agentleFS
Muriel-SalvanMuriel-Salvan/x_aeon_agents/skills/analyzing-github-issue/SKILL.md

analyzing-github-issue

Skill2 starsChanged 2 months agoBSD-3-ClauseView on GitHub

Analyzes requirements described in a GitHub issue. What this does is read the GitHub issue content and devise an implementation plan. Use this when the user is asking you to analyze a GitHub issue or get requirements from it. Use this skill also in Plan mode.

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. About 0 are common, 15 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈15

    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. Distinctive:

    When implementing a GitHub issue, follow those steps.

    line 14
  2. Distinctive:

    Before executing anything, create a checklist named analyzing-github-issue Execution Checklist with all steps of these instructions.

    line 18
  3. Distinctive:

    After completing each step of these instructions, mark the item in the analyzing-github-issue Execution Checklist as completed.

    line 20
  4. Distinctive:

    Do not skip any item.

    line 21
  5. Distinctive:

    If an item cannot be executed, explicitly explain why.

    line 22
  6. Distinctive:

    Never mark the task as completed while any item from the analyzing-github-issue Execution Checklist remains open.

    line 23
  7. Distinctive:

    Always tell the user "SKILL: I am implementing a GitHub issue" to inform the user that you are running this skill.

    line 27
  8. Very specific:

    Always use agent: ask_followup_question to ask the user which GitHub issue should be analyzed, unless the user already gave you this …

    line 31
  9. Very specific:

    Always use cli: ruby {skill_path}/scripts/issue_details {issue_number} to retrieve all the details of this GitHub issue.

    line 36
  10. Distinctive:

    Always analyze the current code structure and content to understand how the GitHub issue should be implemented.

    line 53
  11. Distinctive:

    Always analyze all the rules that you should adhere to when implementing a task.

    line 54
  12. Distinctive:

    Before declaring the task complete:

    line 58
  13. Distinctive:

    If any step was not executed, execute it now.

    line 62
  14. Very specific:

    Always use it every time another skill specifically mentions skill: analyzing-github-issue.

    line 67
  15. Distinctive:

    Always use it every time the user asks you to analyze a given GitHub issue.

    line 68
  16. Distinctive:

    Always use it every time you need to analyze a GitHub issue to gather requirements.

    line 69
  17. Distinctive:

    If the user asked you to analyze a GitHub issue without specifying the number, this skill should perform the following commands:

    line 77
  18. Distinctive:

    If the user asked you to analyze the GitHub issue number 42, this skill should perform the following commands:

    line 85

≈ “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

Implementing a GitHub issue

Sequential steps to be followed when using this skill

When implementing a GitHub issue, follow those steps.

Create the analyzing-github-issue Execution Checklist (MANDATORY)

  • Before executing anything, create a checklist named analyzing-github-issue Execution Checklist with all steps of these instructions.
  • The analyzing-github-issue Execution Checklist must include all numbered steps explicitly.
  • After completing each step of these instructions, mark the item in the analyzing-github-issue Execution Checklist as completed.
  • Do not skip any item.
  • If an item cannot be executed, explicitly explain why.
  • Never mark the task as completed while any item from the analyzing-github-issue Execution Checklist remains open.

1. Inform the user

  • Always tell the user "SKILL: I am implementing a GitHub issue" to inform the user that you are running this skill.

2. Get issue number (can be done during Plan mode)

  • Always use agent: ask_followup_question to ask the user which GitHub issue should be analyzed, unless the user already gave you this information in the prompt.

3. Get issue requirements (can be done during Plan mode)

  • Find this skill directory path, later referenced as {skill_path}.
  • Always use cli: ruby {skill_path}/scripts/issue_details {issue_number} to retrieve all the details of this GitHub issue.

Example with expected output as JSON:

ruby .cline/skills/analyzing-github-issue/scripts/issue_details 29
# => {"body":"# This is the GitHub issue body ...","comments":[],"labels":[],"number":29,"state":"OPEN","title":"This is the GitHub issue title","url":"https://github.com/my-user/my-repo/issues/29"}

Example of an error case with a non-existing GitHub issue:

ruby .cline/skills/analyzing-github-issue/scripts/issue_details 29
# GraphQL: Could not resolve to an issue or pull request with the number of 29. (repository.issue)
# .cline/skills/analyzing-github-issue/scripts/issue_details:9:in 'Kernel#system': Command failed with exit 1: gh issue view 29 --json=number,title,body,comments,labels,state,url (RuntimeError)
#       from .cline/skills/analyzing-github-issue/scripts/issue_details:9:in '<main>'

4. Come up with an implementation plan (can be done during Plan mode)

  • Always analyze the current code structure and content to understand how the GitHub issue should be implemented.
  • Always analyze all the rules that you should adhere to when implementing a task.

Final Verification (MANDATORY)

Before declaring the task complete:

  • Re-list all numbered steps from the analyzing-github-issue Execution Checklist.
  • Confirm each one was executed.
  • If any step was not executed, execute it now.

When to use it

  • This skill can be used when in Plan mode.
  • Always use it every time another skill specifically mentions skill: analyzing-github-issue.
  • Always use it every time the user asks you to analyze a given GitHub issue.
  • Always use it every time you need to analyze a GitHub issue to gather requirements.

Usage and code examples

Those examples are given for a Linux environment. Adapt them if you are running in a Windows environment.

When asked to analyze a GitHub issue

If the user asked you to analyze a GitHub issue without specifying the number, this skill should perform the following commands:

# Use agent tool ask_followup_question to get the GitHub issue number from the user
ruby .cline/skills/analyzing-github-issue/scripts/issue_details 42

When asked to analyze the GitHub issue number 42

If the user asked you to analyze the GitHub issue number 42, this skill should perform the following commands:

ruby .cline/skills/analyzing-github-issue/scripts/issue_details 42

Example of implementation plan

### Current Code Structure

- `lib/my_class.rb`: Has the `debug_mode` accessor

### Implementation Plan

__Files to modify:__
- `lib/my_class.rb`
- `README.md`
- *.erb

__Changes:__

1. Create a `Logger` class within `lib/utils/logger.rb` that logs output.

2. Modify the `lib/my_class.rb` to:

   - Move existing debug logic to Logger`

### Expected Behavior

- `DEBUG=1 bundle exec bin/run` → debug mode enabled and logs visible in stdout
- `bundle exec bin/run` → debug mode disabled (current behavior)

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.