Menu
toolkit for llm-friendly interaction with GitHub pull requests; using this skill the LLM can fetch PR data and analyze it
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a working Figma MCP server connection.
Retrieve Linear task context via Linear MCP for implementation work. Use when the developer needs requirements, scope, or acceptance criteria from a ticket.
Analyze QA regression impact for Tonkeeper Android, iOS, or Web by comparing the current branch with the relevant release branch, reviewing the platform regress.txt, and recommending test blocks, missing coverage, extra checks, and a generated TXT test collection.
toolkit to sync and search TON documentation from git@github.com:ton-org/docs.git; use when answering TON-related questions or referencing TON docs
| name | pr |
| description | toolkit for llm-friendly interaction with GitHub pull requests; using this skill the LLM can fetch PR data and analyze it |
| metadata | {"short-description":"LLM-friendly interactions with GitHub PRs"} |
Use this skill to fetch PR metadata and file diffs into LLM-friendly Markdown files.
gh is installed and gh auth login has been completed.python3 .codex/skills/pr/scripts/get_pr_data.py ensure-setup returns zero exit code.Fetch a PR by number:
python3 .codex/skills/pr/scripts/get_pr_data.py get-pr 354
Fetch from a specific repo:
python3 .codex/skills/pr/scripts/get_pr_data.py get-pr 354 --repo tonkeeper/ios_private
Write to a custom output directory:
python3 .codex/skills/pr/scripts/get_pr_data.py get-pr 354 --output /tmp/pr-354
.context/tasks/<PR_NUMBER>/ (relative to repo root)0.md, 1.md, ...) with keys as headings and the patch field in a diff code block.sha.json with base commit metadata is written to the same directory..env is loaded from the repo root if present.