KS
Killer-Skills

github-issue — how to use github-issue how to use github-issue, github-issue setup guide, github-issue alternative, github-issue vs validator monitor, creating focused github issues, beacon chain validator performance, github-issue install, github-issue for developers, github-issue for ai agents, validator monitor for beacon chain

v1.0.0
GitHub

About this Skill

Perfect for Developer Agents needing automated GitHub issue creation and beacon chain monitoring. github-issue is a lightweight validator monitor for the beacon chain, comprising an indexer, API, Telegram bot, and mini-app for real-time performance tracking.

Features

Creates single, clear-goal GitHub issues for external contributors
Generates epics with sub-issues for multi-layered work requests
Monitors validator performance on the beacon chain using an indexer and API
Provides real-time alerts and rewards via a Telegram bot and mini-app
Enforces scope boundaries to prevent feature creep
Utilizes a decision flow to determine issue creation

# Core Topics

NodeSentinel NodeSentinel
[0]
[0]
Updated: 3/7/2026

Quality Score

Top 5%
39
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add NodeSentinel/beacon-chain-validators-monitor/github-issue

Agent Capability Analysis

The github-issue MCP Server by NodeSentinel is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use github-issue, github-issue setup guide, github-issue alternative.

Ideal Agent Persona

Perfect for Developer Agents needing automated GitHub issue creation and beacon chain monitoring.

Core Value

Empowers agents to create focused, self-contained GitHub issues with real-time alerts and rewards, utilizing decision flows and scope boundaries to ensure clear goals and minimal context, while monitoring validator performance on the beacon chain via GitHub APIs and protocols.

Capabilities Granted for github-issue MCP Server

Automating GitHub issue creation for external contributors
Monitoring validator performance on the beacon chain
Generating epic issues with sub-issues for complex features
Creating single issues for clear, self-contained goals

! Prerequisites & Limits

  • Requires GitHub API access
  • Limited to creating issues for requested features only
  • Dependent on beacon chain data for validator performance monitoring
Project
SKILL.md
5.2 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Creating GitHub Issues

Create focused, self-contained GitHub issues that an external contributor could implement without additional context.

Decision Flow

Work requested
    │
    ▼
Single clear goal? ──yes──> Create single issue
    │
    no
    │
    ▼
Spans multiple layers? ──yes──> Create epic with sub-issues

Scope Boundaries (CRITICAL)

Stick to what was requested. Create issues ONLY for the requested feature. Do NOT expand into adjacent features.

When Feature X depends on Feature Y:

  • Create minimal stub for Y (just enough to unblock X)
  • ASK user if they want a separate epic for Y

ASK before proceeding when:

  1. Adjacent features detected
  2. Ambiguous boundaries
  3. Multiple interpretations possible
  4. Feature seems too large (10+ issues)

Workflow

1. Clarify Scope

ASK user about boundaries before drafting.

2. Review Preference

Use AskUserQuestion:

  • "Review first" (Recommended): Create preview file in scratchpad for feedback before creating issues
  • "Create directly": Create issues immediately with needs-review label added via gh issue edit <num> --add-label "needs-review" after creation

3. Create Issues (Single Script)

Use GraphQL API for reliable creation (see ./graphql-api.md).

CRITICAL: Execute ALL operations in a SINGLE bash script to minimize permission prompts. This includes:

  1. Getting repo info
  2. Getting repo ID
  3. Creating epic
  4. Creating all sub-issues
  5. Linking sub-issues to epic
  6. Adding labels
bash
1#!/bin/bash 2# ALL OPERATIONS IN ONE SCRIPT - Single permission prompt 3 4set -e 5 6# 1. Get repo info 7REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner) 8OWNER=$(echo "$REPO" | cut -d'/' -f1) 9NAME=$(echo "$REPO" | cut -d'/' -f2) 10 11# 2. Get repo ID 12REPO_ID=$(gh api graphql -f query="query { repository(owner: \"$OWNER\", name: \"$NAME\") { id } }" -q '.data.repository.id') 13 14# 3. Create epic 15EPIC=$(gh api graphql -f query=' 16mutation($repoId: ID!, $title: String!, $body: String!) { 17 createIssue(input: { repositoryId: $repoId, title: $title, body: $body }) { 18 issue { number id } 19 } 20}' -f repoId="$REPO_ID" -f title="[Context] Epic: Feature Name" -f body="$(cat <<'EOF' 21## Objective 22Epic description here... 23 24## Sub-Issues 25- [ ] Sub-issue 1 26- [ ] Sub-issue 2 27EOF 28)") 29EPIC_NUM=$(echo "$EPIC" | jq -r '.data.createIssue.issue.number') 30EPIC_ID=$(echo "$EPIC" | jq -r '.data.createIssue.issue.id') 31 32# 4. Create sub-issues 33ISSUE1=$(gh api graphql -f query=' 34mutation($repoId: ID!, $title: String!, $body: String!) { 35 createIssue(input: { repositoryId: $repoId, title: $title, body: $body }) { 36 issue { number id } 37 } 38}' -f repoId="$REPO_ID" -f title="[Context] Sub-issue 1" -f body="Issue body...") 39ISSUE1_NUM=$(echo "$ISSUE1" | jq -r '.data.createIssue.issue.number') 40ISSUE1_ID=$(echo "$ISSUE1" | jq -r '.data.createIssue.issue.id') 41 42# Continue for all sub-issues... 43 44# 5. Link sub-issues (attempt - may not be available on all repos) 45gh api graphql \ 46 -H "GraphQL-Features: sub_issues" \ 47 -f query='mutation($parentId: ID!, $childId: ID!) { 48 addSubIssue(input: { issueId: $parentId, subIssueId: $childId }) { 49 issue { number } 50 } 51 }' \ 52 -f parentId="$EPIC_ID" \ 53 -f childId="$ISSUE1_ID" 2>/dev/null || true 54 55# 6. Add labels 56for issue in $EPIC_NUM $ISSUE1_NUM; do 57 gh issue edit "$issue" --add-label "needs-review" --repo "$REPO" 2>/dev/null || true 58done 59 60echo "Created Epic #$EPIC_NUM with sub-issues"

Issue Structure

Title Convention

Issue titles MUST include context prefix from the user's request. Extract the context (e.g., "Seller", "Buyer", "Payments") and prefix all issues:

[Context] Issue title

Examples:

  • User asks: "create issues for the Seller" → [Seller] Seller Registration, [Seller] Create Product Listing
  • User asks: "create issues for checkout flow" → [Checkout] Cart Summary, [Checkout] Payment Processing
  • Epic title: [Seller] Epic: Seller Experience

Required Sections

Every issue MUST include:

SectionPurpose
ObjectiveSingle, clear goal (one sentence)
ScopeWhat's included
Acceptance CriteriaCheckboxes for "done"
Out of ScopeExplicit boundaries
How to TestVerification steps

Optional: Examples, Technical Notes, Dependencies, Related

Common Mistakes

MistakeFix
Vague objectiveSpecific goal with measurable outcome
Missing acceptance criteriaAdd checkboxes
Expanding into adjacent featuresASK if separate epic needed
Using only labels to link issuesUse GraphQL addSubIssue

Reference Files

Load these on-demand as needed:

  • ./graphql-api.md - GraphQL mutations for creating issues and sub-issues (RECOMMENDED)
  • ./cli-reference.md - Quick gh CLI commands reference
  • ./templates.md - Issue body templates and examples

Related Skills

Looking for an alternative to github-issue or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication