Generate comprehensive technical specifications from GitHub Pull Requests. Use when users provide a GitHub PR URL and request documentation, technical specs, or change analysis. Analyzes PR commits and diffs using gh CLI and git commands to produce structured documentation covering folder structure, DB schema changes, API definitions, test changes, and dependency updates.
Generate comprehensive technical specifications from GitHub Pull Requests.
This skill analyzes GitHub PRs and generates structured technical documentation. It fetches PR information via gh CLI, analyzes git diffs from local repositories, and produces a detailed specification document covering all aspects of the changes.
Basic usage:
python scripts/generate_spec.py <pr-url>
With custom repository path:
python scripts/generate_spec.py <pr-url> --repo-path /path/to/repo
With custom output directory:
python scripts/generate_spec.py <pr-url> --output-dir /path/to/output
gh CLI installed and authenticated (gh auth login)Note: The script automatically handles cases where:
gh pr view to get PR metadataoutputs/ directory with timestampThe generated technical specification includes:
The script automatically detects:
See detection-patterns.md for detailed pattern information.
To customize detection patterns or output format:
scripts/generate_spec.pygenerate_spec_document() function# Generate spec for a PR
python scripts/generate_spec.py https://github.com/owner/repo/pull/123
# Output: outputs/tech-spec-pr123-20260110-143052.md
Executable code (Python/Bash/etc.) that can be run directly to perform specific operations.
Examples from other skills:
fill_fillable_fields.py, extract_form_field_info.py - utilities for PDF manipulationdocument.py, utilities.py - Python modules for document processingAppropriate for: Python scripts, shell scripts, or any executable code that performs automation, data processing, or specific operations.
Note: Scripts may be executed without loading into context, but can still be read by Codex for patching or environment adjustments.
Documentation and reference material intended to be loaded into context to inform Codex's process and thinking.
Examples from other skills:
communication.md, context_building.md - detailed workflow guidesAppropriate for: In-depth documentation, API references, database schemas, comprehensive guides, or any detailed information that Codex should reference while working.
Files not intended to be loaded into context, but rather used within the output Codex produces.
Examples from other skills:
Appropriate for: Templates, boilerplate code, document templates, images, icons, fonts, or any files meant to be copied or used in the final output.
Not every skill requires all three types of resources.