Claude Skills by agentskillexchange

Capture and inspect file reads, writes, and shell activity from coding agents so developers can audit what actually happened after a session goes sideways.

Use Performance Studio when an MCP-compatible agent needs to parse SQL Server .sqlplan files, surface performance warnings, inspect missing-index suggestions, and turn execution-plan evidence into a reviewable tuning workflow.

Use reg-suit when an agent needs to compare screenshot outputs against a stored baseline and publish a human-reviewable diff report. The skill is for visual regression review loops, not for general frontend tooling, because the agent’s job is to manage the compare, publish, and notify cycle around image snapshots.

Use Nano-PDF when an agent needs to update existing PDF slides or insert matching new slides from plain-language instructions. The workflow is bounded to PDF page edits and deck-consistent slide generation, not general design automation.

Inspect or auto-fix shell scripts to reduce quoting bugs and brittle Bash patterns before they break in CI or production.

Use git-filter-repo when an agent needs to surgically rewrite repository history after a leaked secret, a huge binary commit, or a bad subtree split. The agent analyzes the problem, builds the rewrite command, and leaves a clean follow-up checklist for force-push, clone reset, and downstream cleanup.

ripgrep (rg) is a line-oriented search tool that recursively searches directories for regex patterns while respecting .gitignore rules. Written in Rust, it outperforms grep, ag, and ack on large codebases by significant margins and supports Unicode by default.

Controls Rive (.riv) interactive animations at runtime using @rive-app/canvas-advanced, manages state machine inputs, and synchronizes animation states with application data via the Rive WASM runtime.

Rod is a high-level Go library built directly on the Chrome DevTools Protocol for web automation and scraping. It provides thread-safe, chained-context operations with auto-wait, headless browser debugging, and 100% CI test coverage.

Run Claude Code through Claude Code Router to route coding-agent requests by task, provider, or model while preserving terminal workflows and adding provider-specific transformations.

Use Apple-native inboxes and event surfaces as a gated control plane for local AI work, with sender allowlists, approval prompts, and workspace boundaries.

Pause high-risk coding-agent actions, gather human decisions, and resume or block work with durable approval checkpoints.

Rspack is a blazing-fast JavaScript bundler written in Rust with full webpack API compatibility. It provides drop-in webpack replacement with dramatically faster build times, first-class Module Federation support, and seamless integration with existing webpack plugins and loaders.

Configures and optimizes Ruff Python linter settings using the ruff CLI and pyproject.toml schema. Migrates from Flake8, isort, and Black configurations with automatic rule mapping.

Ultra-fast Python linting and formatting using Ruff CLI with pyproject.toml configuration. Supports auto-fix, import sorting (isort-compatible), and rule selection from 800+ built-in rules.

Generates optimized Ruff configuration from existing Flake8, isort, and Black setups. Migrates pyproject.toml rules with automatic conflict resolution.

Use Nanobot to configure a lightweight local personal agent with model providers, MCP tools, memory, chat channels, search, and gateway deployment paths.

Research, outline, draft, review, and optimize long-form blog posts through a repeatable Claude Code workspace instead of ad hoc chat writing.

Deploy Hermes Agent as a persistent personal agent that learns skills from experience, searches past sessions, schedules automations, and coordinates work across CLI and chat channels.

Guide literature review, experiment tracking, evidence records, result reporting, and paper-writing work through a structured research-agent workflow.

Use claude-code-my-workflow when a research task needs a Claude Code workflow for papers, slides, data analysis, or replication packages with specialist-agent review and verification gates.

Constrain Claude Code, Codex, OpenClaw, and similar agent CLIs inside a kernel-enforced local sandbox with explicit filesystem, network, credential, and snapshot controls.

Give an agent a mailbox it can send from, read from, search, sync locally, and mine for login codes or attachments without hand-driving a normal email client.

Use PyOD's agent skill or MCP server to turn natural-language anomaly detection requests into repeatable detector selection, fitting, scoring, and investigation workflows.

Launch risky agent work inside disposable microVMs when you need stronger isolation, sealed egress, and host-side secret injection instead of direct host access.

Use ai-runbooks to give AI assistants role-specific SOC personas, investigation steps, and incident-response procedures for structured security triage.

Execute natural-language browser regression tests with Playwright, caching, auto-healing, and multi-model assertion verification.

Launch supported coding agents in Docker, collect local metrics and HTTP traces, and compare their runs in a built-in dashboard.

Use Microsoft's Magentic-UI to run supervised browser and local file tasks with an agentic UI, model endpoint, and approval-aware configuration.

Use ToolHive to install, isolate, update, and govern MCP servers so agents connect to a predictable local or Kubernetes-backed tool surface instead of a pile of hand-managed server processes.

Use Docker MCP Gateway to run MCP servers in isolated containers, centralize profiles, secrets, tools, and client connections.

Deploy an internal coding agent that accepts tasks from GitHub, Slack, or Linear, runs them in isolated sandboxes, and opens pull requests automatically.

Use GPT Researcher to plan, gather, source, and assemble cited web or local research reports through a repeatable agent workflow.

Turn Claude Code, OpenCode, or Codex into a metric-driven loop that makes one change at a time, verifies it mechanically, and keeps or reverts automatically.

Analyze a web app's source code, execute real exploit attempts against the running target, and return proof-backed findings before release.

Use Camofox Browser to route agent browser work through an anti-detection browser server with stable element refs, snapshots, cookies, proxies, and session isolation.

Use codex-action when an agent operator wants Codex to run inside GitHub Actions for PR review or scheduled repo work with explicit workflow permissions, prompts, and CI boundaries.

Expose Playwright browser and API automation commands to MCP-capable agents for supervised test workflows.

Use Claude Code as a bounded GitHub Actions worker for PR reviews, issue follow-up, and repository automation that stays inside normal workflow triggers and runner policy.

Turn Claude Code into a command-driven workflow surface for research, planning, implementation, testing, and review instead of steering every step ad hoc.

Wrap Claude Code sessions in a spec, approval, and verification workflow before risky implementation work lands.

Trigger CodeRabbit review passes from an agent and work unresolved PR feedback threads into guided or batch autofix loops.

Put Claude Code, Codex, Gemini, or other supported agent CLIs inside a persistent local sandbox instead of letting them operate directly on the host.

Launch coding agents such as Claude Code, Gemini, or Codex in clean sandboxed sessions with redaction and run observability.

Launch computer-use agents in Linux, macOS, Windows, or Android sandboxes and drive full desktop tasks through screenshots, mouse, keyboard, and shell controls.

Use Open Deep Research when an agent should run a configurable research job that searches, compresses, synthesizes, and writes a cited report across multiple model and search backends.

Turn Claude Code into a structured project workflow that captures context, plans work, and executes implementation in reviewable tracks.

Self-host AutoGPT to build, test, deploy, and operate continuous AI agents for repeatable multi-step workflows.

Lets an agent execute OpenAPI or API Blueprint contract checks against a running service so spec drift is caught before release.

Use CAI to run research and bug-bounty-oriented security agents with model routing, tool integrations, tracing, MCP support, and human oversight.