batch-issues
01Skill Claude CodeCodex
Batch-process open GitHub issues with parallel agents. Analyzes conflicts, dispatches workers, creates PRs. Usage: /batch-issues [issue numbers] [--dry-run] [--max-parallel N].
Dead code doesn't get patched. Detect abandoned & end-of-life dependencies that SCA tools miss — before they become the next xz-utils.
Skill Claude CodeCodex
Batch-process open GitHub issues with parallel agents. Analyzes conflicts, dispatches workers, creates PRs. Usage: /batch-issues [issue numbers] [--dry-run] [--max-parallel N].
Skill Claude CodeCodex
Safe commit with branch verification and build/test/lint checks.
Skill Claude CodeCodex
Detect and optionally remove dead code in the Go codebase. Usage: /deadcode [fix] [ ].
Skill Claude CodeCodex
Batch diet-trial fuzz testing across OSS projects. Usage: /diet-fuzz [--count N] [--tool trivy,syft,cdxgen] [--max-parallel N] [--projects-file path].
Skill Claude CodeCodex
Run uzomuzo diet on an external OSS project. Usage: /diet-trial [--tool trivy|syft] [--compare] [--no-source] [--no-save].
Skill Claude CodeCodex
OSS Select — evaluate candidate OSS packages with uzomuzo to support adoption decisions.
Skill Claude CodeCodex
Heavyweight plan cross-check: gpt-5.6-sol (Copilot CLI) reviews the plan, Claude and gpt-5.6-sol debate for up to 2 rounds, then the architect subagent rules neutrally (adopt/revise/reconsider). For high-rework-cost plans (billed in GitHub AI Credits, not Premium requests — see Cost section). Usage: /plan-debate [ ].
Skill Claude CodeCodex
Have the local GitHub Copilot CLI (gpt-5.6-sol, a separate-vendor LLM) critique the latest plan-mode plan file before ExitPlanMode — a sanity check. Usage: /plan-review [ ].
Skill Claude CodeCodex
Pre-push diff review by the local GitHub Copilot CLI (gpt-5.6-sol, a separate-vendor LLM). Usage: /review-diff [BASEREF | --cached] (default base=origin/main).
Skill Claude CodeCodex
1-shot to merge-ready (local-only) — Phase A (5-agent local review iteration) → Phase B (push + self-driven Copilot re-review iteration) → Phase C (reply+resolve all threads). One invocation drives a PR from local agent review through Copilot review convergence to merge-ready state. Runs from your own machine; there…
Skill Claude CodeCodex
Deep-dive security risk analysis for a dependency flagged by uzomuzo diet.
Skill Claude CodeCodex
Data-driven deep evaluation of whether a dependency is worth removing.
Skill Claude CodeCodex
Remove a dependency identified by uzomuzo diet — analysis + issue (default) or direct PR.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: