Software Development skills · page 47

Agent skills for software development, most popular first. Each one is a SKILL.md folder that Claude loads when a task needs it.

2,761 skills · showing 2209–2256

  1. 2209Audiencesadaptyteam/adapty-skillsUse when a user wants different users to see different paywalls or flows at the same placement — by country, language, app version, platform, revenue, subscription state, install date, a custom attribute, or attribution — or wants to create, edit or reuse an Adapty segment through the CLI. Triggers on "show this paywall only to users in Germany", "target users on version 2.0", "a cheaper paywall for non-payers", "users with my custom attribute should see…", "create a segment", "add an audience to my placement", "who sees which paywall".9
  2. 2210Find Implicit State Machineskr4chinin/skillsAudit a codebase for implicit state machines (state spread across flags, status fields, timers and callbacks). Use when asked to find them or to trace impossible states, stuck loading, missing resets or async races. Catalog machines with no defect only when asked for an inventory.9
  3. 2211Migrate Placementsadaptyteam/adapty-skillsUse when someone wants to move an app from paywall placements to Flow Builder flows — "migrate my placements to flows", "switch my paywalls to flows", "we have 40 placements on paywalls and want flows", or a bulk request across many apps or paywalls. Creates NEW flow placements alongside the existing paywall ones and hands back the old→new mapping plus the SDK call change. Never converts a placement in place — the backend refuses a type change. Complements `flow-generator` (which builds and publishes flows) and `adapty-integration` (which owns the app-side call sites).9
  4. 2212Mxl CLITaoELi/MaxwellLinkThis skill should be used when users need to initialize, clean, or configure MaxwellLink workspaces using the mxl command family.9
  5. 2213Prune Commentskr4chinin/skillsAudit code comments and plan which to delete, keep, rewrite or replace with a refactor. Use when asked to prune a codebase's comments, or to sort workaround comments into root-cause fixes and safe deletions.9
  6. 2214Revolut X Authrevolut-engineering/revolut-agent-skillsRevolut X API authentication setup, Ed25519 keypair generation, and request signing. Use when the user asks to set up Revolut X API access, configure API keys, generate an Ed25519 keypair, sign requests manually, or debug 401/403/409 authentication errors.9
  7. 2215Revolut X Public Market Datarevolut-engineering/revolut-agent-skillsRevolut X public market data — public order book (5 price levels) and latest 100 trades across all pairs. No authentication required. Use when the user wants a quick price check or recent trade data and has not configured API keys, or asks about public market data.9
  8. 2216Robodk APIRoboDK/RoboDK-Agent-SkillsReference for writing, porting, or debugging application code against the RoboDK API — the Robolink/Item/Mat SDK for driving RoboDK from Python, TypeScript, C++, C#, MATLAB, C, or Visual Basic. Use when a user wants to write a script that connects to RoboDK, reads/writes item poses and joints, runs MoveJ/MoveL/MoveC, builds targets/frames/tools/programs, converts between Euler/pose conventions, or ports RoboDK API code from one language to another.9
  9. 2217Robodk Driver BuilderRoboDK/RoboDK-Agent-SkillsWrite, port, or debug a RoboDK robot driver — the standalone console program (Python script or compiled executable) that lets RoboDK move a real robot live over its own stdin/stdout protocol ("Online Programming"), as opposed to a post processor generating an offline program file. Use when asked to "write/add a driver for <robot>", "port this driver to another language", "the robot driver doesn't respond to <command>", "support live/online programming for a new robot", or when handed an existing driver file to fix or extend. Distinct from robodk-real-robot-control, which operates an already-wo9
  10. 2218Robodk Post Processor BuilderRoboDK/RoboDK-Agent-SkillsRead, write, debug, and extend RoboDK post processors — the Python files defining a `RobotPost` class (MoveJ/MoveL/MoveC/setFrame/setTool/setSpeed/setZoneData/setDO/waitDI/RunCode/RunMessage/ProgSave...) that translate a RoboDK simulation program into a real robot controller program. Use this skill whenever the user mentions RoboDK, post processors, "the post", a Posts folder, or generating/fixing robot controller code in any dialect (KRL .src, RAPID .mod, Fanuc .ls, Motoman .jbi, Siasun .spf, URScript, Kawasaki .as, G-code) — including indirect asks like "my robot program comes out wrong", "a9
  11. 2219Robodk Real Robot ControlRoboDK/RoboDK-Agent-SkillsThe ONLY skill in this repo allowed to move a real, physical robot — via robot.Connect() and RUNMODE_RUN_ROBOT/PROGRAM_RUN_ON_ROBOT, using RoboDK's robot drivers (Online Programming). Every other RoboDK skill here is simulation-only by design; redirect here the moment a request is unambiguously about the real robot moving, not the simulated one — phrasings like "move the real robot", "run this on the actual/physical robot", "connect to the robot and jog it", "online programming", "drive the robot live". Do not use for anything that stays in simulation, for generating a program to transfer late9
  12. 2220Finding Unknownssidneyswift/skillsSurface the gaps between what a task description says and what the work actually requires, before writing code. Use before implementing anything ambiguous, large, or unfamiliar; when the user asks "what am I missing", wants options or design directions, needs a mock or plan to react to, wants to be interviewed about a spec, is porting from a reference implementation, or gives a vague creative request they lack vocabulary for. Make sure to use this skill whenever the map (prompt/spec) might not match the territory (codebase/real requirements) — even if the user does not say "unknowns.9
  13. 2221Spec Goalssidneyswift/skillsUse when someone asks 'help me write a /goal', 'turn this into a goal', 'draft a goal for Codex', 'spec this for /goal', 'is this a good goal', or 'sharpen this objective'. Turns a defined, durable objective into a ready-to-paste Codex `/goal` with a measurable outcome, verification surface, constraints, boundaries, iteration policy, and blocked-stop condition. If the outcome, evidence, constraints, or approach still contains load-bearing unknowns, use flex-finding-unknowns first. Do NOT use this skill to execute the work.9
  14. 2222Vscode Readykargnas/skillsUse only when the user asks to set up VS Code/Cursor launch, debug, run, or tasks configs (e.g. "make this project VSCode-ready"). Do not run on your own.9
  15. 2223Ziniao Access Policyziniao-open/skills紫鸟访问策略管理:网页访问规则、网页/网页分组、规则生效成员/账号、账号绑定策略的查询和维护。当前无快捷命令,全部通过 ziniao-cli api 直调。9
  16. 2224Ziniao Openapi Explorerziniao-open/skills紫鸟 API 探索:当现有快捷命令无法满足需求时,通过通用 api 命令和已知路径清单探索紫鸟全部 73 个 API 接口。9
  17. 2225Ziniao Sharedziniao-open/skills紫鸟 CLI 共享基础:应用配置初始化、ZClaw 客户端与 Bridge 就绪、统一 apiKey 认证、错误处理、输出格式和安全规则。当用户需要首次使用 ziniao-cli、配置 API Key、启动紫鸟客户端、登录 ZClaw 或排查认证/Bridge 问题时触发。9
  18. 2226Ziniao Skill Makerziniao-open/skills创建 ziniao-cli 的自定义 Skill。当用户需要把紫鸟 API 操作封装成可复用的 Skill(包装原子 API 或编排多步流程)时使用。9
  19. 2227Challenge Memilistu/agent-skillsDirect technical advisor mode for counting/estimation and architecture/design9
  20. 2228Code Reviewer Cn5tldr/claude-skills代码审查,生成中文报告,基于 anthropics/skills 和 obra/superpowers 项目9
  21. 2229Hex Setuphex-inc/hex-skillsInstall, authenticate, and configure the Hex CLI for use with CoCo. Use when: setting up Hex, installing Hex CLI, authenticating with Hex, configuring Hex profiles, verifying Hex connection, Hex auth error, Hex not found, brew install hex. Triggers: install hex, hex setup, hex auth, hex login, hex configure, hex not found, hex authentication, hex profile, hex token, connect to hex.8
  22. 2230Octomeshmakers/octo-claude-skillsPrimary entry point and router for ALL OctoMesh tasks. Drives the octo-cli for platform administration (users, roles, groups, tenants, clients, identity providers, blueprints, CK catalog/library management, stream-data archives, communication adapters/pipelines, AI services) and explores the data model and runtime instances via GraphQL. Routes specialized work to sibling skills. When unsure which OctoMesh skill to use, start here. Trigger on: OctoMesh, octo-cli, CLI command, environment switch, auth/login, AuthStatus, tenant, temporary tenant, test tenant, user, role, group, client credentials10
  23. 2231Pipeline Expertmeshmakers/octo-claude-skillsAuthoring, reading, editing, debugging, and validating OctoMesh ETL pipeline YAML — the node-by-node config, DataContext/JSONPath data flow, triggers, transformations, entity CRUD via CreateUpdateInfo/ApplyChanges, archive (CrateDB) writes, inter-pipeline chaining within a DataFlow, and deployment/debug troubleshooting. Use whenever someone builds or fixes a pipeline definition or asks what a node does. Trigger on: pipeline YAML, pipeline node, node configuration, DataContext, ForEach, For, DataFlow, PipelineTrigger, cron schedule, ToPipelineDataEvent, FromPipelineDataEvent, FromPipelineTrigge10
  24. 2232Mini Speczot/mini-spec**MANDATORY: Invoke BEFORE writing or modifying any code.** Without `design/design.md` you lack critical knowledge of component relationships, responsibilities, and code mappings — changes made without this context risk breaking architectural invariants. Do NOT explore code with other tools first. Load this skill before doing anything else.5
  25. 2233NcdVincent-the-gamer/skillsncd (ncm dumper) is a CLI for batch-converting .ncm files to .mp3. Use when the user says using ncd to convert .ncm files.9
  26. 2234Node CLI CreatorVincent-the-gamer/skillsBuild a Node.js CLI in TypeScript — commands parsed with cac, code built with tsdown, deps updated with taze, source run with tsx. Use when the user wants to create, develop, or add features to a Node.js command-line tool or CLI project.9
  27. 2235Review Changejbaruch/agentic-context-registryReview a Go change when the user asks to inspect a diff for correctness.9
  28. 2236Review Changejbaruch/agentic-context-registryReview a proposed code change and its evidence when asked to assess implementation quality.9
  29. 2237Sniff LocateJordanGunn/nunchuckList findings in `.sniff/findings.jsonl`, validate anchors, reanchor stale findings when code shifts, and regenerate `.sniff/index.json`.9
  30. 2238Apply Genci Tgcc Ceapasqal-io/agent-marketplaceApply for QPU hours on Ruby (Pasqal Orion), the analogue neutral-atom machine at GENCI/CEA TGCC - via the French eDARI portal or the EuroHPC Quantum Access Pilot call - then get the TGCC computing account. For requests such as "apply for TGCC hours", "eDARI application", "apply for Ruby/Pasqal QPU allocation", "EuroHPC quantum hours", "Quantum Access Pilot", or "attach to a project / rattachement". Access only, not running experiments. Unsure which route fits? Use choose-access-method.9
  31. 2239ArchitectureUserAd/ClaudeSkillsManage architecture documentation in .architecture directory. Use when Claude needs to (1) create/update/delete architecture artifacts (domains, services, contracts, schemas), (2) validate architecture documentation, (3) query service dependencies or technology status, (4) document new services or domains, (5) work with RabbitMQ/Redis/PostgreSQL/ClickHouse/MongoDB/HTTP contracts. Triggers on "architecture", "add service", "add domain", "document service", "create contract", "validate architecture".8
  32. 2240Choose Access Methodpasqal-io/agent-marketplaceDecide which neutral-atom QPU access route to pursue - free CEA/GENCI/ EuroHPC access to Ruby (weeks of lead time, specific eligibility) versus Pasqal Cloud pay-as-you-go (today, any country, a card). For requests such as "how do I get QPU access", "which account should I use", "Pasqal Cloud vs CEA", "do I qualify for free QPU time", or "fastest way to real hardware". Hands off to create-pasqal-cloud-account or apply-genci-tgcc-cea: this skill is the decision, not the sign-up flow.9
  33. 2241Codex AssistantUserAd/ClaudeSkillsRun AI-powered tasks using OpenAI Codex CLI. Use when Claude needs to (1) delegate code analysis or generation tasks to Codex, (2) get a second opinion on code changes, (3) perform parallel AI review, or (4) leverage Codex for specific tasks. Triggers on requests like "use codex to...", "run codex", "ask codex", "codex review".8
  34. 2242Submit to Ceapasqal-io/agent-marketplaceSubmit a Pulser parametric experiment to Ruby, the neutral-atom QPU hosted at CEA/TGCC on the irene supercomputer, over SSH — generate the job bundle, deploy it, launch the ccc_msub jobs, monitor them, collect the results, with no manual copying. The templates are TGCC-specific and say what a sibling Bull or Slurm site needs changed; use qpu-submit for a cloud-API QPU. Triggered by phrases like "submit to CEA", "launch on Ruby", "submit to TGCC".9
  35. 2243Validate Emupasqal-io/agent-marketplaceScan a neutral-atom experiment_spec.json and its Pulser sequence, noiseless and noisy, and return a go/no-go on whether the signal survives the Rydberg device's noise well enough to be worth QPU time. Asks where to run: locally (free, small registers, offered first) or on Pasqal Cloud emulators at the real size. This is the gate before a QPU submission, not the submission. Triggered by phrases like "validate this sequence on the emulator", "check noise retention", "is this worth QPU time".9
  36. 2244Google Go Stylelingengyuan/my-skills按 Google Go Style 编写、重构或审查 Go 代码。用于命名、注释、接口、错误处理、并发、包组织与可维护性决策。9
  37. 2245Insight Collectorlingengyuan/my-skillsAnalyze URLs, source code, images, technical documents, or notes, and archive reusable insights, code snippets, and architecture patterns into a knowledge base. Use when collecting knowledge, archiving technical articles, saving reusable code, or recording insights (收录, 记录一下).9
  38. 2246Morningthatmike1/claude-skillsDaily briefing skill that aggregates yesterday's work context from Claude Code conversations, Codex sessions, git history, and memory files into an actionable morning plan with time estimates and sequencing. Use when user says morning, start of day, or what was I doing yesterday.10
  39. 2247Panelsthatmike1/claude-skillsComic-book layout for work output — bold mini-headers, short chunks, whitespace, and [BLOCKER]/[RISK]/[FYI] severity tags. Keeps full technical accuracy; restructures prose for ADHD scannability. Best for code reviews, implementation plans, and long output. Use when user invokes /panels, says "panels mode" / "panels style" / "panel layout". One of a rotating wardrobe with /detective and /punchy.10
  40. 2248Pelelingengyuan/my-skillsRender Mermaid diagrams as SVG with Pele. Use its JavaScript API for custom rendering, theming and browser integration.9
  41. 2249Portpilot Assistantlingengyuan/my-skillsInspect, diagnose, allocate, and free local development ports using the bundled PortPilot CLI. Use when finding available ports, inspecting port listeners, resolving port conflicts, freeing ports, or managing PortPilot configuration.9
  42. 2250Wardenthatmike1/claude-skillsAll-day accountability on request. Build a flexible day plan together, keep the current block visible, and check in through T3 Code with desktop reminders.10
  43. 2251AI Native CLIChaosRealmsAI/agent-cli-specAI-Native CLI design spec. Use when building CLI tools, designing command-line interfaces, or scaffolding new CLI projects. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description. Includes an audit protocol for verifying CLI compliance.3
  44. 2252Connectredpanda-data/skillsTeaches how to build streaming data pipelines with Redpanda Connect (formerly Benthos): declarative YAML configs with the input/pipeline/output model, processors, and Bloblang mappings for transforming messages. Use when creating or editing a Connect pipeline config, wiring inputs and outputs (Kafka topics, S3, HTTP, databases), writing or debugging Bloblang, or running pipelines with `rpk connect run`. For diagnosing a failing pipeline (lint errors, metrics, tracing, dry runs), see `/redpanda:connect-debugging`; for change-data-capture connectors, see the per-database `/redpanda:connect-cdc-*9
  45. 2253Connect Debuggingredpanda-data/skillsDiagnoses, validates, and monitors Redpanda Connect pipelines. Use when a Redpanda Connect pipeline fails, stalls, drops messages, or won't start; when linting a config with rpk connect lint; tuning log level or format; reading Connect metrics (Prometheus, statsd, json_api) or traces (OpenTelemetry); checking /ready and /ping health endpoints; running a dry-run connection test; or diagnosing connector failures including auth errors, TLS errors, Enterprise license errors, backpressure, and checkpoint/cache issues. Covers Redpanda Connect enterprise features and their config keys: enterprise con9
  46. 2254Cue Research CLIsensedeal/cue-skillsCue 深度研究 CLI(@cueai/cue-cli,命令 cue)使用说明。用于行业/公司/人物/政策/合规类深度调研:一句话发起多智能体研究,输出带来源的 Markdown 报告,可落盘、可续接会话追问、可指定搭子模板。涉及「深度调研」「尽调」「行研」「公司研究」「竞品对比」「政策跟踪」「人物核查」等需要多源检索与交叉验证的场景时使用。8
  47. 2255Rpk Debugredpanda-data/skillsCollect Redpanda diagnostics bundles with the `rpk debug` command group, and look up bundle flags, contents, and procedures in the Redpanda docs. Use when collecting a debug bundle for Redpanda Support or self-triage, running `rpk debug bundle` on a broker host or inside a Kubernetes pod, collecting a cluster-wide bundle through the Admin API with `rpk debug remote-bundle`, or reading a bundle to triage a problem such as an Enterprise feature that stopped working. Applies to self-managed deployments only. For client-side triage of a Redpanda Cloud cluster, see /redpanda:rpk-cluster and /redpan9
  48. 2256Rpk Redpandaredpanda-data/skillsOperate a self-managed Redpanda broker node from the CLI with the `rpk redpanda` command group and `rpk iotune`, and look up node commands and broker properties in the Redpanda docs. Use when starting, stopping, or restarting a broker, preparing a node for production, switching between production, development, and recovery mode, running the autotuner or benchmarking disks with iotune, bootstrapping or editing redpanda.yaml, or taking a broker down for a reboot or upgrade. Self-managed only: these commands act on the broker host and don't apply to Redpanda Cloud. For cluster-wide operations (cl9