donnfelker/loop-skills

donnfelker/loop-skills

Plugin Claude Code

Plugin marketplace listing 6 plugins: spec-development, dev-team, pr-autopilot, triangulated-code-review, multi-llm-convergence.

donnfelker/loop-skills

Plugin Claude Code

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. Runs as an agent team when the harness supports one, else as coordinated subagents. Usable standalone for any rigorous.

donnfelker/loop-skills

Plugin Claude Code

(beta/experimental) Host-agnostic, N-model variant of multi-llm-convergence. Drives any artifact (plan, PRD, design doc, spec, or implementation diff) to cross-model consensus from Claude, Codex, Gemini, or another capable host by rotating multiple built-in reviewer families through one uniform read-only reviewer…

donnfelker/loop-skills

Plugin Claude Code

Drives any artifact — a 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 the artifact clears the bar (default.

donnfelker/loop-skills

Plugin Claude Code

Autonomously watch a single pull request and drive its review feedback, failing CI checks, and merge conflicts to completion without supervision. Each round it fetches every unaddressed review and comment (from Claude, CodeRabbit, Copilot, other bots, and humans), the PR's check runs, and its mergeability; addresses…

donnfelker/loop-skills

Plugin Claude Code

End-to-end spec workflow: plan-to-tickets (import a structured plan into a task tracker — 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 pull requests and drive each to…

donnfelker/loop-skills

Plugin Claude Code

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 (using the context7 MCP to verify…