Code Review
Automated code review and analysis
eval-guidance-actionability
by whitespectre
Score assistant responses for guidance & actionability on a strict 1-5 scale, then return strict JSON only with dimension, score, rationale, and improvement suggestions. Use when the user asks to evaluate how actionable, helpful, or step-by-step a response is.
pr-cache-sync
by marxbiotech
Sync local PR review cache with GitHub. Use when user says "sync PR cache", "pull latest review", "refresh cache", "update local cache", or wants to ensure they have the latest review content from GitHub.
google-ads-audit
by Schlsn
Comprehensive Google Ads account audit with actionable recommendations. Use when user wants to audit, analyze, or review a Google Ads account, campaigns, or performance. Triggers include requests to audit account structure, analyze Quality Score, review keywords and search terms, evaluate ads and extensions, check landing pages, identify optimization opportunities, find wasted spend, or create improvement roadmaps. Supports CSV/Excel exports from Google Ads or direct data input.
Linux Privilege Escalation
by jcastillotx
This skill should be used when the user asks to "escalate privileges on Linux", "find privesc vectors on Linux systems", "exploit sudo misconfigurations", "abuse SUID binaries", "exploit cron jobs for root access", "enumerate Linux systems for privilege escalation", or "gain root access from low-privilege shell". It provides comprehensive techniques for identifying and exploiting privilege escalation paths on Linux systems.
ghwf4-review
by ShotaIuchi
Plan またはコードのレビュー記録を作成
review-as
by petestewart
Review a PR or branch using a specific reviewer's technical preferences. Use when the user says "/review-as <name> <pr-number-or-branch>", "review this as matt", "what would matt say about this PR", or needs code reviewed against a particular person's standards.
deployment-env-isolation-check
by JsonLee12138
Validate environment isolation using merged values from .deploy.env.common and .deploy.env.<ENV_MODE>. Use when ensuring test/prod/custom do not share the same registry, remote host, user, and port identity.
BlogClaw
by greentechgear
GitHub: https://github.com/greentechgear/blogclaw
research
by arielperez82
Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.
skill-finder
by dangogit
Find and install the best skill for your current task. Use when the user wants to discover skills, asks "is there a skill for...", "find a skill for...", or "/skill-finder". Searches skills.sh in real-time and uses LLM reasoning to match skills to the user's context.
native-app-publish-ready
by ameistad
Comprehensive app store submission readiness checker for mobile apps. Audits iOS App Store and Google Play Store requirements including build config, privacy compliance, store assets, metadata, technical requirements, and common rejection causes. Use when the user asks to "check if my app is ready to submit", "review for app store", "app store checklist", "pre-submission check", "ready for Play Store", "ready for App Store", "submission readiness", or wants to audit a mobile app before publishing. Supports native iOS (Swift/ObjC), native Android (Kotlin/Java), Flutter, and React Native (including Expo) projects.
updating-work-item
by squirrel289
"Update an existing work item with status changes, effort tracking, test results, and related commits. Use when progressing work, recording test results, or adjusting estimates. Supports: (1) Status transitions (proposed → ready → in-progress → ready-for-review → closed), (2) Feature branch creation and sync, (3) Automatic PR creation on ready-for-review transition, (4) Effort tracking (estimated → actual), (5) Test and commit tracking, (6) Dependency validation (all depends_on items must be closed before closing), (7) Notes with timestamps"
session-advisor
by pure-maple
多模型协作的SESSION管理顾问。当调用Codex或Gemini前，自动提供SESSION复用/新开建议。当用户讨论多模型协作、SESSION管理、上下文隔离时使用。
stgraph-engineer
by ManuelSannazzaro03
STGraph/STEL specialist. Use when analyzing .stg models, debugging STEL expressions, explaining model behavior, detecting errors, or proposing fixes. Trigger when user mentions STGraph, STEL, .stg files, state variables, simulation models, or node expressions.
check-prd
by Liquid-erigeronphiladelphicus552
Review B端 PRDs, requirement docs, SaaS or enterprise product specs, and system design documents with a 14-dimension quality framework. Use this whenever the user asks to check, review, critique, improve, or find gaps in a PRD, 需求文档, 产品方案, B端系统设计, SaaS spec, or similar design document, even if they only say "帮我看看这个 PRD/方案/需求".
reviewing-code
by augmnt
Provides structured code review with prioritized feedback. Use when reviewing PRs, analyzing code quality, checking for bugs, or auditing changes. Triggers on "review this", "check this code", PR reviews, or code quality questions.
moodle-plugin-development-rules
by jrevillaa
Moodle plugin development standards and review rules for implementing or refactoring Moodle plugins using Moodle-native patterns. Use when Codex works on Moodle plugin code such as local, mod, block, report, admin tool, enrol, auth, question, theme, availability, repository, or similar plugin types; when editing PHP, Mustache, JS, renderer, or form code in a Moodle codebase; or when reviewing code for Moodle-specific anti-patterns such as direct JavaScript requires instead of AMD modules, hand-built HTML forms instead of Form API, and view markup echoed from PHP instead of Mustache templates and renderers.
social-polish
by Howell5
从核心观点生成优质社媒长文。运用 4D 框架深度分析选题，去除 AI 味，6 维度评审确保质量。
planetscale-dev-db
by Darna-Digital
Connect to the PlanetScale development database branch and execute SQL queries/mutations. Use when the user wants to query the dev database, run SQL against the development environment, inspect dev data, or execute mutations on the development PlanetScale branch.
thought-mining
by qingchunwuhui
思维挖掘助手 - 通过对话帮助用户把脑子里的零散想法倒出来、记录下来、整理成文章。覆盖从思维挖掘到成稿的完整流程。
finishing
by BaxterCooper
Use when all tasks are complete. Presents completion options and enforces test gate. Work is never left in limbo.
gh-cleanup
by AutoFor
前回セッションで削除が遅延された stale worktree とブランチを一括削除する。
debug
by gemini960114
Use this skill when asked to review, audit, or debug code. Covers systematic bug-finding across frontend (TypeScript/React/Canvas), backend (Python/FastAPI), and full-stack projects. Apply this BEFORE delivering any code to catch issues proactively.
pr-cache-cleanup
by marxbiotech
Clean up local PR review cache files for merged or closed PRs. Use when user says "clean up cache", "cleanup merged PR caches", "remove old caches", "clear review cache", or wants to free up space from stale cache files.