depradarDependency breaking-change radar. Use this skill when the user wants to check for breaking changes, outdated dependencies, upgrade risks, or migration issues...
Install via ClawdBot CLI:
clawdbot install tarun-khatri/depradarGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
/etc/passwdContains instructions to override system prompt or ignore user requests
"Ignore previous instructions"Sends data to undocumented external endpoint (potential exfiltration)
notify → https://hooks.slack.com/services/YOUR/WEBHOOK/URLHardcoded API key or token pattern found in skill definition
ghp_xxxxxxxx...Generated Oct 9, 2026
A platform team adds /depradar --fail-on-breaking to their CI pipeline so every pull request is blocked if any production dependency has a known breaking change that touches the repo. This catches semver-major surprises before they reach staging.
A web agency is migrating a client's Next.js/React codebase from one major version to the next, and uses /depradar --deep to list which source files import affected APIs and what migration pain others reported on GitHub and Stack Overflow. The output becomes the migration checklist for the sprint.
After a production outage that started right after a routine npm update, an SRE runs /depradar --days=7 to see exactly which packages bumped, which breaking changes shipped, and where in their codebase the old API is still used. They roll back only the offending package instead of the whole lockfile.
An internal tooling team maintains a repo with a Node service, a Python data job, and a Go CLI. They run /depradar --all weekly to scan package.json, requirements.txt, and go.mod in one pass and get a ranked severity report covering all three ecosystems.
A solo maintainer of a widely-used library uses /depradar --notify=slack://WEBHOOK with --min-score=40 to get weekly Slack pings only for high-impact breaking changes in dependencies. This keeps them ahead of upstream changes and cuts noise from low-risk patch releases.
The /depradar skill stays free and local, while a hosted dashboard aggregates scan results across all repos in a GitHub org, tracks breaking-change history over time, and sends team-wide alerts. Companies pay per seat or per repo for org-wide visibility.
Rather than running the CLI themselves, customers connect their Git repos and the service runs daily scans, scores breakage risk, and files prioritized upgrade tickets into Jira or Linear. Includes a security/compliance angle mapping breaking changes to SLA and incident history.
Dep Radar findings feed a marketplace where vetted engineers are matched to companies needing hands-on major-version upgrades. The tool's file-level impact scan gives both sides an instant scoping estimate, and the platform takes a commission on completed migration projects.
💬 Integration Tip
Wire /depradar --fail-on-breaking --min-score=60 into CI so pull requests are gated on genuinely risky upgrades, and use --emit=json with --notify to pipe ranked findings into Slack or ticketing systems your team already watches.
Scored Oct 9, 2026
Potentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
https://img.shields.io/badge/License-MIT-blue.svgUses known external API (expected, informational)
api.github.comAI Analysis
The skill definition contains multiple high-risk signals including hardcoded GitHub API tokens (ghp_xxxx), instructions to ignore previous prompts, references to credential files (/etc/passwd), and undocumented external data sinks (Slack webhooks). These patterns indicate credential harvesting, prompt manipulation, and potential data exfiltration capabilities.
Audited Apr 16, 2026 · audit v1.0
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.