Claude Skills by agentskillexchange

Use a practical OpenClaw operations runbook to stabilize long-running deployments, tune coordinator and worker patterns, and apply reusable prompt templates for monitoring, security, and cost control.

Express Kubernetes test steps and assertions in YAML, then execute them against a real cluster before shipping controller or manifest changes.

Use Agent Browser Protocol when an agent needs browser actions to resolve into stable step results, complete with screenshots and surfaced events, instead of racing an always-live browser session.

Adds deterministic SQL analysis, dbt-aware tooling, warehouse metadata, lineage, and test-generation workflows underneath Claude Code, Codex, or terminal-driven agent sessions.

Use Hatchet to queue, retry, pause, resume, observe, and scale long-running agent tasks and background workflows.

Install a multi-runtime SEO skill pack that collects crawl, schema, performance, sitemap, robots, and content evidence before producing audit reports and action plans.

Use prek as a fast pre-commit-compatible hook runner so agents can lint, format, and policy-check repository changes before handing work back.

Dispatch specialized WCAG review agents to inspect code or content before inaccessible patterns ship.

Execute large parallel object-store operations from command files or shell pipelines when agents need speed and repeatability beyond basic aws s3 loops.

Execute repository-stored HTTP request files from the command line so API smoke tests, assertions, and environment-driven checks can run without a GUI client.

Use mcp-server-kubernetes so an MCP-capable agent can inspect, troubleshoot, and manage Kubernetes resources through a configured kubeconfig.

Use Local Deep Research to run private agentic research passes across web, academic, and local document sources with citations and an encrypted knowledge base.

Use SmallCode as a terminal-native coding agent for 8B-35B local models, with budget-managed context, forgiving tool parsing, TODO-driven planning, and patch-based edits.

Use DeerFlow to orchestrate subagents, memory, sandboxes, tools, and skills for supervised research, coding, and creation tasks that take minutes to hours.

Use GSD 2 to break a project into milestones, manage agent context and branches, recover from drift, and let coding agents advance through supervised long-running implementation work.

Use Open Code Review when an agent needs several reviewer personas to inspect a diff, debate findings, and synthesize review output before a human approves, posts, or acts on the review.

Install and operate Oh My OpenAgent as a reusable coding-agent harness for long-running, multi-model development sessions across agent clients.

Install reusable Codex or Claude Code skill bundles for Nature-style manuscript polishing, academic writing, citations, paper reading, response drafting, data handling, slides, and scientific figures.

Use treefmt when an agent needs one repo-level formatting plan across multiple languages instead of stitching formatter commands together ad hoc.

Run just the applicable quality checks on changed files so pre-commit and CI feedback stays fast and targeted.

Use Claude Code Agent Farm when a repo needs many Claude Code workers to run in parallel on bug-fix or best-practice sweeps with coordination, conflict avoidance, and live monitoring.

Create persistent investment-research workspaces where agents process market data, filings, models, charts, and thesis updates over time.

This entry turns WordPress/agent-skills' WP PHPStan guidance into a bounded agent workflow for plugin, theme, and site repositories. The agent inspects the existing PHPStan setup, adds or verifies WordPress-aware stubs, tightens config paths, and fixes or documents only the narrow ignores and baseline changes needed to get useful static-analysis output.

Use borgmatic to drive Borg backup, prune, check, and restore routines from a single declarative config so an agent can supervise backup runbooks instead of stitching raw commands by hand.

Execute PostgreSQL backup, restore, verification, and point-in-time recovery runbooks with explicit repository and WAL handling.

Use Hive as a model-agnostic harness for long-running multi-agent workflows that need state, recovery, observability, human oversight, and business-system tools.

Execute named restic backup profiles with repeatable backup, retention, prune, check, and restore steps instead of hand-running one-off commands.

Dispatch long-running coding work to background agents, check progress later, and pull reviewed outputs back into the main repo flow instead of babysitting one foreground session.

Give coding agents React Native-specific build, upgrade, GitHub Actions, and troubleshooting guidance instead of treating mobile work like generic web development.

Apply reusable refactoring recipes to large codebases so framework upgrades and codemods happen as auditable, reviewable changes.

Build repeatable evaluation experiments for agents and LLM apps with output checks, trajectory scoring, simulators, and trace-based review.

Use Toprank when an agent needs a repeatable Claude Code workflow for Google Ads and SEO audits, with concrete slash commands, account-backed analysis, and optional repo edits instead of one-off marketing prompting.

Run benchmark-style eval suites against models or agents, then inspect scored traces instead of relying on ad hoc chats and gut feel.

Give an agent curated scientific workflows, databases, and domain-specific guidance when general prompting is not reliable enough for research-heavy work.

Use Codemod CLI when an agent needs to scaffold, test, and run a reviewable multi-step migration workflow with approval gates, rather than applying a one-off search-and-replace or browsing the hosted Codemod platform.

Apply standard Python formatters, linters, and type checkers to notebook-heavy repositories without manually converting notebooks to scripts.

Use OpenFang to run packaged autonomous agent workflows on schedules with manifests, dashboards, reporting, and guardrails for sensitive actions.

Use curated Trail of Bits security skills inside Claude Code when the job is auditing, variant hunting, or fix verification rather than generic coding assistance.

Let an agent ingest video, transcribe it, search moments, clip results, and return playable streams without wiring up its own media pipeline.

Expose Shopify Admin API operations to MCP clients for supervised ecommerce catalog, order, customer, and inventory work.

Use OpenHands to run supervised software-engineering agents that inspect repositories, edit code, execute commands, and return reviewable implementation evidence.

Use CloakBrowser as a supervised Playwright/Puppeteer-compatible browser runtime for high-friction browser automation and anti-bot test environments.

Use Warp as a supervised terminal workspace for running Warp Agent or external CLI agents such as Codex, Claude Code, Gemini CLI, and OpenCode with shared shell context.

Use Agent Zero to give an agent an isolated Linux desktop, browser, plugins, skills, and host connector for supervised file, web, and GUI workflows.

Use Cline inside the IDE to let an agent inspect a repository, edit files, run terminal commands, use browser feedback, and pause for approval on risky actions.

Use GitHub Copilot CLI to plan, edit, debug, explain, and automate repository work from a terminal with GitHub context and approval controls.

Lets an agent use Gemini from the terminal to inspect repositories, edit files, run shell commands, and ground work with built-in search and local context.

Turn a planned backlog into markdown tickets, dispatch them through coding agents, and only get pulled back in when a blocker or decision really needs you.

Create disposable E2B cloud sandboxes where agents can execute generated code, install dependencies, collect outputs, and discard state safely.

Uses the WordPress wp-wpcli-and-ops skill to guide an agent through environment-aware WP-CLI work like search-replace, plugin or theme operations, cron inspection, and multisite-safe targeting. It is an operational runbook for guarded WordPress changes, not a plain entry for the WP-CLI product.