agentsclimarketplace

Engineering

98,234 rows, by stacks then stars

  • ACR — Agent Composition Records

    Tethral-Inc/AgentRegistry/io.github.TethralAI/acr MCP server

    1★ repo

    Interaction profile registry for AI agents. Log interactions, query behavioral lenses.

  • SQL Server MCP (macOS)

    TharanaBope/SQL-MCP-Mac-Windows/io.github.TharanaBope/sql-server-mcp-macos MCP server

    1★ repo

    SQL Server MCP with RAG capabilities for macOS (Docker SQL Server support)

  • Github analytics mcp server

    TheNextGenNexus/ai-analytics-mcp-servers/io.github.TheNextGenNexus/github-analytics-mcp-server MCP server

    no license1★ repo

    Get GitHub repository stats, search repos, analyze languages, and compare projects

  • Mcp reverse engineering

    daedalus/mcp_reverse_engineering/io.github.daedalus/mcp_reverse_engineering MCP server

    1★ repo

    A sandboxed MCP tool for reverse engineering with multiple tool integrations

  • Git enhanced

    davidweb3-ctrl/mcp-git-enhanced/io.github.davidweb3-ctrl/git-enhanced MCP server

    1★ repo

    Enhanced Git MCP Server - Code review, commit analysis, and branch management

  • Dingdawg data agent

    dingdawg/dingdawg-agent-1/io.github.dingdawg/dingdawg-data-agent MCP server

    1★ repo

    AI data agent — schema analysis, query optimization, PII detection, pipelines.

  • LionScraper MCP + CLI + HTTP API (Python)

    dowant/lionscraper-mcp/io.github.dowant/lionscraper-python MCP server

    1★ repo

    LionScraper Python: MCP stdio + CLI + HTTP API bridging AI to LionScraper browser extension.

  • Authenticated llm agent

    mikerawsonnz/gosce-agents/io.github.mikerawsonnz/authenticated-llm-agent MCP server

    1★ repo

    JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.

  • Uk parliament erskinemay

    DarkhorseOne/mcp-servers/io.github.nick-ma/uk-parliament-erskinemay MCP server

    no license1★ repo

    MCP server for UK Parliament Erskine May API

  • Whoop mcp server

    rajdeepmondaldotcom/whoop-mcp-server/io.github.rajdeepmondaldotcom/whoop-mcp-server MCP server

    1★ repo

    WHOOP recovery, sleep, strain, and workouts for any AI. Analysis tools, demo mode, fast setup.

  • Api tester

    ryudi84/sovereign-mcp-servers/io.github.ryudi84/api-tester MCP server

    no license1★ repo

    MCP server for API testing: HTTP requests, cURL generation, health checks.

  • Smarter Weather Developer Onboarding

    smarterweather/developer/io.github.smarterweather/onboarding MCP server

    1★ repo

    Agent-first onboarding to Smarter Weather: plans, docs, signup, API keys, MCP config, billing.

  • TWZRD Agent Intelligence

    twzrd-sol/twzrd-trust/io.github.twzrd-sol/twzrd-agent-intel MCP server

    1★ repo

    Trust + receipt layer for x402 agents on Solana: free preflight + paid signed V6 trust receipt.

  • Visus mcp

    visus-mcp/visus-mcp/io.github.visus-mcp/visus-mcp MCP server

    1★ repo

    Security-first web access. Sanitizes pages, blocks injection, redacts PII. Now with PDF/JSON/SVG.

  • TweekIT MCP Server

    equilibrium-team/tweekit-mcp/io.tweekit/mcp MCP server

    1★ repo

    Normalize and convert 400+ file types via TweekIT's hosted MCP endpoint.

  • GoldBean MCP Server

    wuzenghai616-lang/goldbean/xyz.goldbean-api/goldbean-mcp MCP server

    1★ repo

    49 pay-per-use APIs for AI agents via x402. AI, crypto, DeFi, blockchain, weather, search, security.

  • Flutter app

    aneebbaig/app-starter-skills/plugins/app-starter/skills/flutter-app Skill

    0★ repo

    Bootstrap a new Flutter mobile app, or audit and retrofit an existing one, with clean architecture, Riverpod or bloc, FVM-pinned SDK, current packages, and no deprecated APIs. Use when the user wants to start, scaffold, or set up a new Flutter app, a cross-platform mobile app, an Android or iOS app in Dart, or asks to "create a new flutter app". ALSO use on an existing Flutter or Dart codebase when the user asks to audit, review, fix, clean up, refactor, modernize, upgrade, harden, or "bring up to standard" the app, fix analyzer issues, remove deprecated APIs, restructure to clean architecture, or migrate state management to Riverpod or bloc. Handles BYOK LLM apps, backend-backed apps, Play Store release setup, and clean-architecture feature structure.

  • Test gh

    stakiran/gists/.claude/skills/test-gh Skill

    0★ repo

    gh コマンドの動作確認を行う

  • Bash gate add

    mnox/mnox-ai/plugins/bash-gate/skills/bash-gate-add Skill

    0★ repo

    Add a new allow-class (or other extension) to the bash gate hook when a permission prompt surfaces that should have been auto-allowed. Takes the prompting Bash command (pasted text OR a screenshot), runs `bash_gate.py --explain` to diagnose which segment deferred and why, identifies the gap category, surfaces ONE recommendation with confidence score, asks for explicit approval BEFORE building, then dispatches a build subagent to add the class + fixtures + smoke tests. Use when the user says "/bash-gate-add", "/bgate-add", "address this prompt", "fix this gate", "another gate prompt", "auto-allow this", or "the gate should have allowed this".

  • Cc audit

    giovicordova/skills-gc/skills/cc-audit Skill

    no license0★ repo

    Audit a project's Claude Code setup against official Anthropic documentation. Evaluates 9 areas: CLAUDE.md, Rules, Skills, Sub-agents, Hooks, Permissions, Settings, MCP servers, and Feature Selection. Produces a scored AUDIT-REPORT.md with findings that cite documentation sources fetched during the session. Use this skill when the user says 'audit', 'audit my setup', 'review my Claude Code config', 'check my configuration', 'how well am I using Claude Code', 'audit my CLAUDE.md', or wants to assess whether their project is making effective use of Claude Code features. Even if the user only mentions one area (e.g., 'are my hooks right?'), use this skill — it evaluates all 9 areas for a complete picture.

  • Focus

    withqwerty/ship/skills/focus Skill

    no license0★ repo

    Use this skill when the user is mid-build and drifting, scope is creeping, or focus is lost. Trigger on "ship focus", "scope check", "refocus", "what should I cut", "am I scope creeping", "this is getting bigger than expected", "I'm losing focus", "I keep finding things to improve", "should I stop and ship what I have", or "new requirements came in". Also trigger when the user expresses frustration about a task growing beyond its original intent, mentions touching many more files than expected, or asks whether to change direction mid-build. Do NOT trigger for pre-build gut checks (use ship-think) or post-build reviews (use ship-review).

  • Debug pipeline

    LuisHiluy/claude-code-pipeline-skills/debug-pipeline Skill

    0★ repo

    Structured diagnostic runbook for broken AI media pipelines. Walks through symptom → root cause → fix for generator auth failures, stale worker locks, review-app crashes, MCP auth errors, rate limits, and corrupted state files. Use whenever generation jobs fail, workers stop picking up tasks, generated output looks wrong, review tools break, MCP servers error, or any multi-component failure happens in an AI media pipeline. Trigger on "debug the pipeline", "generation is broken", "worker not running", "review app down", "why is this failing", "what's wrong with the pipeline", or anytime the user reports a symptom without yet knowing the root cause.

  • Yfiles init

    yWorks/yfiles-for-html-skills/skills/yfiles-init Skill

    no license0★ repo

    This skill should be used when the user asks to "initialize a yFiles application", "create a new yFiles demo", "scaffold a yFiles project", "set up GraphComponent", or mentions "create app", "new demo", "initialize yFiles", "setup yFiles", or "License.value".

  • Agent optimize

    nakane1chome/claude-skills/skills/agent-optimize Skill

    0★ repo

    Optimize a document for AI agent consumption. Restructures prose into formats that agents parse efficiently while preserving meaning.

    The same file is in 2 other repositories

  • Handoff

    Pawel-Kica/skills-that-ship/skills/handoff Skill

    0★ repo

    Compact the current conversation into a handoff doc a fresh agent can resume from.

  • Recipe url to markdown

    recipes-in-markdown/recipes.md-spec/skills/recipe-url-to-markdown Skill

    0★ repo

    Convert recipe URLs or HTML files to structured Markdown with YAML frontmatter. In chat, paste a recipe URL or HTTP link. In Claude Code or agentic workflows, pass local HTML file paths or directories to batch-process multiple recipes. The skill extracts title, prep time, yield, servings, source, and tags (proteins, spices, cuisine, diet). Ingredient groupings and numbered instructions are preserved. Handles incomplete or malformed inputs gracefully with error callouts in the output. Use whenever you need to convert recipes from web sources to a consistent, queryable Markdown format following the Recipes.md specification.

  • Deploy

    azadmotala/claude-code-team-builder/examples/saas-dashboard/.claude/skills/deploy Skill

    0★ repo

    Deploy TenantFlow to staging or production on Vercel. Handles build, test gate, and Vercel deployment.

  • Architect

    telefrek/vallorcine/skills/architect Skill

    0★ repo

    Run a full architecture decision session for a given problem

  • Prompt paglu

    sushil930/my-claude-skills/skills/prompt-paglu Skill

    no license0★ repo

    World-class AI prompt engineering skill for creating, refining, and enhancing prompts for any LLM task. Use this skill whenever the user wants to: write a new prompt from scratch, improve or refine an existing prompt, enhance a vague instruction into a structured prompt, debug why a prompt isn't working, convert a rough idea into a production-ready prompt, or asks anything related to "prompt engineering", "prompt design", "make this prompt better", "craft a prompt for...", "write a prompt that...", or "Prompt-Paglu". Also trigger when users share a prompt and ask for feedback, optimization, or a rewrite. Even if the user just says "help me prompt Claude/GPT/Gemini to do X", use this skill — do NOT just answer inline without consulting this skill first.

  • Codebase explorer

    madeinoz67/madeinoz-recordmanager-skill/.claude/skills/codebase-explorer Skill

    no license0★ repo

    Deep codebase exploration using semantic search and relationship mapping. Use when you need to understand the current codebase.

  • Apex implement

    zeybek/apex/plugins/apex/skills/apex-implement Skill

    0★ repo

    Use this skill when implementing software changes end to end with language- and framework-independent senior engineering judgment. Apply it to features, bug fixes, refactors, debugging, integrations, migrations, configuration, dependencies, executing a planned `.apex-design/<slug>/` workspace, and production-facing code work that requires inspecting the existing system, controlling risk, preserving contracts, and verifying results. Do not use it for review-only or design-only requests.

  • Code walk

    opendatadiscovery/odd-team/.claude/skills/code-walk Skill

    0★ repo

    Run the feature-advisor query-time subagent over the full ontology to produce a structured impact assessment for a proposed feature or change. Maintainer asks "I want to add X — what's affected?" The agent reads sidecars + concepts.yaml + implicit-adrs.md + refactoring-scopes.md + doc-gaps.md + test-map.yaml + existing adrs/ + live ODD docs (via WebFetch), and emits `lineage/{repo}/feature-walks/{date}-{slug}.md` — a planning aid the maintainer reads BEFORE writing code.

  • Claude api

    simplevaad-debug/superskills/skills/claude-api Skill

    no license0★ repo

    Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

  • Upliftcontrolversion

    uplift-technology-company-limited/uplift-plugins/plugins/upliftcontrolversion/skills/upliftcontrolversion Skill

    0★ repo

    Set up and manage the Uplift auto-increment version system in an Uplift repo (account, the sso service, admin-portal, payment, media, message, subscription, cms, and siblings). Use this WHENEVER the user wants to: add version tags that bump automatically on every deploy, show the running version in the UI or expose it via a /version API, stop OTEL_SERVICE_VERSION from drifting (the hardcoded "1.0.0" bug), make git tags the source of truth for what's deployed, or answer "what version is prod running?". Trigger on phrases like "version bump on deploy", "show the app version", "add a /version endpoint", "auto-increment version", "tag every release", "wire up versioning", even if the user doesn't say the skill name. Mirrors upmove's auto-bump on top of the sso service's existing SemVer/tag convention. (Not about Single Sign-On.)

  • Check performance

    Proportione/proportione-plugins/plugins/check-performance/skills/check-performance Skill

    0★ repo

    Claude Code plugin marketplace + playbook. 9 QA skills (review, security, architecture, performance, WordPress, Terraform) and 8 production guides from an AI-first consultancy.

  • Mcl foundation design

    suwa-sh/multi-cloud-lifecycle-skills/.claude/skills/mcl-foundation-design Skill

    0★ repo

    マルチクラウド基盤(ランディングゾーン)設計用スキル。AWS / Azure / GCP / オンプレミスを対象に、ベンダー中立の canonical model、ベンダー別マッピング、実装仕様、IaC スケルトンを生成する。組織構造、ID、ネットワーク、ポリシー、ログ、課金、セキュリティガードレールをカバーする。クラウド基盤設計、ランディングゾーンアーキテクチャ、組織構造、アカウント/サブスクリプション/プロジェクト階層、ID フェデレーション、ネットワーク分離、ポリシー適用、監査/ログ集約、課金境界、セキュリティガードレールに関する要求で使用すること。1 クラウドのみの言及でも発動する。AWS Organizations/SCP、Azure Management Groups/Policy、GCP Org Policy に関する質問も基盤設計の文脈であればトリガーする。オンプレミス基盤(VMware/OpenStack/ベアメタル Kubernetes 等)やクラウド + オンプレのハイブリッド構成の基盤設計でもトリガーする。

  • Verify test coverage

    matusbu/claude-code-test-automation-skills/.claude/skills/verify-test-coverage Skill

    0★ repo

    Verify test coverage for code changes against the defined test strategy. Use when reviewing a feature branch, commit, or uncommitted changes to ensure adequate test coverage.

  • Init agents md

    Zrzzzz/agent-codebase-skills/init-agents-md Skill

    0★ repo

    为项目初始化「分层 memory 约定」——把跨工具通用规则写到 CLAUDE.md / AGENTS.md, 支持模块嵌套 memory(前后端拆分 / monorepo 的 apps、packages、services), 并支持在 CLAUDE.md ↔ AGENTS.md 之间迁移内容。 支持四种模式: - claude:只写 CLAUDE.md(Claude Code 专属) - agents:只写 AGENTS.md(跨工具开放标准) - both:AGENTS.md 放跨工具通用 + CLAUDE.md 做薄壳引用 - migrate:把现有 CLAUDE.md 内容拆/转到 AGENTS.md(或反向) 本 skill 只管「约定层」:不装 SessionEnd hook——那归 [`init-session-notes`](../init-session-notes/SKILL.md);不初始化 TASKS.md 任务管理—— 那归 [`init-agent-task-md`](../init-agent-task-md/SKILL.md)。 使用:/init-agents-md;或当用户说「为这个项目加上分层约定」「把 CLAUDE.md 迁移到 AGENTS.md」时也命中本 skill。

  • Bisect driver

    Evan-Daruwalla/claude-skill-suite/bisect-driver Skill

    0★ repo

    Automate git bisect to find the exact commit that introduced a behavior change — regression blame. Give it a KNOWN-good ref, a bad ref (default HEAD), and a repro command; it drives `git bisect run`, parses the first-bad commit, and ALWAYS resets the bisect state so your repo is left exactly where it started. Refuses up front on a dirty working tree or an in-progress bisect. Use when the user says "bisect this", "which commit broke X", "find the commit that introduced the regression", "git bisect", "regression blame", "when did this test start failing", or "what change made the output drift". Deterministic, zero dependencies, no model calls.

  • Agents connect

    dkmqflx/claude-tools/.claude/skills/agents-connect Skill

    no license0★ repo

    Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies. Handles gateway setup, target types, outbound auth (OAuth, API key, IAM), credentials, and Cedar policy authoring. Triggers on: "connect to API", "add gateway", "connect to MCP server", "Lambda tools", "OpenAPI", "gateway target", "Cedar policy", "restrict tools", "policy engine", "gateway auth error", "store API key", "outbound credential", "env var API key", "API key None after deploy", "credential not available after deploy", "should this be a gateway target", "give my agent tools", "add tools to agent". Not for inbound auth (who can call your agent) — use agents-harden. Not for debugging agent behavior — use agents-debug. Not for VPC networking errors (agent can't reach APIs due to VPC) — use agents-build. Not for creating or hosting a new MCP server project — use agents-get-started.

  • Ai inference optimization

    pramodmax/openshift-ai-skills/ai-inference-optimization Skill

    0★ repo

    Expert guidance on optimizing LLM inference with Red Hat AI Inference Server, vLLM, LLM Compressor, quantization strategies (W8A8, AWQ, sparsity), and multi-accelerator deployment for production cost efficiency

  • Tap setup

    LeonTing1010/taprun/plugins/tap/skills/tap-setup Skill

    0★ repo

    Adaptively prepare Tap for LOGGED-IN / authenticated websites — not by running a script blind, but by diagnosing first, fixing only the missing rung, passing the human trust gates, then verifying. Public pages / open APIs need none of this (the plugin's MCP over npx already works). Trigger when: the user wants to use Tap on a site that requires login (bank / admin dashboard / internal tool / social); the user says "set up tap", "configure tap", "connect tap", "tap won't connect", "let tap use my logged-in session"; or Tap's run fails on a logged-in site with a peer / bridge-unreachable error. This skill DRIVES setup adaptively via `tap embed --verify`; it does not blindly run an installer.

  • Diagram

    mishafyi/claudus-maximus/plugins/diagram/skills/diagram Skill

    no license0★ repo

    Generate architecture diagrams, flowcharts, sequence diagrams, and system maps from actual codebase analysis. Use this skill whenever the user asks to "draw a diagram", "create a flowchart", "map the architecture", "visualize the system", "show me how X works as a diagram", "create an architecture chart", "generate a sequence diagram", "map the data flow", "show me the database schema", "what calls what", or wants any visual representation of how their code, system, or feature works. Also trigger when the user says "update the diagram", "the diagram is outdated", "how does this work" (when a visual would help), or "explain the architecture". This skill analyzes real code paths first, then generates accurate Mermaid (.mmd) files — not guesswork.

  • Explorer

    agony1997/TouchFish-Skills/plugins/explorer/skills/explorer Skill

    0★ repo

    專案探索者:使用 Opus Leader 指揮多個 sub-agents 並行探索專案結構, 交叉比對後產出結構化的專案地圖文件(PROJECT_MAP.md)。 支援單體、多模組、monorepo 等專案類型的智慧偵測與分工。 使用時機:接手新專案、了解專案架構、產出專案地圖、實作前收集上下文。 關鍵字:explore, 探索, 偵察, 專案地圖, project map, codebase, 了解專案, 專案結構, 探索專案, 分析架構, architecture, 架構分析, onboarding, 新人導覽, 專案概覽, 技術棧, tech stack。

    The same file is in 2 other repositories

  • Init

    mk668a/FDE-SKILLS/skills/init Skill

    0★ repo

    Use when the user wants to set up an FDE-SKILLS workspace or start a new client engagement (e.g. "set up fde", "scaffold fde here", "new engagement with Acme", "start the Globex engagement"). First run creates the .fde/ deterministic spine (config, schemas, bin scripts, empty corpus); with a client name it also creates the per-client engagement directory.

  • Create skill from workflow

    az9713/youtube-transcript-to-skills/.claude/skills/create-skill-from-workflow Skill

    no license0★ repo

    Turn what we just did into a reusable skill. Captures the current workflow as a new SKILL.md file.

  • Harness audit

    ClydeShen/harness-skill/skills/engineering/harness-audit Skill

    0★ repo

    Scans a project for agent-harness gaps and outputs a prioritised list with paste-ready config snippets to close them. Covers hooks, CI, pre-commit, instruction file quality, init.sh, and session discipline. Use when starting a new project, auditing an existing harness, writing or reviewing CLAUDE.md/AGENTS.md, setting up CI gates, beginning multi-day autonomous work, or when user says "set up harness", "health check", "agent discipline", "project setup", "pre-commit hooks", "stop hook", "verification gap".

  • Go concurrency

    Cadasto/go-coding-plugin/skills/go-concurrency Skill

    0★ repo

    Idiomatic, leak-free Go concurrency. This skill should be used when the user writes or reviews Go goroutines, channels, `sync`/`atomic`, `context`, `errgroup`, or worker pools — goroutine lifetimes/leaks, context propagation, typed atomics, mutex misuse, or data races. Pair with `go test -race`, `go vet`, and `goleak`. Defers time/concurrency *testing* mechanics to `go-testing` (synctest). Not for non-Go languages.

  • Authoring tests

    TomerAberbach/claude-config/skills/authoring-tests Skill

    0★ repo

    Use when writing, reviewing, or modifying any test files, or when asked to add test coverage.

  • Eval awareness red team

    jpoindexter/reward-seeking-safety-skills/skills/eval-awareness-red-team Skill

    0★ repo

    Red-team AI evaluations for test recognition, metagaming, prompt-placement effects, grader inference, and appearance management. Use when an agent may know it is being evaluated, behaves differently on benchmark-like tasks, reasons about hidden grading criteria, or when an eval may be gamed by recognizing its setup.

  • Claude docs

    ccronca/dotfiles/claude/skills/claude-docs Skill

    0★ repo

    Consult official Claude Code documentation from docs.claude.com using selective fetching. Use this skill when working on Claude Code hooks, skills, subagents, MCP servers, or any Claude Code feature that requires referencing official documentation for accurate implementation. Fetches only the specific documentation needed rather than loading all docs upfront.

  • Project audit

    Mrbaeksang/ai-project-audit/skills/project-audit Skill

    0★ repo

    Service-profile-driven project audit. Auto-fires when the user requests audit, review, code review, pre-launch check, security audit, OWASP/SOLID/12-Factor compliance, project skeleton/bootstrap/setup, or any equivalent in any language (e.g., 점검, 감사, 리뷰, 출시 전 검토, 보안 점검, 골조, 셋업). Reads the full 0–10 section checklist from SPEC.md, filters items by grade (🔴🟠🟡🔵⚪) against the user's service profile, and outputs results as ✅❌⚠️⏭️ markers re-sorted by risk. Respond in the user's language.

  • Ml config manager

    nishide-dev/claude-code-ml-research/skills/ml-config-manager Skill

    0★ repo

    Generate and manage Hydra configuration files for machine learning experiments. Use when creating new configs (model, data, trainer, logger, experiment, sweep), organizing config hierarchies, or setting up hyperparameter sweeps with Optuna.

  • Performance advisor

    hoqo/claude-plugins/plugins/mongodb/skills/performance-advisor Skill

    no license0★ repo

    Reference guide for MongoDB performance patterns: index strategies (ESR rule, compound, partial, TTL), explain plan interpretation, and performance checklists. Use as background knowledge when advising on indexing or performance. For hands-on optimization of a specific slow query, trigger the query-advisor agent instead.

    The same file is in 2 other repositories

  • Test driven development

    sgrowe/jj-ai/jj-flow/skills/test-driven-development Skill

    no license0★ repo

    Use when implementing any feature or bugfix, before writing implementation code

  • Video backend

    grooverLab/stash/skills/video-backend Skill

    0★ repo

    Generate a video clip through one swappable backend - local MLX preview on this Mac (Apple-native, fits 16GB), a rented GPU or local ComfyUI, or a hosted API (fal - Seedance / Kling / LTX). Use whenever a pipeline stage needs to turn a prompt into an actual video file and you do not want to hardcode which engine renders it. Invoke for "generate the hero video", "render this clip", "make a preview of this shot". One verb, three backends, chosen by config - so preview-locally-then-pay works without changing the pipeline.

  • Skill activation testing

    bogheorghiu/ex-cog-dev/makers-toolkit/skills/skill-activation-testing Skill

    0★ repo

    "You rewrote the description. Did it fire better — or do you just believe it did?" That belief is n=0 until you test it: invoke when validating a skill or prompt change, asking whether a description actually fires, or A/B-ing prompt wording. The cheap proxy gives a number in minutes; the discipline is naming what it can't see.

  • Global config pull

    mjcreativelab/mjcreativelab-agent-prompts/internal/global-config-pull Skill

    0★ repo

    グローバル Claude 設定(~/.claude/ の CLAUDE.md・settings.json・statusline-command.sh・rules/・hooks/・agents/・commands/・keybindings.json・.mcp.json)をリポジトリの dotfiles/claude/ にコピーして取り込む。「設定を取り込む」「グローバル設定を pull して」と言ったら起動。

  • Sap cap nodejs dev

    Fab2295/sap-skills/skills/sap-cap-nodejs-dev Skill

    0★ repo

    SAP Cloud Application Programming Model (CAP) development skill for the **Node.js runtime only**. Domain-first: prefers CDS schema, annotations, projections, and CAP's generic providers over hand-written handler code ("less code → less mistakes"). Use when the user asks to: build CAP applications, define CDS models, design entities / associations / views / projections, add annotations (validation, authorization, UI, search, drafts), configure databases (SQLite / HANA / PostgreSQL through CAP), deploy to SAP BTP (Cloud Foundry or Kyma), wire multitenancy / messaging, or add CAP plugins. Strict scope — this skill ONLY develops SAP CAP Node.js. It MUST refuse, and tell the user why, whenever a request is: - Frontend / UI implementation (Fiori Elements custom code, UI5 controls, React, Vue, HTML/CSS/JS UI work, any browser-side code). CAP-side `@UI.*` annotations in `.cds` are in scope; writing the UI itself is not. - Backend in any other language or stack (Java CAP, Spring, plain Node/Express, NestJS, Python, Go, .NET, serverless functions outside CAP, microservices not built on `@sap/cds`). - Any non-CAP architecture (custom OData providers, hand-rolled REST frameworks, ad-hoc GraphQL servers that don't go through `@cap-js/graphql`). Public-API hygiene — this skill only uses **public, supported, non-deprecated** CAP interfaces: - Public: anything documented at https://cap.cloud.sap/docs/ for the current `@sap/cds` major. - Forbidden: internal modules (paths like `@sap/cds/lib/...`, `_private`, `__internal`), `@protected` / `@internal` / `@experimental` APIs, anything marked deprecated or removed in the changelog. Always prefer the documented public interface; if no public API exists, say so and stop — do not reach into internals.

  • Daily reviewer

    chienchuanw/chuan-skills/plugins/daily/skills/daily-reviewer Skill

    no license0★ repo

    Close out the user's day with an honest retrospective. Read today's Daily note plan, interview the user to catch work done-but-unticked, then score completion, assess every active objective's on-track status, update the tracking files (tick checkboxes, carry unfinished tasks into 延後 with reasons, refresh an objective's 目前進度 when a milestone moved), and write a review into both the Daily note and the Journal with concrete suggestions for tomorrow. Use this whenever the user wants to look back on, review, wrap up, score, or close out their day, or asks whether they are on track — "review my day", "how did today go", "what did I get done", "daily retro", "wrap up my day", "am I on track", "end of day review", "回顧今天", "回顧一下今天", "今天做得如何", "今天完成了什麼", "睡前回顧", "檢討今天", "今天有沒有在軌道上" — even if they don't name a skill. This is the evening bookend to daily-planner: daily-planner builds the morning plan, daily-reviewer reviews it at night. Prefer this skill over daily-planner whenever the user is looking BACKWARD at a day that already happened rather than planning one ahead. It also runs a nightly spending pass — asking once for today's card transactions (pasted notification / app text), logging them into the month's spend-log, checking them against the card-routing rules and overspend / forex-leak / revolving-credit / subscription signals, and flagging semi.tw business expenses for monthly reimbursement — so 記帳 happens nightly instead of in a month-end scramble. Also triggers on "記帳", "今天花了多少", "今天的消費", "對一下帳", "看一下今天刷卡", "review my spending". This pass logs spends that ALREADY happened; for a PRE-purchase decision on whether to buy something you're hesitating over, use money's spend-audit instead.