Coding & Dev Tools
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
-
contentstack Skill Typescript Style 3TypeScript compiler settings, hand-written typings, and TSLint for this repo — use when changing tsconfig, typings, or lint rules.
-
rainmanjam Skill Authz 2Permission and access-control code. Structure, clarity and testability of authorisation logic: where the decision lives, how it is named, and keeping it separable from the code that acts on it.
-
rainmanjam Skill Retro 2Something broke. Deciding what to change in the code so the class of problem is less likely, and writing it up so the next person understands the reasoning rather than just the outcome.
-
rainmanjam Skill Design 3Designing a new interface, module, schema or type together with its validation and failure behaviour: what each input accepts, what happens when it does not, and what the caller gets back when something goes wrong.
-
whitebeardit Skill Opentelemetry Instrumentation 2Instruments Node.js/TypeScript applications with OpenTelemetry spans following best practices. Use when adding distributed tracing, instrumenting HTTP requests, database operations, or when implementing observability with OpenTelemetry in Node.js applications.
-
metabench Skill UI Screenshot Feedback 2Automatic UI screenshots, Electron/Puppeteer capture rigging, control-centre screenshot review galleries, user journey planning, and comment-driven UI iteration.
-
jbaruch Skill Speckit 03 Plan 2Create technical implementation plan from feature specification
-
jbaruch Skill Speckit 01 Specify 2Create feature specification from natural language description
-
jbaruch Skill Speckit 02 Clarify 2Identify underspecified areas and ask targeted clarification questions
-
jbaruch Skill Speckit 05 Testify 2Generate test specifications from requirements before implementation (TDD support)
-
jbaruch Skill Speckit 07 Analyze 2Validate cross-artifact consistency between spec, plan, and tasks
-
normcrandall Bundle Product Management 2Creates PRDs with user stories for brownfield enhancements. Analyzes existing projects, defines requirements, and generates implementable user stories with acceptance criteria, tasks, and dev notes.
-
him0 Bundle Auto Fix 2CI ステータスと PR レビューコメントを確認し、問題を自動修正してコミット&プッシュする。CI 確認、テスト落ち修正、レビュー対応が必要な時に使用
-
him0 Skill Pull Request 2Pull Request を作成する。既に作成済みの場合はコミットを push し、最新の変更に基づいて PR のタイトルと説明を更新する
-
pluginagentmarketplace Bundle Databases 2Game data persistence with player profiles, leaderboards, inventory systems using Redis and PostgreSQL
-
varie-ai Skill Workstation 2Control Varie Workstation sessions (Claude Code multi-session orchestration). Use when: (1) user wants to work on / start / resume a coding project, (2) checking session status, (3) sending commands to a session, (4) listing active sessions, (5) creating new sessions, (6) user replies to a plan approval or question notification, (7) user wants to stop/cancel/interrupt a session, (8) user wants a screenshot of a session or screen. Triggers on: work on, start, resume, sessions, workers, workstation, dispatch, project name, approve, reject, option, pick, yes, no, stop, cancel, interrupt, escape, kill, stuck, screenshot, show me, capture, what does it look like.
-
hegeldev Bundle Coverage 3How to approach code coverage in this project. Use when coverage CI fails, when writing tests for new code, when deciding whether to add // coverage-ignore, or when you need to make untestable code testable. Also use proactively when writing new code to ensure it will be coverable.
-
hegeldev Skill Self Review 3Review your own changes before creating a pull request. Use this before running create-pr, or whenever you want to check that your changes are clean, correct, and well-tested. Trigger when: about to create a PR, finished a chunk of work, or asked to review changes.
-
microsoft Skill Code Review 4Review SynapseML Python and Scala code changes. Use before finalizing PR reviews or implementation changes to check security, compatibility, style, generated code, and targeted tests.
2.7k -
mskadu Bundle Anti Sycophancy 2Eliminate sycophantic agreement patterns in AI responses. Load via /skill anti-sycophancy.
-
mskadu Bundle Permission Manager 2Manage opencode permissions: review always-allow lists, suggest safe read-only commands, configure permission patterns
-
jbaruch Skill Speckit 04 Checklist 2Generate domain-specific quality checklists for requirements validation
-
jbaruch Skill Speckit 00 Constitution 2Create or update project governance principles and constitution
-
jbaruch Skill Speckit 09 Taskstoissues 2Convert tasks to GitHub Issues for project tracking
-
clyra-ai Bundle CI Failure Triage 3Triage CI failures using artifact-first checks. Use when users need fast root-cause isolation from failing runs, integrity verification, and deterministic reruns.
-
clyra-ai Bundle Incident To Regression 3Convert incident artifacts into deterministic regression fixtures and CI-ready outputs. Use when users ask to reproduce a failure, build repeatable graders, or emit junit evidence.
-
clyra-ai Bundle Evidence Receipt Generation 3Generate portable evidence receipts from run artifacts. Use when users ask for ticket-ready proof, receipt footers, or integrity-backed handoff metadata.
-
yansongda Skill Dev Guide 3Use when developing or testing yansongda/supports. Covers commands, code standards, and project structure.
-
openai Bundle Pr Draft Summary 2Prepare a local PR title, description, and branch suggestion when requested or after eligible implementation work.
23.3k -
openai Bundle Maintainer Review 2Assess a GitHub issue or PR for demonstrated need, supported alternatives, correctness, and maintainer action. Desk review only.
23.3k -
openai Bundle Final Release Review 2Assess a JS SDK release candidate or release plan against the previous release and recommend ship or block.
23.3k -
openai Bundle Implementation Kickoff 2Carry implementation through an isolated worktree and local handoff. Use only when this skill is explicitly invoked.
23.3k -
openai Bundle Implementation Strategy 2Choose supported scope and compatibility boundaries for SDK behavior changes; revisit when feedback changes the design.
23.3k -
openai Bundle Code Change Verification 2Run the required final install, build, type, lint, test, and format checks after eligible SDK changes pass review.
23.3k -
openai Bundle Implementation Final Review 2Review completed implementation changes before final verification. Use when repository policy requires independent review or the user explicitly requests it.
23.3k -
yansongda Skill Container Dev 3Use when local PHP environment is unavailable. Fallback container-based development environment for yansongda/supports project.
Frequently asked questions
What are Coding & Dev Tools agent skills?
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
Which Coding & Dev Tools skills are most installed?
Popular Coding & Dev Tools skills on SkillMD right now include typescript-style, authz, retro. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Coding & Dev Tools skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.