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.
-
skyllwt Bundle Daily Arxiv运行或管理每日 arXiv 推荐 feed。用于手动获取新论文推荐、配置/检查/停用 GitHub Actions 定时任务、邮件 digest,以及显式高置信 auto-ingest。
-
skyllwt Skill Paper Draft从 PAPER_PLAN 起草 LaTeX 论文:逐 section 从 wiki 取材撰写 + 生成 figures/tables + BibTeX 验证 + de-AI polish
-
skyllwt Skill Exp Pilot Run预实验执行 — 读取 Pilot Spec YAML,撰写预实验代码,运行实验(运行前需向用户确认,申请用户手动检查),返回结果。由 /ideate Phase 5 调用。不修改 wiki 页面,不判定 pass/fail。
-
skyllwt Skill Exp Pilot Eval预实验结果评估 — 读取预实验结果,应用成功标准,更新 idea 页面(pilot_result,失败时更新 failure_reason),生成 PILOT_VERDICT_REPORT。由 /ideate Phase 5 在 /exp-pilot-run 之后调用。
-
yigityildiz0 Skill Nimble Map ReferenceReference for nimble map command. Load when discovering URLs on a site before bulk extraction. Contains: all flags (limit 1-100000, sitemap.
-
hassaan146 Skill Animated WebsiteTurn any video into a luxury scroll-animated website with parallax effects
-
hassaan146 Skill Morning BriefingDaily industry scan with top content opportunities and urgency levels
-
hassaan146 Skill Contract ReviewerReview any contract and flag what matters before you sign. Use this skill when the user says "review this contract", "should I sign this", "check this agreement", "contract review", "what does this contract say", "flag anything bad", "review my lease", "NDA review", "freelance contract", or pastes a contract, agreement, terms, or legal document they need reviewed before signing.
-
hassaan146 Skill Explainer GraphicCreate visual infographics using real-world analogies
-
hassaan146 Skill Consolidate MemoryReflective pass over your memory files — merge duplicates, fix stale facts, prune the index.
-
hassaan146 Skill Token OptimizationUltra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
-
hassaan146 Skill Difficult Conversation PrepPrepare for tough conversations with a script, talking points, and responses to likely pushback. Use this skill when the user says "difficult conversation", "tough conversation", "hard talk", "how do I tell them", "I need to have a conversation about", "prep me for a confrontation", "how to bring up", "negotiate", or any variation of needing to have an uncomfortable or high-stakes conversation.
-
nota-america Skill Open Gstack BrowserLaunch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.
-
nota-america Skill Open Gstack Browser 2Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.
-
carlkibler Bundle Handle PrHandle GitHub PR comments: assess, fix approved findings, test, commit, and reply.
-
carlkibler Bundle Post MortemAnalyze a failure, find its cause, capture learnings, and prevent recurrence.
-
carlkibler Bundle Decision LogRecord a technical or product decision, alternatives, and rationale for future agents.
-
carlkibler Bundle Scope HammerCut brainstorm output to a shippable MVP: delete, mock, reuse, or ship.
-
carlkibler Bundle Chezmoi DriftCheck chezmoi dotfiles for drift, unmanaged files, and broken skill links.
-
carlkibler Bundle First ContactRed-team onboarding and first use to find confusion, broken expectations, and abandonment.
-
carlkibler Bundle Support StormSimulate launch support load and identify fixes that reduce maintenance.
-
carlkibler Bundle Contacts UnifyMerge and dedupe macOS, iCloud, Google, Zoho, or VCF contacts with reviewable provenance.
-
carlkibler Bundle Visual QA LoopRun before/after visual QA for local UI changes with screenshots and concise findings.
-
carlkibler Bundle Changelog WriterDraft plain-language changelog entries from Git history, optionally updating CHANGELOG.md.
-
carlkibler Bundle Release OperatorRun a CLI or app release: verify, version, test, publish, and verify installs.
-
carlkibler Bundle Remote Host VerifierCompare commands, versions, config, and behavior across local and SSH hosts.
-
carlkibler Bundle Parallel Isolated App TestingPlan isolated parallel test lanes for desktop apps and local tools with shared state.
-
cbusillo Bundle PlanLegacy local plan files only. Use only when explicitly requested; use github-plan for GitHub-backed planning.
-
cbusillo Bundle PeopleResolve named humans, collaborators, users, reviewers, assignees, managers, clients, contacts, GitHub handles, nicknames, aliases, or likely misspellings into private local identity and contact context when identity may affect communication, routing, memory cleanup, rollout friction, GitHub planning, reviews, summaries, or follow-up. Use the optional global people index under Code home plus repo-local `.local/people.yaml` overlays when available, and continue normally when no local people context is configured.
-
cbusillo Bundle LaunchplaneUse for Launchplane-managed product/runtime state, secrets, config, deployments, rollout direction, product ownership boundaries, merge-train flow, and audited operator mutations. Use with github-plan when Launchplane work needs to stay aligned with a durable plan, issue graph, blockers, or rollout sequence. If authority is unknown or discovering private infrastructure access, use docs-lookup first.
-
cbusillo Bundle Skill CreatorGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
-
cbusillo Bundle Work CloseoutUse when the user asks to wrap up, clean up, close out, pause, park, hand off, determine what remains before stopping, preserve plan direction for the next session, update or remove stale plans/handoffs, reconcile issue graph state, remove transient artifacts, or asks whether they can exit. Coordinates GitHub plan cleanup, safe git/worktree hygiene, artifact cleanup, and final state summaries. Safe-to-exit and closeout final answers must include a Love Gate section with explicit `Love:` and `Do not love:` entries before the safe-to-exit verdict.
-
ysyecust Skill Laravel Verification日本語翻訳:このファイルは laravel-verification 用の日本語翻訳が必要です
-
yigityildiz0 Bundle Banner Design 2Design platform-ready banners, covers, display ads, website heroes, and print headers with clear hierarchy, safe zones, responsive crops, accessible.
-
yigityildiz0 Bundle Nimble Search ReferenceReference for nimble search command. Load when searching the live web. Contains: all flags, 8 focus modes.
-
yigityildiz0 Bundle Nimble Extract ReferenceReference for nimble extract command. Load when fetching URLs or scraping pages. Contains: render tiers 1-3, all flags, browser actions, network capture.
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 daily-arxiv, paper-draft, exp-pilot-run. 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.