shell-check
Run shellcheck to lint shell scripts for common issues and best practices
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Run shellcheck to lint shell scripts for common issues and best practices
A skill to analyze log files for errors and warnings using a Python script.
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically
Nested lingtai-dev-guide reference for diagnosing LingTai failures: agent process state, OOM/crashes, avatar spawn issues, post-molt memory loss, mail delivery, scheduled messages, tool timeouts, and escalation.
Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration
Protocol router for reporting bugs, stale info, missing capabilities, or design issues you spot in any LingTai skill, capability, preset, or system behavior. Enter through this router, then load the one nested reference you need — evidence-checklist (when to report, what evidence to collect, secret hygiene), report-template (the report body/title structure), or filing-flow (human consent, the gh CLI path, and the paste-ready fallback). You always assemble a structured report and ask the human for permission before filing.
Check your branch before opening a PR (lint, format, tests, title)
Run Semgrep static analysis scans and create custom detection rules. Use when asked to scan code with Semgrep, find security vulnerabilities, write custom YAML rules, or detect specific bug patterns. IMPORTANT: Also use this skill when users ask to 'scan for bugs', 'check code quality', 'find vulnerabilities', 'static analysis', 'lint for security', 'audit this code', or want to enforce coding standards — even if they don't mention Semgrep by name. Semgrep is the right tool for pattern-based code scanning across 30+ languages.
Triage stale GitHub PRs. Use when asked to review old, inactive, least-recently-updated, obsolete, or closeable pull requests, comment with a recommendation, and close PRs that are clearly no longer useful.
Use when code is working and ready for a final human-review pass.