agentleFS
brayandiazcbrayandiazc/project-starter-template-en-ai/.claude/skills/open-issue/SKILL.md

open-issue

Skill2 starsChanged 2 months agoMITView on GitHub

Drafts and creates a GitHub issue by filling out the right template from .github/ISSUE_TEMPLATE/ based on the type (bug, feature, or task). Use this when the user asks to open/create an issue, report a bug, or record a task/request (e.g. "open an issue for this bug", "create an issue for the new feature", "log this task"). Does not close or comment on existing issues.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a well-formed issue using the repository's template.

    line 7
  2. Very specific:

    Look at the available templates in .github/ISSUE_TEMPLATE/ and pick the one that matches the issue type:

    line 9
  3. Very specific:

    If the type is ambiguous from $ARGUMENTS, ask before choosing.

    line 14
  4. Very specific:

    Read the chosen template to learn its required sections and its front matter (title:, labels:, assignees:).

    line 15
  5. Distinctive:

    Leave as a prompt (don't invent) any data you don't have: versions, environment, screenshots.

    line 21
  6. Very specific:

    Create the issue with the gh CLI following the template, e.g.

    line 23
  7. Very specific:

    Do NOT invent data you don't have (versions, logs, environment) — leave them as prompts, do NOT create a duplicate issue if an identical …

    line 32

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Create a well-formed issue using the repository's template.

  1. Look at the available templates in .github/ISSUE_TEMPLATE/ and pick the one that matches the issue type:
    • bug_report.md — a defect or incorrect behavior.
    • feature_request.md — a new feature or improvement.
    • task.md — an internal work task (chore, refactor, tooling). If the type is ambiguous from $ARGUMENTS, ask before choosing.
  2. Read the chosen template to learn its required sections and its front matter (title:, labels:, assignees:). Respect that front matter.
  3. Fill in each section using the info from $ARGUMENTS and the conversation context:
    • A clear, descriptive title (not generic like "bug").
    • Reproduction steps / expected vs. actual behavior for bugs.
    • Motivation and acceptance criteria for features and tasks.
    • Leave as a prompt (don't invent) any data you don't have: versions, environment, screenshots.
  4. Create the issue with the gh CLI following the template, e.g. gh issue create --title "…" --body "…" --label "…" (or --template <file> for the interactive flow). If there is no remote configured, output the filled issue for the person to paste into GitHub.
  5. Report the URL of the created issue (or the drafted body).

Example: /open-issue login fails with Google on Safari → filled .github/ISSUE_TEMPLATE/bug_report.md, published.

Do NOT invent data you don't have (versions, logs, environment) — leave them as prompts, do NOT create a duplicate issue if an identical one already exists (search first with gh issue list), and do NOT close, edit, or comment on existing issues.

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.