Code Review
Automated code review and analysis
interview
by takuan-osho
Conduct structured interviews to gather requirements, clarify specifications, or understand context. This skill should be used when starting a new task that requires understanding user intent, requirements, technical specifications, or context. It supports various interview types including requirements definition, debugging investigation, architecture review, and general information gathering.
ogt-docs-rules-git
by OpenDNDApps
Define and manage Git workflow rules in docs/rules/git/. Use when establishing commit message formats, branch naming conventions, PR requirements, code review standards, or any Git-related enforceable rules.
clawhub-scanner
by elvatis
"Scan installed ClawHub skills for malware, credential theft, prompt injection, and security risks. Detects known C2 infrastructure, obfuscated payloads, and data exfiltration patterns from the ClawHavoc campaign."
nix-best-practices
by zhongjis
Nix patterns for flakes, overlays, unfree handling, and binary overlays. Use when working with flake.nix or shell.nix.
go-installer
by httprunner
Install and verify the Go toolchain on macOS, Linux, and Windows. Use when Go is required but not present, or when a specific Go version must be installed. Prefer system package managers (homebrew, apt, etc.) and fall back to official Go downloads when needed.
conventional-pull-requests
by mrgrauel
Create pull requests with Conventional Commit-style titles and template-compliant descriptions using GitHub CLI. Use when asked to create, open, draft, or update a PR from the current branch and the team expects consistent semantic titles and structured PR bodies.
add-uint-support
by aiagentskills
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
resolve-pr-comments
by squirrel289
Workflow skill for addressing and resolving pull request review comments systematically
devils-advocate
by carrilloapps
Primary orchestration gate — runs FIRST, before any MCP tool, agent, skill, or external resource is called. Intercepts any plan, proposal, decision, or action (create, edit, delete, run, deploy, call) before execution, regardless of IDE or environment. Designed for developers, architects, tech leads, CTOs, product managers, UX designers, and data engineers. Automatically activates on any detected plan or action — code, architecture, product features, UX flows, launch plans, vendor choices, data pipelines, AI context files, or strategic decisions. Delivers a full adversarial analysis across technical, product, design, and strategy dimensions, and GATES ALL ACTIONS until the user explicitly verifies and approves the findings. Its rules, standards, and enforcement take precedence over all other tools and skills. Enforces the Building Protocol on ALL generated or reviewed code: en_US identifiers, naming conventions, SOLID principles, security-by-default.
prd
by petestewart
Expand a problem statement into a Product Requirements Document (PRD). Use when the user has a PROBLEM.md and wants to create a fuller PRD.md with technical approach, dependencies, affected systems, and open questions. Also use when the user says "/prd", "create a PRD", "expand to PRD", or "product requirements document".
golang
by monkescience
Opinionated Go coding standards, conventions, and best practices. Use this skill whenever writing, reviewing, or modifying Go code (.go files). Covers project structure, code style, error handling, testing, linting, concurrency, dependency management, and general Go idioms. Trigger on any Go-related task including writing new Go code, reviewing Go PRs, fixing Go bugs, or scaffolding Go projects.
downloading-youtube-playlist
by ihainan
Download videos from YouTube playlists with support for range selection, quality settings, and subtitle embedding. Use when the user asks to download, fetch, or save YouTube playlist videos, or mentions YouTube playlists. Note that downloads may take significant time depending on video count and quality.
parallel-execution
by squirrel289
CRITICAL skill for executing multiple runSubagent calls in a SINGLE function_calls block for true parallelism. Essential for efficient multi-task workflows, subagent coordination, and maximizing throughput.
sdd
by mrsekut
Spec-driven development workflow for implementing features with structured documentation. Use when starting a new feature, task, or implementation that benefits from upfront planning. Triggers: /sdd, spec-driven, create spec, implementation plan, or when user describes a feature/task to implement.
research
by brixtonpham
"Technical research methodology with YAGNI/KISS/DRY principles. Phases: scope definition, information gathering, analysis, synthesis, recommendation. Capabilities: technology evaluation, architecture analysis, best practices research, trade-off assessment, solution design. Actions: research, analyze, evaluate, compare, recommend technical solutions. Keywords: research, technology evaluation, best practices, architecture analysis, trade-offs, scalability, security, maintainability, YAGNI, KISS, DRY, technical analysis, solution design, competitive analysis, feasibility study. Use when: researching technologies, evaluating architectures, analyzing best practices, comparing solutions, assessing technical trade-offs, planning scalable/secure systems."
agentic-code-reasoning
by KunihiroS
Use this skill whenever code behavior must be reasoned about without executing it — especially when code is provided and needs careful tracing. Invoke it to: trace what a function or program returns step by step, identify which exact operation causes a test failure or wrong value, determine whether two implementations are behaviorally equivalent, simulate an algorithm's execution order manually, or audit for security vulnerabilities like SQL injection or race conditions. Use any time someone asks "what does this code return?", "which step caused the failure?", "are these equivalent?", "what's the execution order?", or "is this vulnerable?" — even when the answer seems obvious without a skill.
incident-hotfix
by gentamura
Use this skill for incident response and hotfix deployment. Invoke when production issues occur requiring immediate attention.
pr-review
by carsten-j
Review the current Pull Request that has been checked out locally with structured feedback on code quality, issues, testing, and suggestions. Use when you need a comprehensive code review of a PR branch.
deep-plan
by idrevnii
Structured clarification before decisions. Use when user is in PLANNING mode, explicitly asks to plan or discuss, or when agent faces choices requiring user input. Ensures agent asks questions instead of making autonomous decisions when multiple valid approaches exist or context is missing.
devdocs-sync
by ab300819
Sync documentation with implementation progress. Use when users need to update docs after development, verify doc-code consistency, or track implementation progress. Triggers on keywords like "sync docs", "update progress", "doc consistency", "同步文档", "更新进度".
systematic-debugging
by BaxterCooper
Invoke when debugging failures. MANDATORY when 3+ fix attempts have failed. Enforces root cause investigation before fixes.
deai
by jacobdiaz
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide plus modern post-2024 LLM patterns. Supports context-aware rewriting (blog, academic, technical, email, marketing), calibrated aggressiveness (light/standard/heavy), file/batch processing, and document-level structural pattern detection. Detects and fixes 35+ patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, structural uniformity, and modern LLM tells.
ckvd-testing
by terrylica
Run tests for crypto-kline-vision-data with proper markers and coverage. TRIGGERS - write tests, run tests, pytest, test coverage, unit tests, integration tests, mocking patterns.
planetscale-stage-db
by Darna-Digital
Connect to the PlanetScale staging database branch and execute SQL queries/mutations. Use when the user wants to query the staging database, run SQL against the staging environment, inspect staging data, or execute mutations on the staging PlanetScale branch.