Code Review
Automated code review and analysis
sync-docs
by ruchernchong
Update and maintain CLAUDE.md and README.md documentation
Broken Authentication Testing
by jcastillotx
This skill should be used when the user asks to "test for broken authentication vulnerabilities", "assess session management security", "perform credential stuffing tests", "evaluate password policies", "test for session fixation", or "identify authentication bypass flaws". It provides comprehensive techniques for identifying authentication and session management weaknesses in web applications.
ad-performance-learning
by tonyflo79
Post-launch performance analysis and intelligence feedback loop for paid ad campaigns. Use after ads are live and performance data is available. Analyzes real performance data, extracts actionable learnings, and propagates them back into engine files (A01 intelligence, A02 hook taxonomy, A06 Arena calibration, A10 scoring models). When data conflicts with predictions, data wins. Learnings must be actionable (WHAT + WHY + HOW to apply) and the loop must close by updating engine files, not just producing reports. Trigger when users mention ad performance, campaign results, ad analytics, what worked, learning from ads, or updating the engine with results. Requires live campaign performance data.
code-review-and-commit
by abpai
Review uncommitted Git changes for correctness, quality, and project convention alignment, then apply fixes and prepare a safe, atomic commit plan. Use when users ask to review code before committing, improve local changes, split work into logical conventional commits, or execute git add/git commit with clear staging boundaries.
caps-format-validator
by asadullah48
Validate CAPS (Coding Agent Playbook Spec) playbooks for correctness, completeness, and compatibility with Claude Code and Goose
strategic-review-interactive
by kanghohyeong
This skill supports the strategic review process through a web interface.
sync-trending
by likw99
Monitior technology trends (GitHub, etc.), contextualize them against the user's project, and autonomously verify them through installation and testing. Use when the user asks about trending repositories, new tools, or wants to stay updated on tech relevant to their current work.
fsharp-code-review
by bromanko
This skill should be used when the user asks to "review F# code", "fsharp code quality", "F# idioms check", "review my F#", "check code quality", or wants feedback on F# code patterns, idioms, Result handling, or module organization.
Skills
by gighive
For debugging, include what to check, where to check it, and what outcome to expect.
session-pr
by rahulgi
Commit changes from the current Claude Code session to a new branch, push to GitHub, and open a PR. Use when the user wants to save their work as a PR, submit session changes, or create a pull request for what was done in this session.
audit
by rakshit-737
Run structured frontend code audits across accessibility, performance, theming, responsive behavior, and visual anti-patterns. Use when the user asks for an accessibility check, performance audit, responsive review, theming review, or a scored technical quality report for a page, feature, or component.
verify
by biruk741
Run comprehensive validation against a completed plan. Checks each phase's implementation against PLAN.md requirements, then runs project-wide tests, lint, and type checks.
hamburger-method
by Envy-7z
Slices features into vertical deliverable pieces using the Hamburger Method. Generates 4-5 implementation options per layer and composes minimal end-to-end slices. Use when slicing work, breaking down features into layers, or delivering incrementally.
vibe-pr
by tsukiyokai
"CANN 社区自主开发 bot。能接需求、自主开发、自我检视、管理 PR 全生命周期。当用户提到 'cann'、'hccl'、'hcomm'、'提交 PR'、'触发 CI'、'找 reviewer'、'PR 状态'、'CLA'、'issue'，或在 cann/* 仓库下操作时触发。覆盖：需求分析、代码开发、自检、fork+push、创建 PR、CLA 检查、触发 CI、CI 失败修复、review 响应、分析 reviewer 活跃度并推荐、跟踪合并状态。"
enhance
by keenranger
Analyze work patterns and improve Claude configuration. Use when user asks to improve Claude setup, optimize workflow, or says /enhance.
pr-review-workflow
by metyatech
Use when addressing PR review feedback, re-requesting reviews, handling GitHub review bot re-reviews (Codex, Copilot), or managing GitHub notifications. Do not use for creating new PRs or general development.
code-reviewer
by idotta
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
solidity-code-review
by whackur
Smart contract code review and security audit methodology for Solidity. Use when reviewing, auditing, or assessing the security of Solidity code. Provides structured review process, severity classification, key inspection areas, and OWASP SCWE integration. Triggers on tasks involving code review, security audit, vulnerability assessment, smart contract review, or best practices check.
review-plan-implementation
by tstelzer
Review code changes against a plan using the plan location and implementing git commit(s).
writing-release-notes
by danbars
Use when changes are ready to ship and you need to communicate what changed, who it affects, and any required actions without exposing internal-only details.
robonet-workbench
by robonet-tech
"Use Robonet's MCP server to build, backtest, optimize, and deploy trading strategies. Provides 24 specialized tools for crypto and prediction market trading: (1) Data tools for browsing strategies, symbols, indicators, Allora topics, and backtest results, (2) AI tools for generating strategy ideas and code, optimizing parameters, and enhancing with ML predictions, (3) Backtesting tools for testing strategy performance on historical data, (4) Prediction market tools for Polymarket trading strategies, (5) Deployment tools for live trading on Hyperliquid, (6) Account tools for credit management. Use when: building trading strategies, backtesting strategies, deploying trading bots, working with Hyperliquid or Polymarket, or enhancing strategies with Allora Network ML predictions."
forge
by vieko
Verification boundary CLI that delegates tasks to autonomous agents. Use when the user wants to run forge, execute specs, run specs in parallel, run pending specs, define specs from a description, resolve specs, audit code against specs, review changes, watch live logs, check run status, resume a session, or delegate complex multi-step work to an autonomous agent. Triggers include "forge run", "run this spec", "run specs in parallel", "run pending", "forge define", "define specs", "audit the codebase", "review changes", "forge watch", "forge status", "rerun failed", "resolve spec", "delegate this to forge". Do NOT use for simple edits you can make directly, questions that don't require implementation, or straightforward work in the current repo that doesn't need autonomous agent execution.
openclaw-skill-auditor
by CalWade
Audit installed OpenClaw skills for security risks, token bloat, and hidden cost patterns. Use this skill whenever the user asks to scan, audit, check, or review their installed skills — including questions like "are my skills safe?", "which skills are wasting tokens?", "do I have any suspicious skills?", "clean up my skills", or "check my OpenClaw skills". Always invoke this skill for any skill health, quality, or cost investigation.
kaoyan-2027-coach
by storm-crypto
"考研2027全流程学习教练。支持 Obsidian 学习档案初始化、错题归档与复习、今日/周计划、学习日志、周月复盘、模考分析与策略校准。"