Engineering
98,648 rows, by stacks then stars
VladimirGutuev/cross-agent-memory/skills/cross-agent-handoff Skill
5★ repoTransfer unfinished feature work between Claude Code, Codex, Kimi Code, Antigravity, or another coding-agent harness with a verified worktree snapshot. Use only when the user asks to hand off, continue, resume, pause, close, or supersede work in progress, or when the shared-memory index contains an active handoff that clearly matches the current task. Do not invoke for a new unrelated task or ordinary shared-memory recall.
alimobrem/argo-skills/skills/argo-cluster-debug Skill
5★ repoDebug and troubleshoot the Argo ecosystem on live Kubernetes clusters — inspects Argo CD Application sync status, health checks, and controller logs; diagnoses Argo Rollouts canary/blue-green failures and AnalysisRun results; traces Argo Workflow step failures and artifact issues; and debugs Argo Events EventSource and Sensor connectivity. Prefers argocd/argo CLIs when available, falls back to kubectl for CRD inspection. Use when users report failing, stuck, or degraded Argo resources on a cluster.
XKHoshizora/cross-border-network-best-practices/3x-ui-best-practices Skill
5★ repoInstall, secure, inspect, configure, and troubleshoot 3x-ui/Xray panels, including fresh VPS or Docker setup, SSL/reverse proxy, inbounds, clients, VLESS/REALITY, TLS, fallbacks, subscriptions, API automation, live diagnostics, and recovery. Use when the user mentions 3x-ui, 3X-UI, Xray panel, inbounds, clients, VLESS, VMess, Trojan, Shadowsocks, Hysteria, WireGuard, REALITY, subscription links, panel API, install, debug, logs, traffic not counted, connection failure, or best-practice proxy/VPN configuration.
tjboudreaux/rosetta/skills/rosetta Skill
5★ repoReconcile ALL prior agent conversations (Claude Code, Codex, Droid/Factory, Hermes, Cursor) with git history and docs into a cited ground truth, and distill durable decision records (ADRs/PDRs/BDRs). Use whenever the user wants to catch up on or get the state of a project, build or refresh a ground truth, read or mine previous agent/AI conversations, recover or record what was decided (technical, product, or business), capture/index/validate ADRs or PDRs, discover which projects on the machine have agent history, or onboard onto unfamiliar work — even if they don't say the word "Rosetta".
OneWave-AI/open-agent-stack/plugins/ai-news-hq/skills/daily-ai-brief Skill
5★ repoRun the AI-news crew (scout, analyst, editor) to sweep the field with web search and ship a ranked briefing. Trigger when the user asks for an AI news brief, a daily or weekly AI roundup, "what shipped in AI", a model-release recap, or wants the standing cadence run.
skillsaiagent/aiskills/skills/ai-ab-testing Skill
no license5★ repoA/B 测试设计助手适合市场营销、产品、运营、software在用户提出“这个改动值得测吗”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成转化问题优先级、可复制改稿、实验或跟进行动清单。
The same file is in 1 other repository
danielsogl/skills/skills/bdd Skill
5★ repoWrite disciplined Behavior-Driven Development specs and tests with Gherkin / Cucumber. Use whenever the user mentions BDD, Gherkin, Cucumber, .feature files, Given/When/Then, scenarios, Scenario Outline, Background, step definitions, acceptance criteria, executable specifications, living documentation, the Three Amigos, or Example Mapping. Also trigger when the user asks to "write tests in plain English", convert acceptance criteria into tests, design step definitions, refactor an imperative or UI-coupled feature file, or wire up BDD with Vitest (unit/component) or Playwright (end-to-end). Do NOT use for pure unit tests with no business-readable contract, pure performance/load tests, or generic test-framework questions unrelated to behavior specs.
The same file is in 1 other repository
initxy/initxy-skills/skills/ai-native-engineering/gc Skill
5★ repoProject entropy control (gc) — reconcile docs against code, clear dead code and stale docs, archive specs, scan friction, and generate architecture-improvement proposals. Use to clean up a project, when docs have drifted from reality, to find refactor directions, after a large feature merges (scoped), or for periodic maintenance (global).
hubeiqiao/gpt-pro-audit Skill
5★Use when the user asks to audit a plan, document, diff, website finding, or implementation proposal with the best available ChatGPT GPT-5.5 Pro (Extended Thinking) option through Chrome - starts automatically after invocation, packages codebase/project context ChatGPT cannot see, runs up to 5 review rounds until accepted, verifies the response, and applies only accepted findings.
0xtresser/skill-guardian Skill
5★Pre-installation security gate for agent skills. This skill should be used when the user or agent attempts to install any skill — including requests like "install X", "add X skill", "help me set up the X skill", "npx skills add", or when the agent autonomously decides to install a skill. Also triggers on skill cleanup and audit requests like "clean up my skills", "check installed skills", "any unused skills", "review my skills", or "audit my skill list". Do NOT use for MCP server installation, npm/pip package installation, or non-skill tooling.
High ticket conversion architect
wavect/ai-skills/high-ticket-conversion-architect Skill
5★ repoAI agent skills for building better software products.
StringNLPLAB/FlexSQL/claude_harness/.claude/skills/sql-revision Skill
no license5★ repoVerify that a SQL query's actual output faithfully answers the natural-language question.
fboldo/oiap/.agents/skills/oiap-platform-matrix-refresh Skill
5★ repoUse when: refreshing OIAP platform support documentation, updating MATRIX.md, researching agent harness platform docs, auditing exporter assumptions, checking target profiles against adapters, or verifying capabilities such as hooks, MCP, skills, commands, rules, custom agents, runtime bridges, package formats, permissions, and policies across Claude Code, Codex, Gemini CLI, Hermes, Kiro, Cursor, Trae, Factory Droid, Antigravity, and related agent platforms.
Toubat/agentic-debug-mode/skills/agentic-debug-mode Skill
5★ repoUse when a bug, regression, race condition, or unexpected behavior has no proven root cause and you must confirm the cause with runtime evidence instead of guessing from source code.
SpinaBuilds/goodcode Skill
5★Host-agnostic exhaustive multi-agent orchestration for any coding agent that can spawn subagents (Claude Code, Codex, Cursor, OpenCode, OpenHands, …). Pipeline: recon → cheap baseline → a-priori specialist roles cast by routing → parallel fan-out → adversarial verification → loop-until-dry → dedup/score/synthesize. Optimizes for the most exhaustive, correct answer — not the fastest or cheapest. Use for audits, deep reviews, multi-source research, design exploration, large migrations, or any substantial task where completeness beats latency. Triggers: '/goodcode', 'goodcode', 'orchestrate exhaustively', 'fan out subagents', 'multi-agent deep dive', 'be exhaustive'. Skip on trivial or conversational turns.
zystem-io/zymtrace-skills/zymtrace/skills/configure-zymtrace-mcp Skill
5★ repoUse when connecting a coding agent — Claude Code, OpenAI Codex, or Cursor — to the zymtrace MCP server so the user can analyze CPU and GPU flamegraphs through natural-language queries. Walks through finding the gateway URL, generating an auth token (if service-token auth is on), adding the server with the right command for the user's client, and verifying the connection. This skill is plumbing only — the analytical workflow lives in `optimize-cpu-workloads` and `optimize-gpu-workloads`. Trigger phrases: "connect zymtrace MCP", "set up zymtrace MCP", "configure zymtrace MCP", "add zymtrace to /mcp", "connect Claude/Codex/Cursor to zymtrace", "/mcp doesn't show zymtrace", "zymtrace MCP token", "Cursor zymtrace integration", "set up the zymtrace AI assistant".
Zekai-Zhao-321/agent-cli-builder/skills/agent-cli-builder Skill
5★ repoBuild, retrofit, or score an agent-native CLI for AI agents (Claude Code, Cursor, codex, opencode). Use when scaffolding a CLI for agent consumers, bringing a human-first CLI up to agent-first standards, or assessing an existing CLI's agent readiness. Do NOT use for general CLI style or one-off shell scripts.
jthingelstad/mb/skills/mb-agent-blogger Skill
5★ repoUse this skill when an agent is managing its own micro.blog identity with mb. It covers autonomous posting, voice consistency, disclosure, and how an agent should participate as itself rather than impersonating a human user.
magnus919/hermes-droid/factory-droid Skill
5★ repoUse this skill when delegating coding work to Factory Droid's droid CLI for code analysis, edits, specification-first implementation, worktree isolation, or multi-agent missions. Do not use it for small direct edits or when Factory Droid is unavailable.
itsadrianxv/tradeblazer_skills/skills/setup-tradeblazer Skill
no license5★ repoUse after installing tradeblazer_skills to collect user preferences for TBQ3/TB language work, including task focus, strategy type, document output location, and review expectations.
Far-200/think-before-code/skills/code-review-coach Skill
5★ repoSocratic Agent Skills for learning problem-solving and software-engineering judgment — one question at a time.
CSKishan/ame-skill/skills/ame Skill
5★ repoUse when the user invokes /ame, says "ask me exhaustively", "interview me about this", "help me think through what I want to build", "ask me questions about my idea", or wants to clarify requirements before planning or coding. Runs a structured adaptive interview across all software quality dimensions in a single compiled message, writes a compressed spec to .ame/spec.md, and prepares context for /ema. REQUIRES agent/agentic mode with file-write capability (VS Code Agent mode, Google Antigravity, or Claude Code).
YangKuoshih/security-audit/skills/security-audit Skill
5★ repoScans source code files for hardcoded secrets, leaked credentials, and security vulnerability patterns, then produces a severity-classified audit report (Markdown, SARIF, or JSON). Use this skill — not ad-hoc grep — when the user wants to: scan for hardcoded secrets or API keys, do a security audit, find leaked credentials or tokens, check whether sensitive values were committed, run an incremental scan of files changed since a branch, generate a SARIF file for GitHub Code Scanning, or get a report of findings grouped by Critical / High / Medium / Low. Do NOT use for: fixing individual bugs the user has already identified, writing CI/CD pipeline config, checking package dependency CVEs (use a dependency scanner for that), or general code review without a security focus.
DefaultHQ/build-support-agent-skill/skills/build-support-agent Skill
5★ repoPlan and build a production customer-support agent — a RAG product-Q&A bot that drafts replies, posts them for human review, and graduates to controlled autonomy. Use when someone wants to build an in-house support agent, a Slack-native or support-platform AI bot, a ticket-answering / customer-Q&A agent, or wants to build DaanBot-style support automation. Interviews the user about scope, knowledge sources, and guardrails, then guides a phased MVP build. Triggers on 'build a support agent', 'support bot', 'AI for support tickets', 'answer customer questions automatically'.
zephexMCP/agent-skills/skills/zephex Skill
5★ repoUse this skill when the user works in their own codebase with Zephex MCP connected and needs repository intelligence: find or read code, scope a feature or fix before editing, map how their app is wired, verify a package before install, audit a live HTTPS URL, or debug after failed attempts — including when they only say "use Zephex," "use MCP," or a wrong tool name. Use even when built-in Grep/Read seems enough. Do not use for general knowledge, creative writing, git/deploy chores, editing agent skill files, single-line typo fixes, or third-party library API docs (unless Zephex_dev_info fits). Prefer Zephex tools over Grep/Read for their repo; do not describe their code from memory if MCP is connected. Triggers: find_code, read_code, scope_task, get_project_context, explain_architecture, check_package, audit_package, audit_headers, keep_thinking, Zephex_dev_info.
vladzima/video-debug Skill
5★Use when the user references a video, screencast, screen recording, or any path ending in .mp4, .mov, .webm, .mkv, or .gif — especially when asking to debug a UI bug, visual glitch, or reproduction recording. Extracts key frames via ffmpeg scene detection so the agent can visually inspect what went wrong.
stefanoskarakasis/Product-Marketing-Skills/pmm-execution/skills/experiment-doc Skill
5★ repoGuides you through building high-rigor experiment briefs by first understanding your role, what you're testing, and what scale you need to detect real results statistically. Pressure-tests your hypothesis and only approves experiments that can reach significance with realistic sample sizes.
kevinlin/skills/agent-insights Skill
5★ repoGenerate a cross-tool usage insights report from locally stored AI coding agent sessions (Claude Code, Claude Cowork, GitHub Copilot for VS Code/CLI/JetBrains, Cursor, Codex, Kiro, Antigravity, OpenCode) over the last N days, default 30. Use when the user invokes /agent-insights, asks for insights, analytics, or a report on their agent sessions, asks how they're using their coding agents or what's working or causing friction, wants to compare their coding agent tools, or asks what their AI coding patterns look like, even when they don't say "report".
199-biotechnologies/claude-skill-gpt-pro Skill
5★Package files + structured prompts for manual copy-paste into GPT-5.4 Pro for deep reasoning review. Use when user says 'send to GPT Pro', 'GPT Pro review', 'ChatGPT Pro review', 'prepare for GPT', 'package for GPT Pro', 'get GPT to review', 'GPT Pro analysis', 'upload to ChatGPT', 'gpt-pro', '/gpt-pro', 'pack for GPT', 'bundle for ChatGPT', 'have ChatGPT check this', 'send this to GPT', 'GPT deep review'. Creates structured prompt + file bundle as tar.gz in ~/Documents/GPT Pro Analysis/ and copies prompt to clipboard for manual paste into ChatGPT Pro.
trevhud/rote/skills/rote-compile Skill
5★ repoAnalyze an Anthropic-style skill bundle (SKILL.md + references) and produce a compilation plan that separates deterministic work into extracted Python modules, LLM-as-judge work into typed DSPy/BAML signatures, agentic work into bounded agent loops, and human-in-the-loop gates into durable suspend points. Emit the whole pipeline as a runtime-agnostic intermediate representation (pipeline.yaml) plus runnable code for a target workflow engine (Temporal, Inngest, Restate, or plain async) via pluggable adapters. Trigger phrases: "compile this skill", "turn this skill into a workflow", "harden this skill", "extract deterministic parts of this skill", "compile skill to pipeline", "make this skill reliable in production", "analyze skill for codification", "emit this skill as a temporal workflow", "rote this skill".
ghillb/swarmux/.agents/skills/swarmux-release-playbook Skill
5★ repoExecute and verify GitHub Releases for this repo. Use when the user asks to cut a release, publish artifacts, trigger release workflow, or check why a release did not publish.
voderment/AI-UIconfig-skill Skill
5★Refactor an existing SwiftUI project into a governed UI architecture with render-state boundaries, tokenized styling, preview mocks, and a debug-only runtime tuning + writeback tool. Use when the user wants to improve UI maintainability, live-tune styles, or build a reusable UI debugging workflow without changing the product's visual intent.
ByteLandTechnology/headless-ghidra/ghidra-agent-cli Skill
no license5★ repoRust CLI reference for the headless-ghidra pipeline. Covers command syntax, flags, output contract, artifact paths, and workspace layout for all ghidra-agent-cli subcommands. Load when: constructing a ghidra-agent-cli command, interpreting its output, resolving a flag or artifact path question, or debugging CLI behavior. Do not load for P0–P4 workflow sequencing — use the headless-ghidra skill family instead.
sdcrd/trust-guard Skill
no license5★Post-edit verification that prevents silent edit failures. After every Write, Edit, or MultiEdit, re-reads files to confirm changes actually saved to disk across all call sites. Assigns a 0-100 trust score per edit. Catches: silent failures (tool reports success but file unchanged), partial application (some call sites missed), ghost writes (subagent claims write but file empty), worktree confusion, MultiEdit partials. Use whenever editing, writing, modifying, refactoring, or creating files — especially multi-file changes, production code, payments, auth, security-sensitive code, or when using subagents. Works with Claude Code, Cursor, Copilot, Codex, and any AI coding agent. Zero executable code, zero dependencies, pure instructions.
OscarDRT/supastarter-nextjs-skill/supastarter-nextjs-skill Skill
5★ repoGuides development with supastarter for Next.js only (not Vue/Nuxt): tech stack, setup, configuration, database (Prisma), API (Hono/oRPC), auth (Better Auth), organizations, payments (Stripe), AI, customization, storage, mailing, i18n, SEO, deployment, background tasks, analytics, monitoring, E2E. Use when building or modifying supastarter Next.js apps, adding features, or when the user mentions supastarter Next.js, Prisma, oRPC, Better Auth, or related Next.js stack topics.
ferdinandobons/knowledge-transfer Skill
5★Use when a colleague is leaving a project and must hand over knowledge, or when someone new joins a project and receives handover.zip or a handover/ folder. Two phases: export (analyze project + agent project memories from Claude, Codex, or another assistant, then produce a transferable handover.zip archive containing a non-technical onboarding doc + filtered portable memories + a privacy-safe omissions manifest) and import (extract/read the handover package, dry-run the candidate memories, verify every claim against current code, then install accepted memories through the current agent's memory mechanism with per-memory receipts). Trigger on /knowledge-transfer, /knowledge-transfer:knowledge-transfer, $knowledge-transfer, 'handover', 'knowledge transfer', 'passaggio di consegne', 'onboard a new colleague', or when the user mentions taking over / leaving a project.
ryne2010/harness-engineering-audit/plugins/harness-engineering-audit/skills/harness-engineering-audit Skill
5★ repoAudit a repository for OpenAI-style harness engineering and Codex/OMX readiness. Use when reviewing AGENTS.md, Codex config, OMX workflows, MCP, hooks, rules, skills, subagents, docs authority, validation commands, repo legibility, visual product spec packs, generated artifact policy, or production readiness for AI-driven development.
haru0416-dev/quaere/skills/core/quaere-evidence Skill
5★ repoThis skill should be used whenever the user asks to investigate unclear bugs, defend or reject PR review comments, triage CI failures or flaky tests, review risky/security/database/concurrency/external-API changes or multi-file refactors, or make any claim that needs evidence before patching. It enforces a falsifiable claim → defense → probe → decision workflow so the agent does not jump to fixes, accept plausible but unverified explanations, or publish noisy review comments.
lteawoo/skills/skills/architecture-planner Skill
no license5★ repoOrganize screens, APIs, data models, state management, folder layout, and integration boundaries before implementation. Use it when you need a clear technical structure and responsibility split up front.
olanokhin/agent-security-skill/skills/agent-security Skill
5★ repoUse when reviewing or writing LLM, RAG, MCP, tool, or agent code for OWASP-aligned security issues; triggered by "owasp my code", "owasp this PR", AI security review, PR review, or changes to AI system code.
perhapsspy/project-legibility/plugins/project-legibility/skills/agents-md-editor Skill
5★ repoUse when creating, editing, or reviewing AGENTS.md, agents.md, CLAUDE.md, Copilot instructions, Cursor rules, or any always-read repository instruction file. Keep persistent agent instructions small, durable, non-duplicative, and action-oriented; classify content that belongs in commands, onboarding, reference docs, handoff state, enforcement, or removal instead of preserving it in always-read files.
thaolst/ai-growth-agents-for-marketers/skills/ab-test-analyzer Skill
5★ repoAnalyze A/B test results and recommend next actions. Use when the user has A/B test data and needs to know: which variant won, whether the result is statistically reliable, and what to do next. Works for conversion rate tests, copy tests, mechanic tests, UI tests. Input: user counts and conversions for control and variant. Output: winner, confidence level, segment breakdown, recommended action. Includes effect size, p-value, and confidence intervals.
TommyBez/skillsboard/.agents/skills/ab-testing Skill
5★ repoWhen the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," or "experiment playbook." Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics. For page-level conversion optimization, see cro.
The same file is in 3 other repositories
TAKEOFF69/codex-skills-kit/skills/codex-prompt Skill
5★ repoGenerate structured, self-contained Codex task prompts. Use when the user asks for a Codex prompt, delegation task, fix, build, audit, ops/tuning, refactor, PR-series, or master-session brief to hand to another Codex run. Grounds every cited path and command, distinguishes directive from investigative work, and binds completion to explicit evidence.
stark-ydq/voice-to-instrument-skills/voice-to-instrument-guide Skill
5★ repoExpert guidance for converting voice recordings into realistic instrument sounds using AI tools. Use this skill whenever a user asks about voice-to-instrument conversion, how to record voice input for music AI, which instrument suits their voice, prompt engineering for text-to-music tools, or troubleshooting common issues with voice-based AI music production.
christopherlouet/claude-base/.claude/skills/agent-teams Skill
5★ repoMulti-agent team orchestration with native Agent Teams. Trigger when the user wants to launch a team of agents, coordinate parallel work with inter-agent communication, or use swarm mode.
numekudi/engineering-ethics/skills/engineering-ethics Skill
5★ repoソフトウェア・エンジニアリングのための倫理集。開発時に必ず意識するものです。
mataeil/OODA-loop/skills/check-tests Skill
5★ repoRun test suite, track coverage trends, and detect regressions. Detect phase skill — uses config.test_command to execute tests and records results.
yopiesuryadi/mailbot-programmable-inbox Skill
no license5★Integrate mailbot API for AI agent email automation. Create programmable inboxes, send and receive emails, track delivery events, and handle email-based workflows via API, SDK, or MCP Server. Use when building AI agents that need email identity, when setting up agent-to-human communication, when replacing Gmail or Outlook with programmatic email, or when any task involves sending, receiving, or processing emails for AI agents. Covers Node.js SDK, Python SDK, and MCP Server for Claude integration. Always use this skill when the user mentions mailbot, programmable inboxes, agent email, or email automation for AI.
theflixerbox77/ralph-wiggum-codex/skills/ralph-prompt-generator Skill
5★ repoUse when a user has a rough prompt that needs a staged prompt-improvement workflow for `$ralph-wiggum-codex`, with saved draft/final files and explicit review checkpoints.
The same file is in 1 other repository
IncommensurableHubris/fullstack-director/.agents/skills/00-discovery Skill
5★ repoProduce the project's spec spine — the single source of declaration-truth — by ingesting a spec/PRD/brief (or interviewing from an idea), stress-testing its assumptions, and writing requirements with outcome-level acceptance criteria. Use at the START of any project, or when the user says 'new project', 'intake this spec/PRD', 'turn this doc into requirements', 'start discovery', 'specify', or 'I have an idea for…'; for a bare itch pre-commitment ('brainstorm', 'explore an idea', 'I have an itch') use EXPLORE mode; for an existing codebase with no spine ('adopt this codebase', 'reverse-engineer a spec') use ADOPT mode. Owns the spine: Constitution, REQ registry, capabilities, design-intent, architecture-constraints, and the emitted per-project AGENTS.md. Do NOT use for build planning or sprints — that is /01-planner. Do NOT use for design or architecture — use /02-designer or /03-architect.
web-abin/OpenGeno/skills/geno-init Skill
5★ repoInitialize an OpenGeno feature tree for a project. Asks the user to pick a documentation language (English or Chinese, default English), a drift mode, and a generation mode (stub-only by default, or one-shot full docs that fills every L3 section now). Scans the codebase, proposes a module breakdown, generates the L1 root index, L2 module indexes and L3 feature docs in the chosen language, writes .feat-tree.json, and injects the OpenGeno workflow rules into CLAUDE.md (and AGENTS.md if present). Use when starting OpenGeno on a new project. Run once per project.
jmagar/tailscale-rmcp/ai.dinglebear/tailscale-rmcp MCP server
5★ repoRust MCP server and CLI for Tailscale devices, users, keys, policies, and auth.
jmagar/unifi-rmcp/ai.dinglebear/unifi-rmcp MCP server
5★ repoRust MCP server and CLI for UniFi Network controller operations.
Gauraviitkgp/news-mcp/ai.newzai.api/NewzAI MCP server
no license5★ repoNews MCP: real-time headlines & custom news search across 7 regions. Free, just sign in with Google.
bielacki/igdb-mcp-server/ai.smithery/bielacki-igdb-mcp-server MCP server
5★ repoExplore and discover video games from the Internet Game Database. Search titles, view detailed inf…
kwp-lab/rss-reader-mcp/ai.smithery/kwp-lab-rss-reader-mcp MCP server
dormant5★ repoTrack and browse RSS feeds with ease. Fetch the latest entries from any feed URL and extract full…
Leandrogavidia vechain mcp server
leandrogavidia/vechain-mcp-server/ai.smithery/leandrogavidia-vechain-mcp-server MCP server
dormant5★ repoSearch VeChain documentation, query on-chain data, and fetch fee suggestions with direct links to…
corralimited/snapdiff-mcp/ai.snapdiff/mcp MCP server
5★ repoVisual-diff & change-detection tools that catch agentic UI drift for coding agents.
desktop-commander/remote-desktop-commander/app.desktopcommander/remote-desktop-commander MCP server
no license5★ repoHosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer