git:analyze-issue
Analyze a GitHub issue and create a detailed technical specification
Best use case
git:analyze-issue is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Analyze a GitHub issue and create a detailed technical specification
Teams using git:analyze-issue should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/analyze-issue/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How git:analyze-issue Compares
| Feature / Agent | git:analyze-issue | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Analyze a GitHub issue and create a detailed technical specification
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
Please analyze GitHub issue #$ARGUMENTS and create a technical specification. Follow these steps: 1. Check if the issue is already loaded: - Look for the issue file in `./specs/issues/` folder - File naming pattern: `<number-padded-to-3-digits>-<kebab-case-title>.md` - If not found, fetch the issue details from GitHub (see step 2) 2. Fetch the issue details (if not already loaded): - Read `.claude/commands/load-issues.md` to understand how to fetch issue details - Save the issue file following the load-issues.md format 3. Understand the requirements thoroughly 4. Review related code and project structure 5. Create a technical specification with the format below # Technical Specification for Issue #$ARGUMENTS ## Issue Summary - Title: [Issue title from GitHub] - Description: [Brief description from issue] - Labels: [Labels from issue] - Priority: [High/Medium/Low based on issue content] ## Problem Statement [1-2 paragraphs explaining the problem] ## Technical Approach [Detailed technical approach] ## Implementation Plan 1. [Step 1] 2. [Step 2] 3. [Step 3] ## Test Plan 1. Unit Tests: - [test scenario] 2. Component Tests: - [test scenario] 3. Integration Tests: - [test scenario] ## Files to Modify - [file path]: [changes] ## Files to Create - [file path]: [purpose] ## Existing Utilities to Leverage - [utility name/path]: [purpose] ## Success Criteria - [ ] [criterion 1] - [ ] [criterion 2] ## Out of Scope - [item 1] - [item 2] 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: - Issue number and title analyzed - File path where the specification was saved - Key highlights from the specification (2-3 bullet points)
Related Skills
git:load-issues
Load all open issues from GitHub and save them as markdown files
tech-stack:add-typescript-best-practices
Setup TypeScript best practices and code style rules in CLAUDE.md
tdd:write-tests
Systematically add test coverage for all local code changes using specialized review and development agents. Add tests for uncommitted changes (including untracked files), or if everything is commited, then will cover latest commit.
tdd:test-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
tdd:fix-tests
Systematically fix all failing tests after business logic changes or refactoring
sdd:plan
Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task
sdd:implement
Implement a task with automated LLM-as-Judge verification for critical steps
sdd:create-ideas
Generate ideas in one shot using creative sampling
sdd:brainstorm
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
sdd:add-task
creates draft task file in .specs/tasks/draft/ with original user intent
sadd:tree-of-thoughts
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
sadd:subagent-driven-development
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates