Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Interact with GitHub issues - create, list, and view issues.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | — | — |
| case-17 | ✗→✓ | ▲ Improved | — | — |
| case-22 | ✗→✓ | ▲ Improved | — | — |
| case-06 | ✗→✓ | ▲ Improved | — | — |
| case-05 | ✗→✓ | ▲ Improved | — | — |
Interact with GitHub issues - create, list, and view issues.
This command helps you work with GitHub issues using the gh CLI.
Use AskUserQuestion to ask what the user wants to do:
Question:
description: "Open a new issue with title, body, and optional labels"
description: "View open issues in the current repository"
description: "See details of a specific issue by number"
Use AskUserQuestion to get the issue title:
Question:
description: "Enter a concise title like 'Login button unresponsive' or 'Add dark mode support'"
Title guidelines:
If the user provides a long title, help them shorten it and move the details to the body.
Use AskUserQuestion to gather the issue body content:
Question 1 - Issue type context:
description: "Something broken that needs fixing"
description: "Improvement to existing functionality"
description: "Brand new functionality"
description: "General work item or chore"
Question 2 - Description:
description: "Provide context, steps, examples, and any relevant information"
The user will select "Other" here to provide their full description.
Description guidelines:
Question 3 - For bugs, ask about reproduction: If issue type is "Bug", use AskUserQuestion:
description: "I'll describe how to reproduce the issue"
description: "The bug is intermittent or hard to reproduce"
Question 4 - Expected vs actual behavior (for bugs): If issue type is "Bug", use AskUserQuestion:
description: "I'll explain expected vs actual behavior"
Use AskUserQuestion to select labels:
description: "Something isn't working"
description: "New feature or request"
description: "Improvements to docs"
description: "Good for newcomers"
Construct the issue body based on the type:
For Bug reports:
## Description
[User's description]
## Steps to Reproduce
[User's reproduction steps or "Not easily reproducible"]
## Expected Behavior
[What should happen]
## Actual Behavior
[What actually happens]For Feature requests/Enhancements:
## Description
[User's description]
## Use Case
[Why this would be useful]For Tasks/Other:
## Description
[User's description]Run the gh command to create the issue:
bashgh issue create --title "[title]" --body "[constructed body]" --label "[labels]"
Report the issue URL back to the user.
Use AskUserQuestion to determine filtering:
description: "Show all open issues"
description: "Issues assigned to the current user"
description: "Issues I created"
description: "Filter by a label"
If "With specific label" selected, use AskUserQuestion:
description: "Bug reports"
description: "Feature requests"
description: "Documentation issues"
Run the appropriate gh command:
gh issue listgh issue list --assignee @megh issue list --author @megh issue list --label "[label]"Display the results in a clean format.
Use AskUserQuestion:
description: "I'll type the issue number"
Run: gh issue view [number]
Display the issue details including title, body, labels, assignees, and comments.
If gh command fails:
gh auth statusgh auth loginbash gh issue create --title "Title" --body "$(cat <<'EOF' Body content here EOF )"
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 17 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +23 percentage points is the difference between those two pass rates over the 17 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.