代码评审

gitnexus-exploring

abhigyanpatwari

"Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: \"How does X work?\", \"What calls this function?\", \"Show me the auth flow\""

docs-and-website-sync

weapp-vite

面向 weapp-vite monorepo 的文档、website 与公开 skills 同步工作流。适用于源码能力变化后同步配置、CLI、React/Wevu/Vue SFC、多平台、mpcore、README、packaged docs、脚手架 AGENTS.md、AI skills 元数据和触发回归入口。

ln-600-docs-auditor

levnikolaevich

Audit project documentation quality across 8 categories (Hierarchy, SSOT, Compactness, Requirements, Actuality, Legacy, Stack Adaptation, Semantic Content). Delegates to ln-601 for deep semantic verification of project documents. Use when documentation needs quality review, after major doc updates, or as part of ln-100-documents-pipeline. Outputs Compliance Score X/10 per category + Findings + Recommended Actions.

fix-coderabbit-review

pedronauck

End-to-end remediation workflow for PR review feedback by PR number. Use when Codex must export CodeRabbit issues for a PR, fix every issue completely, commit all fixes in a single commit, and resolve GitHub review threads afterward.

Ai Code Generation

omer-metin

Anti Marketing

omer-metin

Ai Music Audio

omer-metin

Agent Based Modeling

omer-metin

brand-name-generator

shipshitdev

Generate creative brand names, company names, product names, or startup names. Includes naming strategies, brandability scoring, and domain availability checking.

copywriter

shipshitdev

Brand voice guardian and conversion-focused copywriter, specializing in direct, no-fluff copy that adapts to project's brand voice

phx:audit

oliver-kriska

Holistic project health audit using 5 parallel specialist subagents. Analyzes architecture, performance, security, test quality, and dependencies. Produces actionable report with health score. Use quarterly or before major releases.

phx:investigate

oliver-kriska

Investigate a bug or error in Elixir/Phoenix code. Uses Ralph Wiggum approach - checks obvious things first, reads errors literally. Add --parallel for 4-track deep investigation.

ln-513-agent-reviewer

levnikolaevich

"Worker that runs parallel external agent reviews (Codex + Gemini) on code changes. Background tasks, process-as-arrive, critical verification with debate. Returns filtered suggestions with confidence scoring."

learn

agentskill-sh

Discover, install, and manage AI agent skills from agentskill.sh. Search for capabilities, install mid-session, scan for security issues, and provide feedback. Use when asked to find skills, install extensions, or check skill safety.

linkedin-success-factors

sachacoldiq

7 key LinkedIn success factors and campaign takeaways. Use as a checklist before launching LinkedIn campaigns or reviewing campaign performance.

sdr-outbound-rules

sachacoldiq

SDR outbound writing rules, 8 allowed messaging frameworks, and tone guidelines by offer type. Use when training SDRs, creating messaging guidelines, or standardizing outbound quality.

1k-pkg-upgrade-review

OneKeyHQ

Reviews package version upgrades — diffs source between versions, traces call sites, and generates compatibility reports.

1k-sentry-analysis

OneKeyHQ

Analyze and fix production errors from Sentry crash reports (AppHang, ANR, crashes, stacktraces).

phx:challenge

oliver-kriska

Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, or PR readiness.

ln-222-story-replanner

levnikolaevich

Replans Stories when Epic requirements change. Compares IDEAL vs existing, categorizes operations (KEEP/UPDATE/OBSOLETE/CREATE), executes in Linear.

ln-610-code-comments-auditor

levnikolaevich

Audit code comments and docstrings quality across 6 categories (WHY-not-WHAT, Density, Forbidden Content, Docstrings, Actuality, Legacy). Use when code needs comment review, after major refactoring, or as part of ln-100-documents-pipeline. Outputs Compliance Score X/10 per category + Findings + Recommended Actions.

checking-changes

streamlit

Validates all code changes before committing by running format, lint, type, and unit test checks. Use after making backend (Python) or frontend (TypeScript) changes, before committing or finishing a work session.

1k-patching-native-modules

OneKeyHQ

Patches native modules (expo-image, react-native, etc.) to fix native crashes or bugs.

swarm-expert

desplega-ai

Multi-agent coordination expert for agent-swarm MCP. Use when the user asks about swarm coordination, delegating tasks to agents, checking swarm status, agent messaging, or managing multi-agent workflows.