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.
-
armelhbobdad Bundle Skf Test Skill 3Cognitive completeness verification — quality gate before export. Use when the user requests to "test a skill" or "verify skill completeness."
-
armelhbobdad Bundle Skf Quick Skill 3Fast skill from a package name or GitHub URL — no brief needed. Use when the user requests a "quick skill" or "skill from URL" or "skill from package."
-
armelhbobdad Bundle Skf Create Skill 3Compile a skill from a brief. Supports --batch for multiple briefs. Use when the user requests to "create a skill" or "compile a skill."
-
armelhbobdad Bundle Skf Export Skill 3Package for distribution and inject context into CLAUDE.md/AGENTS.md/.cursorrules. Use when the user requests to "export" or "package a skill."
-
armelhbobdad Bundle Skf Rename Skill 3Rename a skill across all its versions — transactional copy-verify-delete with platform context rebuild. Use when the user requests to "rename a skill."
-
armelhbobdad Bundle Skf Update Skill 3Smart regeneration preserving [MANUAL] sections after source changes. Use when the user requests to "update a skill" or "regenerate a skill."
-
armelhbobdad Bundle Skf Analyze Source 3Discover what to skill in a large repo and produce recommended skill briefs. Use when the user requests to "analyze source for skills" or "discover skill opportunities."
-
armelhbobdad Bundle Skf Refine Architecture 3Improve architecture doc using verified skill data and VS feasibility findings. Use when the user requests to "refine skill architecture" or "improve architecture doc."
-
seasonedcc Skill Worktrees 7Run parallel tasks in isolated git worktrees, each with its own env file and its own SQLite store. Use when creating or removing a worktree, running parallel lanes or agents, running gates or a server for a specific worktree, or when the user mentions worktree, parallel lanes, or isolated environments.
-
seasonedcc Skill Background Jobs 6Write background work against the in-process scheduler — makeJob and makeCronJob, registration in the jobs array, retries and dedupe, idempotency in an append-only store, fan-out, and the tests that prove each. Use when adding or changing a job, enqueuing work from business or ingest code, editing app/business/jobs.server.ts or app/framework/scheduler.server.ts, picking a retry or interval setting, or testing what a job runs and what it enqueues.
-
seasonedcc Skill Database Design 6Design SQLite tables and migrations under the project's zero-exception append-only, event-sourced doctrine. Use when creating tables, writing migrations, adding columns, modeling a state change, deriving current state, choosing between an identity and an event table, or writing the dev seed.
-
seasonedcc Skill Framework Folder 5Enforce the separation between reusable framework code and product code in app/framework/. Use when adding a file or a helper to app/framework/, importing a framework module, wiring the database connection or the scheduler, or deciding where a new abstraction belongs.
-
seasonedcc Bundle Composable Functions 6Build business functions with the composable-functions library — applySchema, context validation with capability flags, combinators, and Result handling. Use when writing or changing a function in app/business/, validating input or context, composing with pipe/sequence/all/collect/branch, throwing InputError or ContextError, or unwrapping results with fromSuccess.
-
oozoofrog Bundle Jev TriageClassify bug reports and reported impact with Jev while keeping symptoms separate from confirmed causes. Do not automatically publish or assign issues.
-
oozoofrog Bundle Jev ContextRank retrieved development context or select an existing source value with Jev. Preserve mandatory documents and never invent paths or quotations.
-
oozoofrog Bundle Jev DecisionDelegate a bounded implementation-plan, scope, next-step, or already-installed-skill choice to Jev when project criteria are explicit. Do not use for advice-only review or execution authorization.
-
oozoofrog Bundle Jev CalibrateEvaluate saved Jev choices against acceptable labels and check sensitivity to wording, language, and option order. Evaluation outputs never authorize production actions.
-
oozoofrog Bundle Ponytail Beck Tdd사용자가 $ponytail-beck-tdd 또는 Ponytail과 켄트 벡의 TDD를 명시한 구현·기존 테스트 점검·개선 작업에 사용한다. 새 동작은 하나의 실패 테스트로 개발하고, 기존 테스트는 구현과 대조해 동작 보장·진단력·유지비를 개선한다. 일반 코딩 요청에는 자동 적용하지 않는다.
-
ysyecust Skill Golang Patterns堅牢で効率的かつ保守可能なGoアプリケーションを構築するための慣用的なGoパターン、ベストプラクティス、規約。
-
oozoofrog Bundle Jev Product ChoiceChoose among bounded product-copy or UX alternatives using explicit user preferences and Jev. Do not infer user values or claim unmeasured product outcomes.
-
oozoofrog Bundle Jev Review EvidenceUse Jev for bounded quality signals, claim-to-evidence checks, and additional test prioritization. Never replace actual builds, tests, or required checks.
-
oozoofrog Bundle Astra OrchestratorAstra 리더·워커·Git 전용 워커로 작업을 조정하도록 요청할 때 사용한다. 스킬 자체의 설명·편집이나 일반 단일 작업에는 자동 적용하지 않는다.
-
langwatch Skill Tracing 3Add LangWatch tracing and observability to your code. Use for both onboarding (instrument an entire codebase) and targeted operations (add tracing to a specific function or module). Supports Python and TypeScript with all major frameworks.
-
langwatch Skill Online Evaluations 3Configure LangWatch online evaluations and guardrails for production traffic. Use when the user wants to score live traces or threads, monitor production quality, sample incoming traffic, or synchronously block unsafe requests and responses. Do not use for batch experiments.
-
langwatch Skill Eval Triage 3Investigate failing experiments and evaluations with LangWatch. Triage a failing experiment run to the exact rows and evaluator scores that regressed, then to a root cause. Use when an experiment fails, scores drop, or evaluations regress.
-
langwatch Skill Debug Instrumentation 3Debug and improve your LangWatch traces. Inspects production traces for missing input/output, disconnected spans, unlabeled traces, and missing metadata. Use when traces look broken or incomplete.
-
kyopark2014 Bundle BusinfoAmazon Athena(AwsDataCatalog.businfo)로 실시간 버스 도착·잔여좌석 정보를 조회합니다. 차량번호(번호판), 노선 ID, 최근 N시간, 일별 요약 조회에 사용합니다. 사용자가 "버스 잔여좌석", "버스 도착", "차량번호", "노선", "businfo", "Athena 버스" 등을 요청할 때 사용합니다.
-
kyopark2014 Bundle My Vaultsob-docs(Obsidian형 vault)에 저장된 마크다운 노트를 조회·검색·생성·수정합니다. 사용자가 "vault", "내 노트", "ob-docs", "위키링크", "백링크", "노트 찾아줘", "메모 저장", "vault에 적어줘", "지식베이스" 등을 요청할 때 사용합니다.
-
kyopark2014 Bundle Book SearchSearch for books using Kyobo Book Centre's online catalog. Use when users want to find books by keyword, title, author, or topic. Supports Korean and English search terms and returns book titles with direct purchase links. Perfect for book recommendations, finding specific titles, or discovering books on particular subjects.
-
kyopark2014 Bundle Img2textocrExtract text from an image file (PNG, JPG, etc.) using Tesseract OCR and save the result as a .txt file. Automatically crops the top header and bottom footer regions before OCR so that page titles, section headings in the margin, and page numbers are excluded from the output. Use this skill whenever the user wants to convert an image to text, extract body text from a scanned page, or perform OCR on a document image while skipping headers and footers (e.g. "page_033.png을 텍스트로 변환해줘", "이 이미지에서 본문만 추출해줘", "img2text로 변환해줘").
-
kyopark2014 Bundle Skill CreatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
-
kyopark2014 Bundle System Monitor로컬 macOS/Linux 시스템의 CPU, 메모리, 디스크, 네트워크 사용량과 리소스를 많이 쓰는 상위 프로세스를 조회하고, 임계치를 초과하면 경고를 표시합니다. 사용자가 "시스템 모니터링", "시스템 상태", "서버 상태", "CPU 사용률", "메모리 현황", "디스크 용량", "네트워크 상태", "업타임", "프로세스 목록", "리소스 사용량", "느려졌는데 뭐가 문제야", "서버 헬스체크", "리소스 리포트 만들어줘" 등을 언급하거나, 컴퓨터/서버가 느리다고 불평하거나, 시스템 상태를 그래프나 리포트 파일로 받고 싶어할 때 반드시 이 skill을 사용하세요. 명시적으로 "모니터링"이라는 단어를 쓰지 않아도 시스템 성능·리소스·무거운 프로세스·서버 점검 요청이면 사용합니다.
-
kyopark2014 Bundle Browser HarnessSite-specific browser playbooks (domain-skills, interaction-skills) for Naver, GitHub, etc. Automate the browser with the browser-use CLI (state/indexed elements, eval, screenshots)—same stack as skills/browser-use. Upstream browser-harness Python repo is optional for advanced CDP.
-
kyopark2014 Bundle Asil Price Lookup아실(asil.kr) 사이트에서 아파트 실거래가(매매), 전세, 월세 정보를 조회합니다. browser-use CLI와 Python BeautifulSoup을 사용하여 특정 아파트 단지의 매매 실거래가, 전세가, 월세 정보를 검색하고 결과를 정리합니다. 사용자가 "아파트 실거래가 조회", "전세 시세 확인", "월세 정보", "아파트 매매가", "갱신 제외 전세" 등을 요청할 때 사용합니다.
-
materialofair Skill E2e 2Playwright end-to-end orchestration for critical user journeys, artifact capture, flaky-test isolation, and CI-ready reporting.
-
materialofair Skill AI Commenting 2AI-native code annotation protocol that encodes intent, risk, dependencies, constraints, and test expectations in machine-parseable comments.
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 skf-test-skill, skf-quick-skill, skf-create-skill. 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.