rc-review-workflow

Solid

Runs a review→fix→re-review loop over a PRD slug implementation by driving the Claude Code Workflow tool — fanning out multiple review lenses in parallel, synthesizing their findings into a reviews-NNN round, fixing the valid issues, and repeating until clean or a round cap. Use when the user wants an automated multi-lens review-and-remediate loop on a slug, orchestrated by Claude. Do not use for a single-pass review (use rc-code-review or rc-review-round), to fix an existing round (use rc-fix-reviews), or on non–Claude Code hosts (run the review skills manually).

AI & Automation 19 stars 1 forks Updated 2 weeks ago MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
43
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Review → fix → re-review as a Claude Workflow Drive an automated **review → fix → re-review** loop over a feature slug's implementation using the Claude Code **`Workflow`** tool. Each round fans out several review lenses in parallel, synthesizes their findings into a `reviews-NNN/` round (the `rc-review-round` format), fixes the valid issues (the `rc-fix-reviews` contract), and repeats until a round surfaces **no new issues** or a round cap is hit. **Invoking this skill is the explicit opt-in to call the `Workflow` tool.** This is **Claude Code only** — the `Workflow` tool does not exist in other agents. On other hosts, run the loop by hand: `/rc-review-round` then `/rc-fix-reviews`, repeated. ## When to stop and defer - **No `Workflow` tool available** (non–Claude Code host) → stop and tell the user to run `/rc-review-round` + `/rc-fix-reviews` manually. Do not emulate the loop by hand here. - **Slug not implemented** (`.rc/tasks/<slug>/` missing, or no task implementation to review) → stop; nothing to review yet. ## Phase 1 — Resolve the slug Take `<slug>` from the argument and confirm `.rc/tasks/<slug>/` exists with its PRD/TechSpec and the implemented change set to review. The loop reviews the implementation of that slug, not an arbitrary diff. ## Phase 2 — Confirm parameters Confirm with the user before launching (the loop edits the working tree during fix rounds): - **Round cap** — max rounds (default **3**); the loop also stops early when a round finds zero ...

Details

Author
rodolfochicone
Repository
rodolfochicone/rc-project
Created
1 months ago
Last Updated
2 weeks ago
Language
JavaScript
License
MIT

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

rc-tasks-workflow

Executes the tasks of a RC feature slug by driving the Claude Code Workflow tool — one subagent per task, in dependency order, each implementing and verifying its task and returning structured test evidence. Use when the user wants to run a slug's task_NN.md files as a Claude-orchestrated workflow on a Claude Code host. Do not use to author tasks (use rc-create-tasks), to execute a single task in isolation (use rc-execute-task), or on non–Claude Code hosts (run each task via rc-execute-task in dependency order).

19 Updated 2 weeks ago
rodolfochicone
Code & Development Solid

rc-review-round

Performs a comprehensive code review of a PRD implementation and generates a review round directory with issue files compatible with rc-fix-reviews. Use when reviewing implemented PRD tasks, creating a manual review round without an external provider, or performing a quality audit of code changes. Do not use for fetching reviews from external providers, fixing existing review issues, executing PRD tasks, or editing source code.

19 Updated 2 weeks ago
rodolfochicone
Code & Development Solid

review-loop

Bounded review-apply-resolve convergence loop for a GitHub PR (draft PRs are fine). Runs up to N=5 iterations of pr-reviewer → implement-suggestion (--resolve-all) → polish simplify, converging until every review thread is resolved — through a fix OR a reply (answered question, recorded rationale) — so the PR is left with zero open threads (only genuine human-judgment flags stay open). On convergence it also refreshes the PR description to match the shipped diff and, best-effort, notes the linked Linear ticket. Use after opening a draft PR to converge the branch to a clean, review-ready state before undrafting. Callers: autonomous-workflow Phase 6/7, create-pr (post-draft), and standalone via /review-changes. Invoke with /review-loop <PR-URL|#n> [--cap N] [--critical] [--no-feedback] [--no-refresh].

8 Updated 2 days ago
mthines