How to install load-issues
npx skills add https://github.com/neolabhq/context-engineering-kit --skill load-issuesFull instructions (SKILL.md)
Source of truth, from neolabhq/context-engineering-kit.
name: load-issues description: Load all open issues from GitHub and save them as markdown files argument-hint: None required - loads all open issues automatically allowed-tools: Bash(gh issue:), Bash(mkdir:), Write
Load all open issues from the current GitHub repository and save them as markdown files in the ./specs/issues/ directory.
Follow these steps:
-
Use the gh CLI to list all open issues in the current repository:
- Run
gh issue list --limit 100to get all open issues
- Run
-
For each open issue, fetch detailed information:
- Run
gh issue view <number> --json number,title,body,state,createdAt,updatedAt,author,labels,assignees,url - Extract all relevant metadata
- Run
-
Create the issues directory:
- Run
mkdir -p ./specs/issuesto ensure the directory exists
- Run
-
Save each issue as a separate markdown file:
- File naming pattern:
<number-padded-to-3-digits>-<kebab-case-title>.md - Example:
007-make-code-review-trigger-on-sql-sh-changes.md
- File naming pattern:
-
Use the following markdown template for each issue file:
# Issue #<number>: <title>
**Status:** <state>
**Created:** <createdAt>
**Updated:** <updatedAt>
**Author:** <author.name> (@<author.login>)
**URL:** <url>
## Description
<body>
## Labels
<labels or "None">
## Assignees
<assignees or "None">
- After all issues are saved, provide a summary of:
- Total number of issues loaded
- List of created files with their issue numbers and titles
IMPORTANT: Execute all steps in the correct order and ensure all issue data is properly formatted in the markdown files.
Related skills
More from neolabhq/context-engineering-kit and the wider catalog.
memorize
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
multi-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
plan-do-check-act
Iterative PDCA cycle for systematic experimentation and continuous improvement
plan-task
Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task
prompt-engineering
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
propose-hypotheses
Execute complete FPF cycle from hypothesis generation to decision