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.
-
tools-only Bundle 1194 2025 11 01 Claude Desktop Troubleshooting 0ff9062bSession Learning Capture: Claude Desktop Troubleshooting & Configuration Optimization
7 -
adobe Bundle Direct 2Set a redesign direction for an existing website. Analyzes the user's intent, picks a palette and visual direction, and writes the target spec (PRODUCT.md, DESIGN.md, DESIGN.json) plus a reasoning trace at stardust/direction.md. Use when the user asks to redesign a site, refresh the design, set a new design direction, define a redesign target, or invokes `$stardust direct` (`/stardust:direct` in Claude Code).
142 -
adobe Bundle Uplift 2One-shot brand-faithful presales redesign of a website page. The user provides only the URL; everything else — extraction, tension identification, three differentiated variants (one fully cinematic), validation — is derived from the captured brand surface. Use when the user asks to "uplift", "refresh", or "redesign a site for presales" without wanting to coordinate the extract / direct / prototype chain themselves.
142 -
adobe Bundle DynamicsFind, classify, triage, re-implement and verify a source site's dynamic surface (APIs, search, forms, modals, media, tags, client-rendered and sheet-backed content) during a migration to a platform. Migration-bound — invoked by prepare-migration, replica, migrate and rollout, or standalone on an already-migrated site; never for redesign-only work.
142 -
adobe Bundle Create Site 2Use this when a user wants to create a brand-new AEM Edge Delivery site from scratch and no GitHub repository or DA content exists yet — triggers include 'set up a new site', 'create a new EDS project', or 'onboard a new site'. Covers creating the GitHub repo from the boilerplate, installing aem-code-sync, seeding initial DA content (nav, footer, homepage), and returning a live preview URL. For importing or migrating existing pages use page-import; for building blocks on an existing site use content-driven-development.
142 -
adobe Bundle Find Test Content 2Use this when you need to find existing pages that already use a specific block in an AEM Edge Delivery Services project, for example to locate test content or examples during block development. Covers reporting page URLs with occurrence counts and block variants. This searches existing content; to import a new page from a URL use page-import.
142 -
adobe Bundle Commerce App Admin UI 2Add or modify Adobe Commerce Admin UI extensions on the commerce/backend-ui/2 extension point: custom grid columns, mass actions, order view buttons, a custom Admin menu entry, and custom ACL resources. Use whenever the user wants to extend the Commerce Admin — add a column to the order, product, or customer grid, add a bulk/mass action to a grid, add a button to the order view page, add a custom menu item or page, or declare custom permissions the app checks itself — even when they don't name the extension point.
142 -
adobe Bundle Commerce App Eventing 2Add or modify Commerce and external event subscriptions, configure event field extraction and filter rules in an Adobe Commerce app. Use when the user wants to set up event-driven workflows triggered by Commerce operations (such as order placement or catalog changes) or third-party systems. Requires a base app initialized with commerce-app-init.
142 -
redpanda-data Bundle Connect Cdc Mongodb 2Streams change data capture from MongoDB into Redpanda or Kafka using Redpanda Connect's mongodb_cdc input, built on MongoDB Change Streams over a replica set or sharded cluster. Use when configuring mongodb_cdc, setting up Change Streams, enabling an initial snapshot before live streaming, choosing between update_lookup and pre_and_post_images document modes, or checkpointing with resume tokens in a cache resource. Also covers Redpanda Enterprise destination features like Iceberg Topics, Tiered Storage, and server-side Schema ID Validation, all of which require a Redpanda Enterprise license.
6 -
redpanda-data Bundle Connect Cdc Tigerbeetle 2Guides setup and operation of the tigerbeetle_cdc input in Redpanda Connect, which streams change data capture from a TigerBeetle financial transactions database into Redpanda or Kafka. Use when configuring tigerbeetle_cdc, connecting to a TigerBeetle cluster, choosing a persistent progress_cache for checkpointing, filtering settled vs pending transfers, routing by ledger, or resolving cgo-build or duplicate-event issues. Unlike the other CDC inputs, tigerbeetle_cdc is a certified community connector and does not require an Enterprise license, though it can still land data on Enterprise destination features like Iceberg Topics and Tiered Storage.
6 -
skillbench-ai Skill SigninSign in to SkillMeter
-
hlnd2t Skill Find Cnetworkgameserverbase CreatefakeclientFinal-guarantee fallback for the find-CNetworkGameServerBase_CreateFakeClient preprocessor. Recovers CNetworkGameServerBase_CreateFakeClient in CS2 engine2.dll / libengine2.so when the string-xref preprocessor cannot resolve the function. Use this skill only after the deterministic preprocessor returns failure. Trigger: CNetworkGameServerBase_CreateFakeClient
-
skillbench-ai Skill SignoutSign out of SkillMeter and stop all telemetry
-
skillbench-ai Skill BackfillManually trigger or inspect SkillMeter historical transcript backfill
-
skillbench-ai Skill TelemetryReview and toggle SkillMeter telemetry for local organization repositories
-
wuyoscar Bundle Jev ActChoose one legal next action in a browser, desktop, game or simulation. Supply fresh observed state and available actions. The host or simulator executes and checks the result; selection does not grant permission.
-
wuyoscar Bundle Jev EvalJudge supplied outputs against explicit criteria, including code-change reviews and authorized safety evaluations. Use for evidence-backed review leads, rubric judgments, or batch, multi-turn and team transcript evaluation; not permission to merge or run targets.
-
wuyoscar Bundle Jev DocumentsLocate, select, extract and verify evidence in documents or observed code inventories. Use for source-span extraction, passage reranking, claim checks or choosing code locations to inspect. Preserve citations and no-match outcomes; use required graph tools for exact code lookup.
-
baijunjie Skill Commit按 Conventional Commits 规范生成 Git 提交。用于提交代码、撰写 commit message、选择 type/scope、归纳多点改动等场景。
-
baijunjie Bundle Cron给当前项目装上(或更新)一套 crontab 定时任务安装器——任务清单 tasks.conf 加 install.sh / uninstall.sh,随仓库提交。用于"给这个项目配定时任务""装个 cron 安装脚本""把脚本挂到 crontab 上""加一个每天跑的定时任务"等场景。
-
baijunjie Bundle Bug Fix修复 bug。用户指定工单或直接描述缺陷时按它修,没指定时到 docs/bugs/ 里挑一个;先复现再定位根因,根因没定位到不许动手。bug 是代码与产品文档不符,只改代码不改产品文档;确实要改产品设计的必须先问用户。修完验证通过就删掉工单。用于「修这个 bug」「找个 bug 修」等场景。
-
baijunjie Bundle Plan Exec根据开发文档执行开发任务。用户没指明做哪份时自行挑选当前最适合开工的里程碑;按编号顺序读取 docs/development 下的开发文档并逐个实现,边做边勾文档里的 checkbox;里程碑做完后把该固化的内容整理进产品文档,自足的里程碑随即删除,给后续里程碑留了过渡层或未了结的账的则写下落地状态、留到账清为止。
-
baijunjie Bundle Plan Write开发文档输出。把已讨论确定的方案整理成开发文档,按 docs/development/YYYYMMDD-{简述}/ 目录、按可独立测试合并的里程碑拆分并编号(只有一个里程碑时就只写一份 README.md),只写设计不写实现代码。
-
baijunjie Skill Find Issues在指定的 Git 仓库中搜索与问题描述相关的 Issue 和 PR。用于"这个问题上游有人提过吗""帮我搜下 xxx 仓库的 issue""查查有没有相关 PR"等场景。
-
baijunjie Bundle Dev Memory给当前项目装上(或更新)项目级 dev-memory skill,让开发记忆的读写规则随仓库提交。用于"给这个项目配开发记忆""初始化 dev-memory""更新项目里的记忆 skill"等场景。
-
talent-summoner Skill Talent SummonerSource and review hiring candidates through Talent Summoner, monitoring asynchronous work through completion. Use for creating or resuming a sourcing session, editing an ideal candidate profile, finding more candidates, saving reviews, finding work emails, or preparing outreach.
-
baijunjie Bundle Codex Bridge在当前用户环境给 Codex 装上(或更新)读取 Claude 规范的 `claude` skill,让 Codex 开工前先盘点用户级与项目级的 CLAUDE.md、skills、agents、settings,并把兼容的工作流用于本次任务。用于"让 Codex 也认 Claude 的规范""Codex 读不到我的 CLAUDE.md""配一台新电脑的 Codex""同步 Codex 侧配置"等场景。
-
chartyr Skill Trellis CheckComprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions.
-
hlnd2t Bundle Init GamebinInitialize this repository's disposable local game binaries and per-binary BinSync auto-recovery sidecars for an exact GAMEVER from download.yaml or its latest entry. Use only when explicitly asked to initialize gamebin/bin state for a CS2 game version.
-
taichuy Bundle QA Evaluation验收或审计 1flowbase 当前任务、PR 或项目质量。对照已确认目标、设计/架构约束和当前实现收集证据,识别开发偏离并报告已验证、失败与未验证;不默认扩展为全量测试或修复。
-
taichuy Skill Test Driven DevelopmentChoose risk-proportionate tests and verification evidence for 1flowbase behavior changes. Define observable expectations before implementation, reuse failure evidence, and control execution cost; use qa-evaluation for final acceptance.
-
adobe Bundle Workfront Local TestingUse when making Workfront load your locally running App Builder extension, or when a local extension that worked before has stopped appearing. Reach for this whenever the user is: trying to preview their local build inside Workfront before deploying; setting `extensionOverride` in localStorage but Workfront still shows the published version; seeing buttons, widgets, or left-panel items not appear in Workfront even though `aio app dev` is running; hitting a cert warning on localhost that blocks Workfront from loading the extension; seeing a local extension silently break after a Chrome update (Chrome 142+ blocks localhost connections); asking what value to set `extensionOverride` to and exactly where to set it in the browser; asking whether a custom-form widget should appear in the field picker; or wondering if Workfront admin rights are needed to see locally-loaded extension points. Separate from `appbuilder-workfront` (the umbrella) and `appbuilder-project-init` (scaffolding / dev server).
142 -
hlnd2t Bundle Fix CppheadersUse when hl2sdk_cs2 C++ headers must be repaired to match the latest vtable or record-layout YAML references. Runs run_cpp_tests.py to obtain layout diffs, maps failing cpp_tests entries to their configured headers, edits only those headers, and repeats validation until the differences are resolved. Triggers: fix cpp headers, fix-cppheaders, repair vtable layout, repair record layout, header layout differences.
-
hlnd2t Bundle Create Cpp TestsCreate a new cpp_tests entry for validating a C++ interface vtable layout against binary reference YAMLs. Creates the .cpp test file in cpp_tests/ and appends a configs/<GAMEVER>.yaml entry under cpp_tests:. Use when a user asks to add vtable layout validation for a new hl2sdk_cs2 interface class.
-
hlnd2t Bundle Cleanup WorkspaceClean up the local workspace after a dev branch has been merged into main. Verifies the current dev branch is fully merged into origin/main, then switches to main, pulls the latest, deletes the local dev branch, and deletes the remote dev branch if it still exists. STOPS and warns the user if the current branch is not yet merged. Triggers: cleanup workspace, cleanup branch, delete merged branch, finish dev branch, post-merge cleanup
-
hlnd2t Skill Get Func From YAMLLoad function information from a pre-generated YAML file. Use this skill when you need function address, size, signature, and optional vtable metadata before downstream analysis. This skill checks for existing function YAML files and errors out if not found.
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 1194-2025-11-01-claude-desktop-troubleshooting_0ff9062b, direct, uplift. 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.