Explorar skills

Code quality check: linting, complexity analysis, duplication detection, and dead code identification. Detects project linting config, runs appropriate tools, and creates a structured GitHub issue.

Use when user requests autonomous operation across multiple issues. Orchestrates parallel workers using Task tool, monitors with TaskOutput, handles SLEEP/WAKE cycles, and works until scope is complete without user intervention.

Install the full four-role agent-team pattern (spec → plan → impl → review) into the current repo as one unified setup. Use when the user wants an end-to-end agent pipeline driven by a single issue label, or types /install-agent-team.

Generate benchmark tasks from git history of the current or specified repository. Use this skill when the user wants to: - Create benchmark tasks based on real problems their team already solved (closed PRs, past commits, resolved issues) - Mine git history for good evaluation candidates - Turn a commit range or set of PRs into a NASDE benchmark - Build a regression test suite from their team's ac

Use during all development - no TODOs, no FIXMEs, no "we'll add this later"; do it now or get explicit deferral permission

Use when running git push or diagnosing why a push failed. Especially when output mixes SSH transport with hook output (lefthook, husky, pre-commit), errors include "Permission denied (publickey)" or "rejected/non-fast-forward", a pre-push hook fails, or about to debug SSH with `-v`.

Use when implementing GitHub issues for skill or plugin development through TDD-governed phases with iterative planning, implementation, and review loops. Use this whenever the issue involves SKILL.md files, agent prompts, hook scripts, or plugin workflows.

Git hygiene: clean up merged branches, prune stale remotes, and verify repository state.

Defines behavior protocol for spawned worker agents. Injected into worker prompts. Covers startup, progress reporting, exit conditions, and handover preparation.

Use when working with non-admin groups that have pynchy_repo_access, understanding git worktree isolation, diagnosing uncommitted work left in a worktree after a service restart, or understanding post-run merge behavior.

Triage open GitHub issues and recommend what to work on next. Builds a dependency graph from issue bodies, detects circular dependencies, ranks unblocked issues by weighted scoring (blocks-others, priority, type, age, milestone), and presents top candidates for interactive selection. Triggers: what should I work on next, triage backlog, next issue, pick next task, recommend issue, prioritize issue

Use when managing the pynchy service on the server — deploying changes, observing logs, checking service status, restarting the service, setting up GitHub auth, rebuilding the agent container, or running any commands on pynchy-server via SSH. Also use when interacting with the LiteLLM proxy — investigating failed requests, model routing errors, spend tracking, health checks, API gateway diagnostic