loop-skills

End-to-end spec workflow. Bundles plan-to-tickets (import a structured plan into ClickUp, Linear, Jira, Asana, Notion, GitHub Projects, or a markdown fallback as a ticket hierarchy) and implement-full-spec (turn a parent ticket with N actionable subtasks into N stacked PRs and drive each to merge-ready through multi-round bot and human review). Depends on the dev-team and pr-autopilot plugins — install all three together.

Drive a single unit of work — one spec, ticket, finding, or change request — from spec to a committed, reviewed result with a dev team of coordinating agents: Dev to QA to Reviewer in a bounded cycle. Usable standalone, or as the per-subtask engine behind implement-full-spec.

Autonomously watch a single pull request and drive its review feedback to completion — each round fetch unaddressed reviews and comments from bots and humans, address the actionable ones, commit, push, reply/resolve threads, and re-request review, looping until a quiet round or a safety cap. Includes a --single-pass mode (one autonomous round, no loop). Owns the shared pr-review-mechanics reference.

Triangulated multi-reviewer code review orchestrator. Borrows from research methodology — checks each finding against multiple independent reviewers (comprehensive, security, codex, codex adversarial) to reduce blind spots, then runs a QA analyst pass that substantiates every finding (verifying any third-party library claims via the context7 MCP) and demotes unsubstantiated ones into a dedicated 'Invalidated Findings' section of the prioritized, timestamped report.

Drives any artifact (plan, PRD, design doc, spec, or implementation diff) to convergence by alternating two genuinely different LLM reviewers — a Codex reviewer and an independent Claude review subagent — applying each round's findings and looping until both independently agree it clears the bar. Grounds offline reviewers in local source-of-truth clones, runs a liveness watchdog so a silent reviewer can't hang the loop, and commits per round for an auditable trail.

(beta/experimental) Host-agnostic, N-model variant of multi-llm-convergence. Runs from Claude, Codex, Gemini, or another capable host and rotates multiple built-in reviewer families through one uniform read-only reviewer protocol. Keeps the original's guarantees: local-only grounding, liveness supervision, per-round commits, hard preflight for each selected family, and a full clean-cycle convergence rule. No user-provided command adapters. Ships parallel to multi-llm-convergence (untouched) until promotion.