Check Copilot Review Comments. Fetches, adversarially verifies, and resolves Copilot code-review comments on the current PR, then drives an automated re-review loop (re-request → watch → verify → fix → converge). Use when the user asks to "check copilot comments", "what did copilot say", "copilot review", or "/copilot-check".
Execute a GitHub HLR (High-Level Requirement) issue end to end — first-cut breakdown, specialist co-production and synthesis, /plan:tasks → sub-issues, parallel build, QA verification, security gate, and PR. Use when the user runs `/do-hlr <issue#>` or asks to implement/execute an HLR. Runs the full pipeline for substantial HLRs and a lean path for small ones.
Interact with Zendesk API - read tickets, test connection, export data
Reads emails from Gmail account. Use when the user asks to "look at emails", "check emails from [sender]", "read recent emails", or "/read-email". Fetches emails with full body content for analysis.
Checks documentation consistency across the repository. Use when user asks to "check consistency", "are the documents consistent", "is everything aligned", "verify documentation", or "/repo-consistency".
Rewrites git history to permanently remove sensitive data. DESTRUCTIVE OPERATION - rewrites commit history. Use when user asks to "purge secrets from history", "remove sensitive data from git history", "clean git history", or "/repo-security-purge". Requires explicit confirmation.
Scans a repository for sensitive information and security vulnerabilities. Use when the user asks to "scan for security issues", "check for sensitive data", "repo security scan", "make sure this repo has no sensitive information", "security audit", "scan history for secrets", or "/repo-security-scan".
Scans repository for security issues and automatically remediates them. Use when the user asks to "clean up security issues", "fix security problems", "remove sensitive data", "sanitise the repo", or "/repo-security-clean". More aggressive than /repo-security-scan - this skill takes action.