-
-
Notifications
You must be signed in to change notification settings - Fork 751
feat: add resolving-github-issues skill #137
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
feat: add resolving-github-issues skill #137
Conversation
Systematic workflow for analyzing and implementing fixes for GitHub issues: - Phase-based approach: Fetch → Analyze → Plan → Checkpoint → Implement - Feasibility assessment with complexity rating - Three determination paths: proceed, clarify, or beyond scope - User checkpoint before implementation (never auto-commit) - Safety measures and common mistakes documented 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
WalkthroughAdds a new Markdown skill document at Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes
Poem
Pre-merge checks and finishing touches✅ Passed checks (3 passed)
✨ Finishing touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 0
🧹 Nitpick comments (2)
skills/resolving-github-issues/SKILL.md (2)
68-68: Add language specifiers to fenced code blocks. Lines 68, 82, and 89 contain template code blocks without language identifiers. These should specify a language (e.g.,```textor```diff) to comply with Markdown best practices.Apply this diff to add language specifiers:
- ``` + ```text IMPLEMENTATION PLAN- ``` + ```text REQUIRES CLARIFICATION- ``` + ```text COMPLEXITY WARNINGAlso applies to: 82-82, 89-89
139-156: Use heading syntax for Common Mistakes subsections instead of bold emphasis. Lines 141, 145, 149, and 153 use**bold**formatting for section headers within the Common Mistakes section. Markdown convention and linting rules recommend using heading syntax (e.g.,### Starting implementation without checkpoint) for better semantic structure and accessibility.Apply this diff to convert emphasis to headings:
- **Starting implementation without checkpoint** + ### Starting implementation without checkpoint - **Skipping codebase analysis** + ### Skipping codebase analysis - **Underestimating complexity** + ### Underestimating complexity - **Auto-committing or pushing** + ### Auto-committing or pushing
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
skills/resolving-github-issues/SKILL.md(1 hunks)
🧰 Additional context used
🪛 LanguageTool
skills/resolving-github-issues/SKILL.md
[style] ~101-~101: Consider using a more formal alternative.
Context: ...tinue?" - REQUIRES CLARIFICATION: "Need more info. Want me to comment on the issue?" - BE...
(MORE_INFO)
🪛 markdownlint-cli2 (0.18.1)
skills/resolving-github-issues/SKILL.md
68-68: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
82-82: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
89-89: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
141-141: Emphasis used instead of a heading
(MD036, no-emphasis-as-heading)
145-145: Emphasis used instead of a heading
(MD036, no-emphasis-as-heading)
149-149: Emphasis used instead of a heading
(MD036, no-emphasis-as-heading)
153-153: Emphasis used instead of a heading
(MD036, no-emphasis-as-heading)
🔇 Additional comments (4)
skills/resolving-github-issues/SKILL.md (4)
1-14: Well-structured frontmatter and clear introduction. The description starts with "Use when..." as required and comprehensively summarizes the skill's purpose. The core principle (Fetch → Analyze → Plan → Checkpoint → Implement → Verify) is well articulated, and the "announce at start" instruction sets appropriate context.
29-126: Comprehensive, logical workflow with seven clearly defined phases. Each phase has specific actionable steps (e.g.,gh issue view, git commands), clear outputs, and decision criteria. The progression from Fetch → Analyze → Assess → Determine → Checkpoint → Implement → Complete is well-reasoned and prevents premature implementation.
96-169: User control and safety measures are explicit and well-enforced. Phase 5 mandates approval before proceeding; Phase 7 offers options rather than auto-proceeding; the Safety Measures section explicitly prohibits auto-commit/push (lines 160, 163). The repeated emphasis on checkpoints and approval aligns perfectly with the PR requirement that "the skill never auto-commits."
171-176: Integration references are clear and contextually appropriate. The skill correctly identifies complementary workflows (finishing-a-development-branch, systematic-debugging) and notes the creating-github-issues skill as the inverse workflow. Verify that the referenced skills exist in the codebase by confirming their SKILL.md files are present in the skills directory.
- Add language specifiers (text) to fenced code blocks (lines 68, 82, 89) - Convert bold text to proper ### headings in Common Mistakes section 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
|
@coderabbitai review |
✅ Actions performedReview triggered.
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 0
🧹 Nitpick comments (1)
skills/resolving-github-issues/SKILL.md (1)
98-102: Minor: Inconsistent formality in checkpoint prompts.Line 100 uses the more formal "Shall I continue?" while lines 101–102 use the informal "Want me to..." Consider standardizing to maintain consistent tone:
- REQUIRES CLARIFICATION: "Need more info. Want me to comment on the issue?" + REQUIRES CLARIFICATION: "Need more info. Should I comment on the issue?" - BEYOND SCOPE: "This needs [X]. Want me to document findings on issue?" + BEYOND SCOPE: "This needs [X]. Should I document findings on the issue?"This aligns with the formal "Shall I..." on line 100 and improves the professional tone during user interactions.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
skills/resolving-github-issues/SKILL.md(1 hunks)
🧰 Additional context used
🪛 LanguageTool
skills/resolving-github-issues/SKILL.md
[style] ~101-~101: Consider using a more formal alternative.
Context: ...tinue?" - REQUIRES CLARIFICATION: "Need more info. Want me to comment on the issue?" - BE...
(MORE_INFO)
🔇 Additional comments (7)
skills/resolving-github-issues/SKILL.md (7)
1-4: Well-formatted front matter and clear trigger description.The metadata and description effectively communicate the skill's purpose and when to invoke it. The "Use when..." trigger phrasing is appropriate for a skill document.
6-25: Clear overview with well-defined usage scope.The "When to Use" and "Don't use for" sections prevent scope creep and clearly delineate this skill from related workflows. The announcement guidance is a nice touch for transparency.
27-126: Comprehensive and logically sound phase workflow.The seven-phase structure effectively separates information gathering, decision-making, and execution. The placement of the user checkpoint (Phase 5) before implementation is a strong control point that prevents wasted effort and maintains user agency. The feasibility assessment table is practical and covers key risk dimensions.
127-137: Excellent quick reference table.The table effectively summarizes all seven phases with clear phase names, actions, and outputs. Useful for quick review and as a mental model reminder.
139-155: Well-chosen common mistakes with practical fixes.Each mistake directly reinforces a key safety principle (checkpoint enforcement, thorough analysis, conservative complexity ratings, no auto-commit). The structure of problem → fix is clear and actionable.
157-169: Comprehensive safety measures aligned with workflow phases.The "Never" and "Always" sections effectively reinforce the core principles: user control (no auto-commits, checkpoints), change safety (testing, diffs), and destructive action prevention (force-push restrictions). These directly support the skill's goal of user-centric issue resolution.
171-175: Clear skill integrations with appropriate cross-references.The integration section effectively identifies downstream workflows (
finishing-a-development-branch), conditional-use scenarios (systematic-debuggingfor complex bugs), and complementary opposites (creating-github-issues). This helps users understand how the skill fits into the broader ecosystem.
|
Hi! Claude, in my experience, has no problem resolving github issues. Can you tell me about the problems that led to this skill and your other github-related skill? |
|
It doesn’t evaluate whether the issue is complete and actionable and it
doesn’t always start working in a feature branch. I’ve been using this
skill for a while and it produces superior results.
Regards,
…--Paul
Quality is never an accident; it is always the result of high intention,
sincere effort, intelligent direction, and skillful execution. --William
A. Foster
Paul Holstein
954-536-6678 | www.linkedin.com/in/paulholstein/
***@***.*** | Fort Lauderdale, FL - Asheville, NC
<https://maps.google.com/?q=43+E+Chestnut+St,+Asheville,+NC+28801>
[image: facebook] <https://facebook.com/paulh> [image: linkedin]
<https://us.linkedin.com/in/paulholstein>
On Tue, Dec 2, 2025 at 6:20 PM Jesse Vincent ***@***.***> wrote:
*obra* left a comment (obra/superpowers#137)
<#137 (comment)>
Hi! Claude, in my experience, has no problem resolving github issues. Can
you tell me about the problems that led to this skill and your other
github-related skill?
—
Reply to this email directly, view it on GitHub
<#137 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AKRWOAJ3KDNCRZTGHJNA4OT37YNDZAVCNFSM6AAAAACNZ3AX42VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZTMMBUGM2TMMRQGQ>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
Summary
Change Type
feat:- New feature (MINOR: x.X.0)Breaking Changes
N/A
Test Plan
Context
This skill fills a gap in the superpowers collection - there's currently no workflow for handling GitHub issues. This provides a structured approach that:
finishing-a-development-branchandsystematic-debuggingThe complementary skill
creating-github-issues(for the opposite workflow) will be submitted as a separate PR.🤖 Generated with Claude Code
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.