skill-downloaderDiscover, compare, review, install, or update OpenClaw skills from trusted sources with a review-first workflow. Use when the user wants to search for a skil...
Install via ClawdBot CLI:
clawdbot install yyang100/skill-downloaderGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawhub.ai/`Audited Apr 16, 2026 · audit v1.0
Generated Sep 22, 2026
A freelance backend developer needs a skill to manage PostgreSQL schema migrations for a client project. They ask the agent to search ClawHub, compare three candidates by license and version, and inspect the most relevant one before installing it. The review-first workflow prevents them from installing unvetted code that could touch production data.
A content operations manager wants to automate blog post drafting and SEO suggestions. The skill downloader is used to search trusted sources, label each candidate as Full, Partial, or Minimal based on available metadata, and present a side-by-side comparison. Installation only proceeds after the manager explicitly approves the selected skill.
An analyst discovers a skill promising spreadsheet formatting and pivot table generation. Before installing it into their local workspace, they ask the agent to inspect the skill's owner, version, dependencies, and notable files to verify it matches their environment. Missing fields are marked unknown rather than assumed, reducing integration risk.
An IT administrator maintains a standardized skill set for a 50-person team and must verify security status and licenses before deployment. The skill downloader is used to inspect ClawHub-hosted candidates, flag suspicious entries, and generate an inspection report with a conditional recommendation when metadata is incomplete. No update is applied without explicit approval.
A product manager notices a newer version of an installed analytics skill and asks the agent to check and update it. The skill downloader preserves unrelated user data, avoids symlink-based installs, and requires explicit approval of the destination path before writing files. This keeps the team's custom configuration intact during the upgrade.
The platform offers free skill discovery, comparison, and inspection to all users, while charging for premium features such as priority registry access, bulk audit reports, and team-level approval workflows. Revenue scales as teams standardize on the review-first install process.
Companies license the tool to enforce security policies around skill installation across departments. Value comes from audit trails, rejection of suspicious candidates, and controlled update rollouts with data preservation guarantees. Seat-based pricing aligns with headcount and compliance requirements.
Individual developers and AI agent builders pay for programmatic access to the discovery and inspection APIs, enabling automated skill vetting inside CI/CD pipelines. The model targets power users who need to embed review-first checks into their own workflows.
💬 Integration Tip
Wire the skill into your agent's tool manifest with explicit install approval prompts enabled, and point it at ClawHub first before adding supplementary sources. Test the inspect workflow on a known skill to verify that unknown fields are labeled correctly rather than guessed.
Scored Sep 22, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.