffixed nightly UAT project under `/Volumes/EVO/dev`, then execute explicit acceptance criteria for a Codex GPT-5.4-Mini chat, Browser and Files panels, and git commit flow; capture criterion-level screenshots and write an evidence-linked report in the created project. Use when validating or documenting the Kata Code nightly release flow.---# Validate Kata Nightly## WorkflowUse [@Computer](plugin://computer-use@openai-bundled) (or equivalent "computer-use" capability) for every Kata Code UI action and visual check. Capture screenshots and/or video and copy each capture into the created project immediately.1. Launch `/Applications/Kata Code (Nightly).app`. If the bundle is missing, download the latest nightly from the GitHub tags page.2. Use `Check for Updates…` in the app menu and complete the update flow.3. Use the app's New Project flow to create a new project at `/Volumes/EVO/dev/nightly-uat/nightly-uat-<timestamp>` (or a temp location such as `/tmp/nightly-uat-<timestamp>`) if not running locally. Use the exact project name `nightly-uat-<timestamp>` and a timestamp unique to this run.4. Copy [assets/report.md](assets/report.md) to the created project as `report.md`. Save all screenshots and any video recording in the created project.5. Evaluate every acceptance criterion below. Capture a screenshot for each criterion, even when it fails, and save it as `AC##-<short-name>.png` in the created project.6. Complete `report.md`. Mark each criterion `Pass`, `Fail`, or `Blocked`, include the exact evidence filename, and list all failures and blockers in the final summary.## Acceptance Criteria| ID | Criterion | Required screenshot || ---- | ------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- || AC01 | Kata Code (Nightly) opens successfully. | `AC01-app-launched.png` shows the running nightly app. || AC02 | `Check for Updates…` completes and the app reports the latest nightly is installed or restarts after installing it. | `AC02-update-check.png` shows the update result. || AC03 | The New Project flow creates and opens `/Volumes/EVO/dev/nightly-uat-<timestamp>`. | `AC03-new-project.png` shows the created project name or path. || AC04 | A new chat uses Codex with `GPT-5.4-Mini` and receives a response. | `AC04-codex-response.png` shows the selected model and response. || AC05 | The right-panel Browser loads "Pair with this environment" modal at `http://127.0.0.1:3774`. | `AC05-browser.png` shows the loaded local page. || AC06 | The right-panel Files view shows the created UAT project tree. | `AC06-files-panel.png` shows the project files. || AC07 | `nightly-uat.txt` appears as an untracked change before commit. | `AC07-untracked-file.png` shows the file in Files or Changes. || AC08 | The new file is committed and `git status` is clean. | `AC08-commit-clean.png` shows the commit result and clean status in Changes. |## Notes- Refresh Computer state after every UI change before selecting the next element.- Use `osascript` for the app menu when needed.- Use `open -n` for the nightly bundle if another Kata Code app is already running.- Use the required filename for every acceptance-criteria screenshot.- Save all evidence files and `report.md` inside the created `nightly-uat-<timestamp>` project.- Record video only when the Computer plugin supports it for the active environment; save it in the created project.

Frequently asked questions