update-pr-summary
The update-pr-summary skill regenerates a pull request's title and description based on the complete diff between the base and head branches. Use this when you need to refresh PR documentation to accurately reflect all accumulated changes across a feature branch, rather than just the latest commit message.
git clone --depth 1 https://github.com/fcakyon/claude-codex-settings /tmp/update-pr-summary && cp -r /tmp/update-pr-summary/plugins/github-dev/skills/update-pr-summary ~/.claude/skills/update-pr-summarySKILL.md
# Update PR Summary Update a PR title and description based on the complete changeset. When explicitly invoked with extra text, treat that text as the PR number or URL. ## Process 1. **Fetch PR info** - Use `gh pr view <pr> --json title,body,baseRefName,headRefName`. 2. **Analyze the complete changeset** - Use `git diff <base-branch>...HEAD` to review all committed changes in the branch. - Ignore unstaged changes. - Make the summary describe the full branch diff, not just the latest commit. 3. **Generate the updated summary** - Follow the `create-pr` skill format for title and body. - Start the title with a capital letter and a verb, with no `fix:` or `feat:` prefix. - Use plain language. Avoid jargon and internal shorthand unless an exact command or tool name is needed. - Keep the body to a single short section. - Include 1-2 sentences, a few bullets, and one usage snippet or before/after example when helpful. - Do not include test plans, changed file lists, or line-number links. 4. **Apply the update** - Use `gh pr edit <pr> --title "..." --body "..."`.
Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Manages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle operations, debugging diagnostics, and tier sizing. Supports Kafka, Atlas clusters, S3, HTTPS, and Lambda integrations for streaming data workloads and event processing. NOT for general MongoDB queries or Atlas cluster management. Requires MongoDB MCP Server with Atlas API credentials.
This skill should be used when user asks to "query Azure resources", "list storage accounts", "manage Key Vault secrets", "work with Cosmos DB", "check AKS clusters", "use Azure MCP", or interact with any Azure service.
This skill should be used when user asks to "clean gone branches", "remove deleted local branches", "prune branches removed from remote", or explicitly invokes "clean-gone-branches".
Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
This skill should be used when user asks to "commit these changes", "write commit message", "stage and commit", "create a commit", "commit staged files", or explicitly invokes "commit-staged".
This skill should be used when user asks to "create a PR", "make a pull request", "open PR for this branch", "submit changes as PR", "push and create PR", or explicitly invokes "create-pr".