agentleFS
thefrederiksenthefrederiksen/devthrottle/.claude/skills/read-issues/SKILL.md

read-issues

Skill110 starsChanged 5 days agoMITView on GitHub

List GitHub issues, let the user pick one, and download all content including images so an agent can work on it. Use this when the user wants to browse, review, or select issues to work on.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If a specific issue number is provided in $ARGUMENTS, skip to Step 2.

    line 18
  2. Distinctive:

    If a search query or label filter is provided, use it:

    line 20
  3. Distinctive:

    If no filter is provided, list all open issues:

    line 32
  4. Very specific:

    If $ARGUMENTS contains a specific issue number, use that directly

    line 46
  5. Distinctive:

    Look for patterns like:

    line 68
  6. Distinctive:

    Read the image using the Read tool so Claude can see it

    line 75
  7. Distinctive:

    If no images are found, note that and continue

    line 76
  8. Distinctive:

    After presenting the issue, ask the user:

    line 110
  9. Very specific:

    Always use gh CLI for all GitHub operations

    line 116
  10. Distinctive:

    If the repo has many issues, default to showing only open ones

    line 119

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Read GitHub Issues

Browse, filter, and select GitHub issues, then download all content and images so an agent can fully understand and work on the selected issue.

Input: $ARGUMENTS

Instructions

Step 1: List Issues

If a specific issue number is provided in $ARGUMENTS, skip to Step 2.

If a search query or label filter is provided, use it:

# By label
gh issue list --label "bug" --state open

# By search
gh issue list --search "QUERY" --state open

# All open issues
gh issue list --state open --limit 30

If no filter is provided, list all open issues:

gh issue list --state open --limit 30

Display the issues in a clear format showing:

  • Issue number
  • Title
  • Labels
  • Assignee
  • Created date

Step 2: Select an Issue

  • If $ARGUMENTS contains a specific issue number, use that directly
  • Otherwise, use AskUserQuestion to let the user pick which issue to work on
  • Present the top issues as options with their titles

Step 3: Download Full Issue Content

Once an issue is selected, fetch everything:

# Get full issue details including body
gh issue view ISSUE_NUMBER

# Get all comments
gh issue view ISSUE_NUMBER --comments

# Get issue metadata as JSON for structured parsing
gh issue view ISSUE_NUMBER --json title,body,labels,assignees,comments,state,milestone,createdAt,updatedAt,author

Step 4: Extract and Download Images

  1. Parse the issue body and all comments for image URLs
  2. Look for patterns like:
    • ![alt](https://...) — Markdown images
    • https://github.com/user-attachments/... — GitHub uploaded images
    • https://user-images.githubusercontent.com/... — Legacy GitHub images
  3. For each image found:
    • Download it to a temporary location using curl or Invoke-WebRequest
    • Save to a temp directory like $env:TEMP/gh-issues/ISSUE_NUMBER/
    • Read the image using the Read tool so Claude can see it
  4. If no images are found, note that and continue

Step 5: Present Complete Issue Context

Provide a comprehensive summary including:

## Issue #NUMBER: TITLE

**State:** open/closed
**Labels:** label1, label2
**Assignee:** @username
**Created:** date
**Author:** @username

### Description
[Full issue body]

### Images
[Display all downloaded images]

### Comments (N total)
[All comments with authors and dates]

### Key Requirements
- [Extracted actionable items from the description]
- [Any acceptance criteria mentioned]

### Related Files (if mentioned)
- [Any file paths or code references from the issue]

Step 6: Offer Next Steps

After presenting the issue, ask the user:

  • Would you like to implement this issue? (suggest using /developer-agent NUMBER, or /implementation-loop NUMBER to drive it through Dev+QA to merged)
  • Would you like to assign it to yourself?
  • Would you like to add a comment?

Important Notes

  • Always use gh CLI for all GitHub operations
  • Download images so Claude can actually see and understand visual bug reports
  • Parse both the issue body AND all comments for complete context
  • If the repo has many issues, default to showing only open ones

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.