multi-agent-skill-syncAudit and converge local skills across Codex, Claude, OpenClaw, OpenCode, workspace skills, and shared agent libraries; compute a hygiene score, classify sha...
Install via ClawdBot CLI:
clawdbot install donttal/multi-agent-skill-syncGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/LearnPrompt/skill-syncAudited Apr 17, 2026 · audit v1.0
Generated Oct 3, 2026
A platform team supports engineers who use Codex, Claude, OpenClaw, and OpenCode simultaneously. Skill Sync audits every host root, scores skill hygiene, and replaces duplicate copies with symlinks to a single canonical source. This eliminates version drift and makes onboarding reproducible.
An AI consultant finishes an engagement on a Mac Studio and must replicate the exact skill layout on a Linux workstation. Using --export-manifest and --import-manifest, they transfer the topology and restore backups for any conflicts. The client's agent environment works identically on first boot.
A security-conscious engineering org needs to audit duplicate and mixed-format skills that may have been installed from untrusted sources. Skill Sync's status model identifies shared, compatible, and mixed skills, while --diff highlights content differences. Risk teams can then approve or quarantine skills chain-wide.
A developer experimenting with dozens of AI agent skills creates conflicting installs across Codex, Claude, and shared roots. Skill Sync scans and recommends safe dedupe actions, moving originals into timestamped backups. If anything breaks, --restore latest --apply rolls back the last run.
A DevEx team bakes Skill Sync into container provisioning so every ephemeral dev environment starts with a converged, symlinked skill layout. --adopt-root agents --apply runs during image build, and --status shared,specific verifies the result. Developers get the same skills regardless of host.
The core CLI remains open source and installable via pip, while teams pay for a hosted dashboard that aggregates hygiene scores, tracks skill lineage, and alerts on drift across many machines. This mirrors successful developer-tool open-core models without locking the CLI.
Large organizations pay for a support contract that includes security-reviewed manifests, audit exports, and guaranteed SLAs for the dedupe and restore workflows. The add-on targets compliance-heavy industries that need documented change control for agent skills.
A cloud service hosts canonical skill packages and lets distributed teams pull a verified, symlinked layout onto any machine using the same manifest format. The service becomes the source of truth for an organization's agent skills, with built-in versioning and rollback.
💬 Integration Tip
Always run the scan-only command first and review --status compatible,mixed before any --apply; pair --adopt-root with --export-manifest for cross-machine reproducibility. Add --restore latest --apply to your runbook as an immediate rollback step after any convergence.
Scored Oct 3, 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.