How do I install the Kumo Issue skill?

Run npx skillmds@latest add tomevault-io/kumo-issue 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 Kumo Issue 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 Kumo Issue?

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 Kumo Issue free to use?

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

Who published Kumo Issue?

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

Kumo Issue by tomevault-io — Agent Skill

Name: Kumo Issue
Author: tomevault-io

Kumo Issue

File a GitHub issue on the kumo-coding-agent repo to report a gap, bug, or feature request for the Kumo data science agent (context docs, skills, or verticals). Use when someone says "report a problem with the agent", "the agent got something wrong", "file an issue", or "request a new skill". Use when this capability is needed.

tomevault-io d0d2e30 2 files · 4.5 KB Updated Sep 17, 2026

File contents

File a kumo-coding-agent Issue

Create a structured GitHub issue on kumo-ai/kumo-coding-agent for agent gaps, bugs, or feature requests.

This command works in both Claude Code (interactive) and Codex (headless). In Codex, provide a description as the argument — interactive prompting is not available.

User input: $ARGUMENTS

Instructions

Step 1: Validate GitHub CLI Auth

Run:

gh auth status

If gh is not authenticated, tell the user to run gh auth login -h github.com first and stop before gathering more information.

Step 2: Gather Information

If $ARGUMENTS is provided, parse it to understand the issue.

If $ARGUMENTS is empty, ask the user these questions (skip in headless mode):

What happened? (What were you trying to do?)
Which skill or context doc was involved? (If known)
What did you expect vs what happened?

Step 3: Classify the Issue

Determine the type based on the description:

Type	Signal	Label
gap	"agent didn't know", "missing info", "couldn't answer"	`gap`
bug	"wrong info", "incorrect", "outdated", "says X but should be Y"	`bug`
feature	"add support for", "new skill", "new vertical", "would be nice"	`enhancement`

Step 4: Identify Affected Files

Search for files related to the issue:

grep -rl "<relevant keyword>" context/ skills/

If the user mentioned a specific file, verify it exists and note the relevant section.

Also check if this is already tracked:

grep -i "<keyword>" context/_gaps.yaml

If already tracked, tell the user and ask if they still want to file an issue.

Step 5: Compose the Issue

Title format: kumo: <concise description>

Examples:

kumo: missing Databricks Unity Catalog connector docs
kumo: pql-syntax.md lists MODE as valid aggregation
kumo: add healthcare/clinical trials vertical

Body template:

## Type

<gap | bug | feature>

## Affected File(s)

- `<path>` (line ~N)

## Description

<Clear description of the issue>

## Expected Behavior

<What should happen / what info should be there>

## Current Behavior

<What actually happens / what the doc currently says>

## Suggested Fix

<If obvious — otherwise "Needs investigation">

## Context

<Any additional context: SDK version, customer use case, etc.>

---
*Filed via `/kumo-issue` by @REPORTER*

Step 6: Create the Issue

First, capture the reporter's GitHub identity:

gh_user=$(gh api user --jq '.login')

Replace @REPORTER in the body template with @$gh_user.

Run:

gh issue create \
  --repo kumo-ai/kumo-coding-agent \
  --title "<title>" \
  --label "kumo-coding-agent,<type-label>" \
  --assignee "manushmurali-kumo" \
  --body "<body>"

Use a heredoc for the body to preserve formatting.

If gh is not authenticated, tell the user to run gh auth login -h github.com first and provide the exact command to retry.

Step 7: Follow Up

After the issue is created:

Print the issue URL
Tell the user: "Your issue has been filed. A Kumo team member will review it and follow up with you."
If the type is gap, suggest also adding an entry to context/_gaps.yaml with status: open
If the type is bug and the fix is obvious, suggest running /kumo-pr to fix it directly

Source: kumo-ai/kumo-coding-agent — distributed by TomeVault.

---name: kumo-issuedescription: File a GitHub issue on the kumo-coding-agent repo to report a gap, bug, or feature request for the Kumo data science agent (context docs, skills, or verticals). Use when someone says "report a problem with the agent", "the agent got something wrong", "file an issue", or "request a new skill". Use when this capability is needed.---# File a kumo-coding-agent IssueCreate a structured GitHub issue on kumo-ai/kumo-coding-agent for agentgaps, bugs, or feature requests.**This command works in both Claude Code (interactive) and Codex (headless).**In Codex, provide a description as the argument — interactive prompting isnot available.**User input:** $ARGUMENTS## Instructions### Step 1: Validate GitHub CLI AuthRun:```bashgh auth status```If `gh` is not authenticated, tell the user to run `gh auth login -h github.com`first and stop before gathering more information.### Step 2: Gather InformationIf `$ARGUMENTS` is provided, parse it to understand the issue.If `$ARGUMENTS` is empty, ask the user these questions (skip in headless mode):1. What happened? (What were you trying to do?)2. Which skill or context doc was involved? (If known)3. What did you expect vs what happened?### Step 3: Classify the IssueDetermine the type based on the description:| Type | Signal | Label ||------|--------|-------|| **gap** | "agent didn't know", "missing info", "couldn't answer" | `gap` || **bug** | "wrong info", "incorrect", "outdated", "says X but should be Y" | `bug` || **feature** | "add support for", "new skill", "new vertical", "would be nice" | `enhancement` |### Step 4: Identify Affected FilesSearch for files related to the issue:```bashgrep -rl "<relevant keyword>" context/ skills/```If the user mentioned a specific file, verify it exists and note therelevant section.Also check if this is already tracked:```bashgrep -i "<keyword>" context/_gaps.yaml```If already tracked, tell the user and ask if they still want to file an issue.### Step 5: Compose the Issue**Title format:** `kumo: <concise description>`Examples:- `kumo: missing Databricks Unity Catalog connector docs`- `kumo: pql-syntax.md lists MODE as valid aggregation`- `kumo: add healthcare/clinical trials vertical`**Body template:**```markdown## Type<gap | bug | feature>## Affected File(s)- `<path>` (line ~N)## Description<Clear description of the issue>## Expected Behavior<What should happen / what info should be there>## Current Behavior<What actually happens / what the doc currently says>## Suggested Fix<If obvious — otherwise "Needs investigation">## Context<Any additional context: SDK version, customer use case, etc.>---*Filed via `/kumo-issue` by @REPORTER*```### Step 6: Create the IssueFirst, capture the reporter's GitHub identity:```bashgh_user=$(gh api user --jq '.login')```Replace `@REPORTER` in the body template with `@$gh_user`.Run:```bashgh issue create \ --repo kumo-ai/kumo-coding-agent \ --title "<title>" \ --label "kumo-coding-agent,<type-label>" \ --assignee "manushmurali-kumo" \ --body "<body>"```Use a heredoc for the body to preserve formatting.If `gh` is not authenticated, tell the user to run `gh auth login -h github.com` firstand provide the exact command to retry.### Step 7: Follow UpAfter the issue is created:1. Print the issue URL2. Tell the user: "Your issue has been filed. A Kumo team member will review it and follow up with you."3. If the type is **gap**, suggest also adding an entry to `context/_gaps.yaml` with status: open4. If the type is **bug** and the fix is obvious, suggest running `/kumo-pr` to fix it directly---> Source: [kumo-ai/kumo-coding-agent](https://github.com/kumo-ai/kumo-coding-agent) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions