review-swarm
Review Swarm runs four specialized read-only agents in parallel to examine a git diff or file scope for behavioral regressions, security risks, performance issues, and coverage gaps. The main agent then filters and ranks findings by severity, delivering only high-signal issues with a clear fix path—no file edits or automated fixes applied.
Review Swarm finds high-signal bugs, security risks, and regressions in git diffs by running four parallel read-only reviewers and filtering results by severity.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-03-29
Review Swarm finds high-signal bugs, security risks, and regressions in git diffs by running four parallel read-only reviewers and filtering results by severity. Review Swarm runs four specialized read-only agents in parallel to examine a git diff or file scope for behavioral regressions, security risks, performance issues, and coverage gaps. The main agent then filters and ranks findings by severity, delivering only high-signal issues with a clear fix path—no file edits or automated fixes applied.
Use it when
- Review Swarm deploys four specialized agents simultaneously—one for behavioral regressions, one for security risks.
- Yes.
Verify before relying
Read SKILL.md below before installing (2 files). Open directory: indexed for reading, not audited.
Similar skills
Install
Dimillian/Skills/review-swarm · repository language: Shell
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does review-swarm do with my git diff before merge?
Review Swarm examines your git diff or file scope using four specialized read-only agents running in parallel to find high-signal bugs, security risks, regressions, and coverage gaps. A main agent then filters and ranks findings by severity, delivering only the issues that matter most with a clear fix path—no automated edits are applied.
How does review-swarm run parallel code review of staged changes?
Review Swarm deploys four specialized agents simultaneously—one for behavioral regressions, one for security risks, one for performance issues, and one for test coverage gaps. Each agent analyzes your staged changes independently, then the main agent consolidates their findings into a prioritized list ranked by severity.
Can review-swarm check current changes for regressions?
Yes. Review Swarm includes a dedicated behavioral agent that scans your diff for regressions, contract mismatches, and backward-compatibility fallout. It runs in parallel with security, performance, and coverage agents to catch breaking changes before merge.
What security and performance review does review-swarm provide?
Review Swarm runs specialized security and performance agents on your diff. The security agent flags vulnerabilities and privacy risks; the performance agent detects leaks, reliability risks, and operational brittleness. Both feed into a prioritized fix path ranked by signal strength.
Does review-swarm edit files or apply automated fixes?
No. Review Swarm is read-only. It identifies and ranks high-signal issues with a clear fix path, but does not modify files or apply automated fixes. You retain full control over remediation decisions.
What scope can review-swarm analyze—just staged changes?
Review Swarm can analyze staged changes, explicit file scope, or a full git diff. You choose the scope, and the four parallel agents examine it for behavioral regressions, security risks, performance issues, and coverage gaps within that boundary.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Review Swarm
Review a diff with four read-only sub-agents in parallel, then have the main agent filter, order, and summarize only the issues that matter. This skill is review-only: sub-agents do not edit files, and the main agent does not apply fixes as part of this workflow.
Step 1: Determine Scope and Intent
Prefer this scope order:
- Files or paths explicitly named by the user
- Current git changes
- An explicit branch, commit, or PR diff requested by the user
- Most recently modified tracked files, only if the user asked for a review and there is no clearer diff
If there is no clear review scope, stop and say so briefly.
When using git changes, choose the smallest correct diff command:
- unstaged work:
git diff - staged
(truncated - see the full file via the links below)
File tree — 2 files
review-swarm/SKILL.md
review-swarm/agents/openai.yaml
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Find high-signal bugs, security risks, and regressions in a git diff before merge”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Bug Hunt Swarm deploys four read-only sub-agents in parallel to investigate bugs, regressions, and crashes from different angles—reproduction scope, code paths, recent changes, and proof strategies. The main agent then synthesizes findings into ranked hypotheses with supporting evidence and the fastest path to confirm or disprove each theory, all without making code edits.
This skill diagnoses and resolves Swift Concurrency issues in modern Swift codebases through systematic triage and targeted fixes. It handles actor isolation, Sendable safety, and async/await migration while preserving existing behavior and ensuring test suite compatibility.
Qt Cpp Review combines deterministic linting with parallel agent-driven analysis to audit Qt6 C++ code across model contracts, ownership, threading, API correctness, error handling, and performance. It reports only high-confidence issues with structured mitigations and operates read-only, never modifying your code.
Qt Qml Review combines deterministic linting with parallel agent-driven analysis to audit Qt6 QML code across six focused domains: bindings, layout, component loading, delegates, states, and performance. The skill reports only high-confidence issues with structured mitigations and never modifies code.
understand-diff compares your code changes to the project's knowledge graph, surfacing which components were modified and what else might be impacted. It traces dependencies and cross-layer concerns to highlight potential risks, then generates a diff overlay for visual exploration in the dashboard.
Agent Teams Playbook provides a structured 6-stage workflow for coordinating multiple agents across different runtime platforms. It handles task planning, capability discovery, team assembly, parallel execution, and result aggregation—with built-in quality gates and cross-platform adaptation for Claude Code, Codex, OpenClaw, and Cursor.