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.
-
dannykkh Bundle Python Backend Fastapi명시적 `/python-backend-fastapi` 호출 전용 FastAPI 참고서. 일반 Python 백엔드 작성·리뷰에는 자동 적용하지 않는다.
-
dannykkh Bundle Dotnet Coding Standards명시적 `/dotnet-coding-standards` 호출 전용 .NET 참고서. 일반 구현에는 자동 적용하지 않고 프로젝트 구조와 네이티브 코딩 능력을 우선한다.
-
dannykkh Bundle Crafting Effective ReadmesUse when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.
-
dannykkh Bundle Fullstack Coding Standards명시적 `/fullstack-coding-standards` 호출 전용 풀스택 참고서. 일반 구현에는 자동 적용하지 않고 네이티브 코딩 능력과 프로젝트 규칙을 우선한다.
-
chorus-aidlc Skill BlogWrite release blog posts for Chorus — problem-first narrative, bilingual (zh/en), following the project's editorial style.
Audited -
chorus-aidlc Skill ReleaseRelease a new version of Chorus — bump version, update CHANGELOG, commit, tag, and create GitHub release.
Audited -
chorus-aidlc Skill Brainstorm ChorusOptional divergent-then-convergent dialogue for fuzzy ideas. Invoked from the idea skill as a prelude to structured elaboration; produces one ElaborationRound of decision-point Q&A and returns control. Never writes files, never posts comments, never resolves elaboration.
Audited -
chorus-aidlc Skill Code Reviewer ChorusRead-only adversarial Chorus code-review gateway — independently reviews an Idea's aggregate code change (the whole feature across all its tasks) and posts a single structured VERDICT comment on the Idea.
-
chorus-aidlc Skill BrainstormOptional divergent-then-convergent dialogue for fuzzy ideas. Invoked from the idea skill as a prelude to structured elaboration; produces one ElaborationRound of decision-point Q&A and returns control. Never writes files, never posts comments, never resolves elaboration.
Audited -
chorus-aidlc Skill Chorus BrainstormOptional divergent-then-convergent dialogue for fuzzy ideas. Invoked from the chorus-idea skill as a prelude to structured elaboration; produces one ElaborationRound of decision-point Q&A and returns control. Never writes files, never posts comments, never resolves elaboration.
Audited -
stacksjs Skill Stacks CLIUse when building CLI commands or tools with Stacks - the @stacksjs/cli package for creating commands with argument parsing, option handling, colored output, tables, progress indicators, prompts, or integrating with the buddy command system. Covers @stacksjs/cli and app/Commands/.
Audited -
stacksjs Skill Stacks CmsUse when working with the CMS in a Stacks application - posts, authors, pages, categories, tags, comments, blog configuration, RSS feeds, or sitemaps. Covers @stacksjs/cms, CMS models, routes, and actions.
Audited -
navikt Skill HandoffPrepare a portable handoff when the user requests transferring work to another session, client, or colleague. Ordinary context compression and same-session delegation belong to the client.
-
navikt Skill To SpecDocument resolved requirements and design choices as a concise implementation plan or specification, including a requested local document. Use `grill-with-docs` for unresolved design choices and `to-issues` for several independently deliverable slices.
-
navikt Skill PrototypeBuild a bounded, runnable throwaway experiment to resolve uncertain behavior or an interface contract. Use for data models, state machines, event flows, retries or failure semantics; use `design-prototype` for visual layouts and user-flow sketches.
-
navikt Skill To IssuesTurn a resolved plan or specification into independently useful implementation issues with native dependencies. Use when the user asks to break work into tickets; use `wayfinder` for unresolved decisions and `issue-management` for tracker mechanics.
-
navikt Bundle WayfinderOrganize several unresolved, dependent decisions as a persistent shared issue map when a conversation checkpoint cannot keep the route navigable across sessions. Select automatically from that need or continue an existing map; use grill-with-docs for each design decision, and ordinary planning when the direction is already settled.
-
navikt Skill Pull RequestPrepare and publish a pull request for a verified, scoped change when the user asks to open or update a PR. Use `review` to assess the diff first; implementing or reviewing work alone does not authorize publication.
-
navikt Bundle Nais ManifestCreate, change or review Nais Application and Naisjob deployment resources. Use for ingress, probes, resource limits, access policies, scaling or scheduled jobs; use `nav-troubleshoot` to diagnose a live workload and specialist skills for application code.
-
navikt Bundle Diagnosing BugsDiagnose failures, hangs, flakes or performance regressions from reproduction, code and runtime evidence. Use when the cause is unclear; use `tdd` for an established fix and `nav-troubleshoot` when the missing evidence is in a deployed Nais environment.
-
navikt Bundle Domain ModelingChallenge and maintain canonical domain terminology and qualifying architectural decisions during authorized design work. Use when concepts, boundaries, or durable trade-offs change; reading existing vocabulary alone does not need this skill.
-
navikt Skill Issue ManagementInspect, create, update, link or close GitHub issues for work that is already shaped. Use for tracker mechanics and explicit issue requests; use `triage` to assess readiness and `to-issues` to decompose a resolved plan.
-
navikt Bundle Improve Codebase ArchitectureFind refactoring opportunities that simplify module boundaries and improve testability and navigation. Use when existing code is tightly coupled, shallow or hard to change; use `architecture-review` to evaluate a concrete architecture proposal.
-
zai-org Skill RepoClone or fork a GitHub repository with optional local setup, or open repository resources such as files, branches, issues, and settings in the browser. Use when the user wants a new local checkout or the web UI, not a Codespace or an existing pull-request checkout.
-
zai-org Skill IssueCreate, view, list, or close GitHub issues and manage the labels and milestones that organize issues and pull requests. Use when the user wants to track or organize repository work, not when they are referring to a pull request itself.
-
zai-org Skill SetupVerify GitHub CLI installation and guide authentication for the intended GitHub host and account. Use when gh is missing, authentication is invalid, the user wants to switch accounts or hosts, or another GitHub skill cannot pass preflight.
-
zai-org Skill CommitCreate a local Git commit from staged changes using a conventional commit message. Use when the user wants to record already prepared changes locally, not when they want to create, review, or merge a pull request.
-
zai-org Skill ReleaseCreate a GitHub release and prepare changelog notes for a version tag. Use when the user wants to publish or draft a repository release, not merely create a Git commit, tag, or pull request.
-
zai-org Skill CodespaceCreate, list, connect to, stop, or delete GitHub Codespaces. Use when the user explicitly wants to manage a remote Codespaces development environment, not for cloning a repository locally.
-
zai-org Skill Glab StackManage stacked diffs and merge requests with the GitLab CLI. Use when the user wants to create, save, amend, sync, navigate, or reorder a stack of dependent merge requests. Triggers on tasks involving stacked diffs, stacked MRs, dependent merge requests, or incremental code review workflows using `glab stack`.
-
zai-org Skill Fund WatchOngoing monitoring of held or shortlisted funds over a window — manager changes, size and flow shocks, 仓位 shifts, style drift, and performance/rank deviation — graded by what a holder must act on. Triggers on "基金跟踪", "持仓基金有没有问题", "基金预警", "盯一下这几只基金", "经理换人了吗", "fund watch", "规模异动".
-
zai-org Skill Cash ForecastA 13-week rolling direct cash forecast — opening cash, AR-ageing-driven receipts, disbursements (payroll, AP, tax, debt service, capex), closing cash, and headroom against a covenant or minimum balance, with an explicit collection curve and DSO assumption and a downside case. Triggers on "13周现金流", "滚动资金预测", "资金计划", "现金流预测", "未来三个月资金够不够", "回款预测", "cash forecast", "13-week cash flow", "liquidity runway".
-
zai-org Bundle Fund ScreenMulti-criteria fund screening across mutual funds, ETFs, and LOFs — by type, performance, risk, size, fees, holdings, manager. Triggers on "筛选基金", "找基金", "fund screen", "哪些基金满足", "近一年收益前10%的股票基金", "重仓XX的基金".
-
zai-org Skill Peer BenchmarkThe company's own metrics against listed comparables — peer set built with search_stocks and confirmed with get_stock_info, metrics from get_stock_financials, aggregated to a median or weighted average with get_stock_financials, and every 口径 adjustment between management accounts and statutory accounts stated. Triggers on "同业对标", "跟同行比", "对标分析", "行业中位数", "我们的毛利率在行业什么水平", "peer benchmark", "industry median", "competitive benchmarking".
-
zai-org Skill Fund ProfileDeep-dive profile of a single fund — performance vs benchmark and peers, risk, drawdowns, size and flows, fees, holdings snapshot, manager tenure. Triggers on "基金画像", "分析这只基金", "XX基金怎么样", "fund profile", "<基金代码> 深度分析".
-
zai-org Skill Risk ScanFast risk-record screen for one company or a batch — 失信被执行, 终本案件, 限制高消费, 司法涉诉, 行政处罚, 股权质押与冻结, 对外担保, 破产重整与司法拍卖, plus adverse media — with severity ranking. Triggers on "风险排查", "有没有失信", "涉诉情况", "被限高了吗", "有没有破产重整", "黑名单筛查", "risk screen", "批量排查供应商".
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 repo, issue, setup. 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.