plugins/git/skills/analyze-issue/SKILL.md
Analyze a GitHub issue and create a detailed technical specification
npx skillsauth add NeoLabHQ/context-engineering-kit analyze-issueInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Please analyze GitHub issue #$ARGUMENTS and create a technical specification.
Follow these steps:
Check if the issue is already loaded:
./specs/issues/ folder<number-padded-to-3-digits>-<kebab-case-title>.mdFetch the issue details (if not already loaded):
.claude/commands/load-issues.md to understand how to fetch issue detailsUnderstand the requirements thoroughly
Review related code and project structure
Create a technical specification with the format below
[1-2 paragraphs explaining the problem]
[Detailed technical approach]
Remember to follow our strict TDD principles, KISS approach, and 300-line file limit.
IMPORTANT: After completing your analysis, SAVE the full technical specification to:
./specs/issues/<number-padded-to-3-digits>-<kebab-case-title>.specs.md
For example, for issue #7 with title "Make code review trigger on any *.SQL and .sh file changes", save to:
./specs/issues/007-make-code-review-trigger-on-sql-sh-changes.specs.md
After saving, provide a brief summary to the user confirming:
development
This skill should be used when need prioritize what changed code in repository human must review.
documentation
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.
tools
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.
development
Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed). Use when you want write tests for new logic or increase test coverage.