Development

Programming, frameworks, implementation, frontend, backend, and app development

skills in category: 66,240
pages available: 2,760

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse development skills

Showing 13,585–13,608 of 66,240 skills

Stack DetectADetect language, framework, database, spatial libraries and tile stack from repo files before DB, dashboard or deploy work. Python, .NET, Node/Next.js, Expo.developmentpythongoVotes: 0GitHub stars: 8
New ToolAScaffold a new AGIS dashboard tool: page, client component, API route, sidebar entry, worker stub.developmentreactapiVotes: 0GitHub stars: 8
Inference BackendAFlask inference backend on Hugging Face Spaces: job lifecycle, endpoints, telemetry, model loading, limits, proxy routes.developmentnextjsflaskVotes: 0GitHub stars: 8
Gee Api RoutesAServer-side Earth Engine in Next.js API routes: init once, promisified evaluate, layers, palettes, tile URLs, validation, timeouts.developmentgonextjsVotes: 0GitHub stars: 8
AuditASecurity and performance audit of the AGIS dashboard into docs/AGIS-AUDIT.md.developmentbashapiVotes: 0GitHub stars: 8
Agis ArchitectureALayout and conventions of the AGIS Next.js dashboard: routes, component layers, workers, backends, env vars.developmentreactnextjsVotes: 0GitHub stars: 8
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
UpgradeAUpdate marketplace, bundle and every module; show changelog since the installed version; apply migration notes; re-run doctor.developmentnodegitVotes: 0GitHub stars: 8
HelpAList all toolkit commands and agents by module. Use when asked what the toolkit can do or how to run something.developmentgodockerVotes: 0GitHub stars: 8
DoctorACheck runtimes, GIS libraries, DB clients, installed modules, secrets hygiene, repo standards and toolkit version; print pass/fail with fixes.developmentpythonshellVotes: 0GitHub stars: 8
Quality RetrofitAScan an existing codebase and bring it into compliance with strict quality standards — style, formatting, linting, type checking, dead-code removal, magic-number and literal extraction, sanitizer wiring, secret scanning, and CI-ready gates. Extends existing configuration rather than replacing it, and lands changes in reviewable phases with tests green between each. Use when the user says "retrofit", "clean up this codebase", "add quality gates", "enforce standards", "fix lint", "remove dead c...developmenttypescriptpythonVotes: 0GitHub stars: 2
Project SetupBScaffold a new project from product discovery through production-oriented quality gates. Runs a multi-round Grill Me interview covering users, outcomes, scope, brand assets and colors, accessibility, platforms, signing, distribution, service model, data, security, operations, and release pipeline before stack selection. Scans first and reuses or extends existing code, assets, and configuration instead of creating parallel duplicates. Creates a confirmed PROJECT_BRIEF, README, CHANGELOG, and P...developmenttypescriptpythonVotes: 0GitHub stars: 2
Feature DeliveryADeliver scoped features and behavior changes in existing projects. Scan and enhance canonical code, clarify only the requested delta, map requirements to acceptance and tasks, verify readiness, implement with real tests and red drills, reconcile completion, and resume from current evidence. Use for adding a feature, extending behavior, implementing a scoped change, or resuming delivery. Use project_setup for a new project and quality_retrofit for a quality-only retrofit. Do not apply this ful...developmentpythongoVotes: 0GitHub stars: 2
ScaffoldA在当前项目目录里铺设方法论脚手架（CLAUDE.md + docs 八件套 + .gitignore + README）。后端技术栈固定为 Go（版本基线见 skill 内表格），数据库由 Claude 按项目意图判断。用户说"搭脚手架/初始化项目/开新项目/scaffold"时触发；用户描述要做一个新产品/工具/网站且当前不在项目目录时也触发（auto 模式，配合 auto-scaffold 常驻规则）。developmenttypescriptgoVotes: 0GitHub stars: 2
Sop GenerateAGenerate a screenshot-backed business SOP (operating manual) for any deployed internal web app. Trigger phrases: generate business SOP, operating manual, sop-generate, write an operating procedure doc for this system. Distinguish this from a development-process SOP — this skill produces a manual for "how business staff operate this system," not a code/deployment procedure doc.developmentgoshellVotes: 0GitHub stars: 2
ScaffoldALay down the methodology scaffolding in place inside the current project directory (CLAUDE.md + the eight-doc set + .gitignore + README). The backend stack is fixed to Go (version baseline in the table inside the skill); Claude decides the database based on project intent. Triggered when the user says "set up scaffolding / initialize project / start new project / scaffold"; also triggered when the user describes wanting to build a new product/tool/website while not currently inside a project ...developmenttypescriptgoVotes: 0GitHub stars: 2
ScaffoldA在当前项目目录里铺设方法论脚手架（AGENTS.md + docs 八件套 + .gitignore + README）。后端技术栈固定为 Go（版本基线见 skill 内表格），数据库由子代理按项目意图判断。用户说"搭脚手架/初始化项目/开新项目/scaffold"时触发。developmenttypescriptpythonVotes: 0GitHub stars: 2
Ui SweepA在 SOP 截图前把全站可交互元素系统性点一遍、改完一批 UI 后做回归扫描、用户说“把所有按钮点一遍”、或需要一次交互冒烟测试时触发。用 agent-browser 驱动 + 通用化遍历引擎,逐屏逐元素点击观察并八分类记账,产出 JSONL 台账、每屏截图与报告。developmentrustgoVotes: 0GitHub stars: 2
Ui SweepATriggers before SOP screenshots to systematically click every interactive element on the site, as a regression sweep after a batch of UI changes, when the user says \"click through all the buttons\", or whenever an interaction smoke test is needed. Driven by agent-browser plus a generalized traversal engine: click and observe every element on every screen, log to an eight-category ledger, and emit a JSONL ledger, a per-screen screenshot, and a report.developmentrustgoVotes: 0GitHub stars: 2
Speak HumanAClaude 要开口提问(尤其是用 AskUserQuestion 抛选项)或组织任何对用户的表达输出时必须遵守的说话纪律——每次提问前过一遍自检清单,每次输出前过一遍表达纪律。规则源自作者 548 次真实抉择记录的数据挖掘,不是抽象礼仪。手动触发用 `/speak-human`;若已 touch 常驻标志文件则每个会话开局自动注入,全程有效。developmentpythongoVotes: 0GitHub stars: 2
Speak HumanADiscipline Claude must follow whenever it's about to open its mouth — asking a question (especially via AskUserQuestion with options) or shaping any output aimed at the user. Run the self-check before every question, and the expression discipline before every output. The rules come from data-mining 548 real decision records the author made — not abstract etiquette. Trigger manually with `/speak-human`; if the always-on flag file has been touched, it auto-injects at the start of every session ...developmentpythongoVotes: 0GitHub stars: 2
SettleATurn a rough idea or underspecified repository change into a decision-complete implementation by inspecting the codebase, discovering intent, resolving material decisions through evidence-backed rounds, then implementing and verifying. Use when the user invokes /groundwork:settle, /settle, or $settle with or without a task, or asks to be brainstormed, grilled, or questioned before coding. Do not use for explanation-only work or pure research.developmentrustgoVotes: 0GitHub stars: 5
Speckit ClarifyAFixture stub — exists so pre-flight's invocation-form detection has a hyphen-skill install to find. Never invoked.developmentVotes: 0GitHub stars: 7
Speckit ClarifyAfixture placeholder - another agent scaffolded this tree; the probe must not adopt itdevelopmentVotes: 0GitHub stars: 7
Speckit ClarifyAfixture placeholder - a local install holds invocationForm at hyphen-skillsdevelopmentVotes: 0GitHub stars: 7