Load Issues
Mirror every open GitHub issue into `./specs/issues/` markdown so agents and humans plan from a stable local backlog.
Overview
load-issues is an agent skill most often used in Build (also Validate scope, Operate iterate) that exports all open GitHub issues into `./specs/issues/` markdown files via the gh CLI.
Install
npx skills add https://github.com/neolabhq/context-engineering-kit --skill load-issuesWhat is this skill?
- Lists up to 100 open issues via `gh issue list` then fetches full JSON per issue
- Creates `./specs/issues/` with `mkdir -p` and one markdown file per issue
- Filename pattern: zero-padded number plus kebab-case title (example `007-make-code-review-trigger-on-sql-sh-changes.md`)
- Structured template: status, dates, author, URL, body, labels, assignees
- Closing summary reports total loaded issues and created filenames
- Fetches open issues with `gh issue list --limit 100`
- Six-step numbered procedure ending in a load summary
Adoption & trust: 513 installs on skills.sh; 1.1k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your backlog lives only on GitHub while agents and specs need local, linkable issue documents in the repo.
Who is it for?
Repos already on GitHub with `gh` authenticated where you maintain specs beside code and want a fresh issue dump before planning.
Skip if: Non-GitHub trackers, closed-issue archives only, or workflows that must not write files into `./specs/issues/`.
When should I use this skill?
Load all open issues from the current GitHub repository and save them as markdown files (no arguments required).
What do I get? / Deliverables
Every open issue becomes a numbered markdown file under `./specs/issues/` with metadata and body text, plus a summary list you can feed into planning skills.
- One markdown file per open issue under `./specs/issues/`
- Summary of total issues loaded and filenames created
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Issue snapshots are a build-phase PM artifact that feeds implementation and spec work without leaving the repo. Bulk export and templated issue files are classic product-management hygiene before coding or agent task breakdown.
Where it fits
Pull open issues into specs before cutting a milestone scope doc from real backlog titles and labels.
Refresh `./specs/issues/` at the start of a build week so writing-plans or task agents cite current issue numbers.
Re-run the export after triage on GitHub so local markdown matches what shipped or what remains open.
How it compares
Use instead of manual copy-paste from the GitHub UI when you need repeatable, agent-readable issue snapshots in-repo.
Common Questions / FAQ
Who is load-issues for?
Solo and indie builders using GitHub who want open issues materialized as markdown for context-engineering, specs, and agent-driven PM in the same repository.
When should I use load-issues?
In Build PM when refreshing the local backlog; in Validate scope when grounding a prototype or milestone against real open work; in Operate iterate when re-syncing issues before the next sprint or agent plan.
Is load-issues safe to install?
It runs `gh issue` commands and writes markdown under `./specs/issues/`; confirm repo and token scope, and review the Security Audits panel on this Prism page before install.
SKILL.md
READMESKILL.md - Load Issues
Load all open issues from the current GitHub repository and save them as markdown files in the `./specs/issues/` directory. Follow these steps: 1. Use the gh CLI to list all open issues in the current repository: - Run `gh issue list --limit 100` to get all open issues 2. 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 3. Create the issues directory: - Run `mkdir -p ./specs/issues` to ensure the directory exists 4. 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` 5. Use the following markdown template for each issue file: ```markdown # 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"> ``` 6. 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.