Code Review
Automated code review and analysis
housekeeping
by lidessen
Manages project housekeeping including documentation organization, dependency management, directory structure, code cleanup, technical debt tracking, and infrastructure configuration. Use when organizing documentation, cleaning up dependencies, reorganizing folders, removing dead code, addressing tech debt, or maintaining project structure.
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。"
gas-test-review
by whichguy
Review test plans and existing tests for GAS projects using the mocha/chai test framework. AUTOMATICALLY INVOKE when: - "review test", "test plan", "test coverage", "validate tests" - File patterns: .test.gs, .spec.gs, .test.html, .spec.html - After qa-analyst generates specs - Before committing test files to GAS projects NOT for: Testing the framework itself, general JS/TS tests (use code-reviewer)
code-review
by yarlson
This skill should be used when the user asks to "review my changes", "review this code", "check my work", "what's wrong with my changes", "review before I push", "security review", "do a code review", or mentions reviewing, auditing, or analyzing local code changes before committing or opening a PR.
tabctl
by ekroon
Manage and analyze Edge tabs and groups with tabctl. Use when asked to list, search, analyze stale or duplicate tabs, generate reports, or organize tabs. Prefer read-only commands and only run mutating actions with explicit targets and confirmation.
GitHub Push
by alfredang
Secure git push with automatic secret detection, README generation, and repository setup. Scans for secrets, auto-generates README, configures repo description/topics/discussions, and pushes to GitHub.
git-worktree
by AntJanus
Use when you need to work on multiple branches simultaneously, run parallel Claude Code sessions, handle emergency hotfixes during feature work, review PRs without switching branches, or test across branches without losing current work. Use when asked to "work on two branches at once", "parallel development", "switch without losing work", "create a worktree", or "hotfix while working on a feature".
domain-modeling
by jwilger
Domain modeling principles: parse-don't-validate, make invalid states unrepresentable, primitive obsession detection, semantic types, and domain veto authority. Activate when designing types, reviewing code for domain integrity, or when domain review is needed in a TDD cycle.
dependency-audit
by 1Mangesh1
Dependency auditing, updating, and vulnerability management for npm, pip, and other package managers. Use when user asks to "audit dependencies", "update packages", "fix vulnerabilities", "check outdated", "npm audit", "pip audit", "upgrade dependencies safely", or any dependency management tasks.
pentest-authentication-authorization-review
by crtvrffnrt
"Security assessment skill for authentication and authorization controls. Use when prompts include session handling, token abuse, MFA weaknesses, account takeover, IDOR/BOLA/BFLA, privilege escalation, tenant isolation, or identity boundary validation. Do not use when the task is generic recon, pure parser fuzzing, or final report composition only."
infra-code-review
by yarlson
This skill should be used when the user asks to "review my infra changes", "review my IaC", "check my infrastructure code", "review this deploy config", "review my cloud config", "review infra before I push", or mentions reviewing, auditing, or analyzing infrastructure-as-code changes — any tool, any cloud, any format.
ruler-rules-init
by Adonis0123
Migrate and bootstrap Ruler-based AI rules across repositories with English-first templates, preset-based project detection, and safe, idempotent setup. Use when creating or standardizing .ruler/* files, generating AGENTS.md/CLAUDE.md, wiring ruler:apply into package.json, adding generated-file ignores in .gitignore, and designing applyTo scoping patterns such as ` and web/`.
conductor-review
by airclear
Acts as a Principal Software Engineer to review completed or in-progress work against project standards, tech stack choices, and the implementation plan. Use when the user wants a quality check on their code or before finalizing a track.
trae-agent-writer
by learnwy
"Create subagent definitions (agent.md files) for independent AI workers. Use when user wants to: create an agent, build a grader/evaluator, make an A/B comparator, spawn independent workers, or create something that runs in isolation. Triggers on: '创建 agent', 'subagent', 'grade outputs independently', 'blind comparison', 'run this in parallel'. Do NOT use for skills (use trae-skill-writer) or rules (use trae-rules-writer)."
content-research-writer
by Crumbgrabber
Assists in writing high-quality content by conducting research, adding
staged-review-validator
by Adonis0123
Validate staged-changes-review findings with evidence-based verdicts and minimal-fix guidance. Use when you need to confirm whether each reported issue is valid and actionable.
Transport & Routing
by torlando-tech
https://github.com/torlando-tech/reticulum-kt/rns-core/src/main/kotlin/network/reticulum/transport/Transport.kt (lines 2319-2338) - Kotlin implementation
mutation-testing
by jwilger
Mutation testing to validate test quality before PR creation. Runs mutation tools, enforces 100% kill rate, reports surviving mutants with recommended fixes. Activate when validating test coverage, preparing pull requests, checking test quality, or when asked about mutation testing.
requesting-code-review
by Crumbgrabber
Use when completing tasks, implementing major features, or before merging
validation
by lidessen
Unified validation orchestration for code quality, consistency, and project health. Auto-triggers on code changes, PR creation, or explicit validation requests. Coordinates refining, housekeeping, and custom validators into cohesive pipelines. Use for "validate", "check", "verify", "验证", "检查", or when quality assurance is needed.
android-espresso-dependencies
by hitoshura25
Add Espresso and AndroidX Test dependencies to Android project
subagent-driven-development
by Crumbgrabber
Use when executing implementation plans with independent tasks in the
Announce Mechanism
by torlando-tech
Cryptography & Identity: Key generation, signature verification, ratchets
gas-ui-debug
by whichguy
Symptom-based GAS UI debugging. Route by user's problem description. AUTOMATICALLY INVOKE when user describes: - "blank", "empty", "nothing shows" → CONSOLE_CHECK - "error", "red message" → CONSOLE_CHECK - "button doesn't work", "click does nothing" → HANDLER_TEST - "nothing happens" → CONNECTION_CHECK - "looks wrong", "layout broken" → SNAPSHOT_CHECK - "slow", "loading forever" → PERFORMANCE_CHECK MCP REQUIRED: chrome-devtools (with browserUrl for GAS auth)