Skip to content

Agent Tooling

Skills that build, configure or extend agents and other skills.

Search and filter within Agent Tooling

9105 skills

chrome-browserjackson2w/claude-code-skillsRead this skill before the first step that uses Claude in Chrome, the browser extension whose tools are named mcp__claude-in-chrome__* (also called Chrome, the browser extension, or the external browser) and which acts in the person's real Chrome with their own sign-ins; before those tools are turned on there may be a single enable__mcp__claude-in-chrome tool instead. It covers loading the tools in one ToolSearch call, checking the person's open tabs and working in a new tab, site permissions, GIF recordings, console logs, dialogs to avoid, and when to stop and ask. It is not for the built-in browser (mcp__Claude_Browser__* or mcp__remote-devices__Claude_Browser__* tools), which has its own skill, and it does not decide which browser to use.Stars: 1Updated Claude CodeCodexUnverifiedInstall
computer-usejackson2w/claude-code-skillsRead this skill before the first step of any request to do something in an app on the person's own computer (Notes, Finder, System Settings, any desktop app), to look at their screen, or for "computer use". Computer use (desktop control) lets Claude take screenshots of the person's desktop and control it with clicks, typing and scrolling through the Claude desktop app; its tools are named mcp__computer-use__* when the session runs in the desktop app and mcp__remote-devices__computer_* when a cloud session is linked to the person's computer; before computer use is turned on for a conversation there may be no such tools, only an enable__mcp__remote-devices__computer tool, which turns it on. It covers turning it on, picking the right tool, the access flow, and the safety rules for tiered apps, links and financial actions. It is not for websites, which go through Claude in Chrome or the built-in browser and their own skills.Stars: 1Updated Claude CodeCodexUnverifiedInstall
deep-researchjackson2w/claude-code-skillsUse this skill when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alternatives, analyzing trends or history, understanding markets or industries, or reviewing literature or studies and (2) synthesizing that research into a comprehensive, narrative report. If you're planning to search the web or internal knowledge bases, consider using this skill. This skill coordinates research subagents, so use it only when you have a tool for spawning subagents (the Agent or Task tool); otherwise, research the question directly.Stars: 1Updated Claude CodeCodexUnverifiedInstall
tailscale-pihole-dns-routingjackson2w/claude-code-skillsThis skill should be used when a host or device on a network with both Tailscale and Pi-hole seems to bypass Pi-hole's ad-blocking despite DNS still resolving fine, when deciding whether to use Tailscale's tailnet-wide "Override DNS servers"/Global Nameservers setting (including whether to enable it for roaming ad-blocking), when a device's DNS silently breaks after that Override toggle is turned off, when Pi-hole silently rejects/resets DNS queries arriving over a Tailscale interface, or when systemd-resolved needs to be configured so a host gets Pi-hole for general DNS while keeping Tailscale MagicDNS working for *.ts.net hostnames. Trigger phrases include "tailscale override dns servers", "pihole bypassed tailscale", "resolv.conf generated by tailscale do not edit", "magicdns not resolving publicly", "systemd-resolved pihole tailscale", "Domains=~. resolved.conf", "tailscale accept-dns per device", "DNS=~. wildcard route", "pihole-dns-client playbook", "host missed by dns overhaul", "apt-get update failed after systemd-resolved install", "SSH_CLIENT tailscale IP over LAN hostname", "magicdns wrong answer right after tailscaled restart", "pihole listeningMode LOCAL", "dns.listeningMode ALL", "pihole rejects tailscale query connection reset", "roaming ad-blocking over tailscale", "nftables flush ruleset wipes tailscaled", "cloudflare backup nameserver tailscale unreliable", "tailscale global nameserver backup order", "ssh could not resolve hostname", "getent hosts not found but dig works", "ResolveUnicastSingleLabel", "single-label hostname resolution fails", "bare hostname ssh resolve failure ansible", "resolvectl query not found LLMNR", "restart of systemd-resolved failed exit status", "dns using direct mode directManager", "tailscale apt upgrade broke dns", "systemctl restart tailscaled did not fix dns", "resolv.conf plain file instead of symlink".Stars: 1Updated Claude CodeCodexUnverifiedInstall
termius-fleet-ssh-setupjackson2w/claude-code-skillsThis skill should be used when setting up or extending Termius as an SSH client across a fleet of mixed LXC/VM/bare-metal/VPS hosts, when adding a new host to an existing Termius setup, when building Termius Snippets or Startup Snippets for recurring diagnostic commands, when a Termius SFTP session lands in the wrong directory or the user asks how to bookmark a remote SFTP path, or when an SFTP connection silently lands in the home directory instead of the intended target directory. Trigger phrases include "termius setup", "add a host to termius", "termius snippet", "termius startup snippet", "termius broadcast", "termius workspace", "sftp default path", "sftp bookmark remote directory", "Subsystem sftp -d flag", "sftp lands in home directory instead of", "termius keychain import ssh key", "tmux new -As", "termius sftp permission denied silently falls back".Stars: 1Updated Claude CodeCodexUnverifiedInstall
unifi-wireguard-vpn-clientjackson2w/claude-code-skillsThis skill should be used when running or debugging a commercial WireGuard VPN (Proton, Mullvad, etc.) as a WireGuard CLIENT on a UniFi gateway (UCG/UDM) with policy-based traffic routes for chosen devices — sites hang or half-load only while on the VPN, the tunnel's health probes pass but real browsing stalls, an app (WhatsApp media, a bank app) fails only through the tunnel, QUIC/HTTP3 gets no reply, MTU/MSS questions, domain-based VPN bypass, or a watcher that fails over between tunnels. Trigger phrases include "sites hang on vpn", "proton on unifi", "wireguard client unifi", "traffic route kill switch", "vpn bypass domain", "QUIC through VPN", "UDP 443 no reply", "MSS clamp vpn", "mtu black hole wireguard", "probe passes but sites fail", "trafficroutes api", "proton-watch", "vpn degraded".Stars: 1Updated Claude CodeCodexUnverifiedInstall
fes-agent-portabilitymodassarislam37/funnel-engineering-systemInstall, invoke, diagnose and distribute Funnel Engineering System skills across Codex, Claude Code, Cursor, Gemini CLI, GitHub Copilot and OpenCode, while preserving host-specific permission boundaries.Stars: 1Updated Claude CodeCodexUnverifiedInstall
fes-coordinatormodassarislam37/funnel-engineering-systemCoordinate bounded host subagents and engineering handoffs while preventing overlapping edits and false claims of independent review.Stars: 1Updated Claude CodeCodexUnverifiedInstall
fes-evaluationmodassarislam37/funnel-engineering-systemEvaluate Funnel against standard agent with paired, held-out engineering tasks, reproducible quality evidence and explicit pass/fail metrics; use when assessing reliability or promoting a generated skill.Stars: 1Updated Claude CodeCodexUnverifiedInstall
fes-skill-forgemodassarislam37/funnel-engineering-systemDetect a verified gap in FES engineering capabilities and create a narrow, project-local, instruction-only agent skill that is validated and immediately applied to the current task when useful. Do not generate a skill for every task.Stars: 1Updated Claude CodeCodexUnverifiedInstall
graph-lcb1lucascb/graph-lcbUse the `graph` CLI (graph-lcb) to build, validate, and query typed, evidence-backed knowledge graphs stored in a local `.graph/` workspace. Make sure to use this skill whenever the user mentions graph-lcb, the `graph` command, a `.graph/` folder, graph.json, entity or edge contracts, JSONL batch imports, or wants to map, model, explore, or query a codebase, multiple repositories, documents, systems, or any domain as a graph with nodes and edges, even if they never name the tool. Also use it for searching or traversing an existing graph, finding paths or dependencies between nodes, creating or changing contracts, and importing records in bulk. Also use it to continue an unfinished mapping or to keep a graph current after its sources change.Stars: 1Updated Claude CodeCodexUnverifiedInstall
graph-lcb1lucascb/graph-lcbUse the `graph` CLI (graph-lcb) to build, validate, and query typed, evidence-backed knowledge graphs stored in a local `.graph/` workspace. Make sure to use this skill whenever the user mentions graph-lcb, the `graph` command, a `.graph/` folder, graph.json, entity or edge contracts, JSONL batch imports, or wants to map, model, explore, or query a codebase, multiple repositories, documents, systems, or any domain as a graph with nodes and edges, even if they never name the tool. Also use it for searching or traversing an existing graph, finding paths or dependencies between nodes, creating or changing contracts, and importing records in bulk. Also use it to continue an unfinished mapping or to keep a graph current after its sources change.Stars: 1Updated Claude CodeCodexUnverifiedInstall
linkedin-account-managervpicciuolo/Linkedin-SuperAgent-MultiSkillsReview, prepare, and manage approved changes across a LinkedIn member profile or company page. Use for headline, About, Experience, Featured, skills, page details, content, comments, inbox, connections, and account housekeeping.Stars: 1Updated Claude CodeCodexUnverifiedInstall
oyyo-linkedinvpicciuolo/Linkedin-SuperAgent-MultiSkillsRoute an end-to-end LinkedIn request to the right OYYO ONE AI workflow. Use for broad LinkedIn goals, multi-step projects, or when the user asks what this pack can do. For a single clear task, use the focused skill directly.Stars: 1Updated Claude CodeCodexUnverifiedInstall
pretty-mermaiddrafael/coding-harnessRender beautiful Mermaid diagrams as SVG or ASCII art using the beautiful-mermaid library. Supports 15+ themes, 5 diagram types (flowchart, sequence, state, class, ER), and ultra-fast rendering. Use this skill when: 1. User asks to "render a mermaid diagram" or provides .mmd files 2. User requests "create a flowchart/sequence diagram/state diagram" 3. User wants to "apply a theme" or "beautify a diagram" 4. User needs to "batch process multiple diagrams" 5. User mentions "ASCII diagram" or "terminal-friendly diagram" 6. User wants to visualize architecture, workflows, or data modelsStars: 1Updated Claude CodeCodexUnverifiedInstall
reflectdrafael/coding-harnessReview the current session for durable, evidence-backed improvements to existing local skills. Manual invocation only; use when the user explicitly asks to reflect or run a session retrospective. Never edit skills or perform external actions without individual approval.Stars: 1Updated Claude CodeCodexUnverifiedInstall
sharpendrafael/coding-harnessDeepen a task without broadening its scope, then rewrite its prompt. Manual invocation only; use when the user explicitly invokes sharpen or requests this prompt-sharpening workflow. Do not execute the rewritten task or decide choices the user owns.Stars: 1Updated Claude CodeCodexUnverifiedInstall
skill-hunterdrafael/coding-harnessUse when the user wants to find NEW external skills for a project, build a skill stack from external registries, or compare external options against project needs. Do not use for questions about how to use already-installed/local skills.Stars: 1Updated Claude CodeCodexUnverifiedInstall
continue-workTsukiNi22/ai-utilsResume a task stopped with the pause skill at the user's next "continue" - reads the checkpoint of the project (~/.claude/pauses, checkpoint.sh of pause), checks it against the real state (git status and diff, the files, what still runs) and trusts the real state when they differ (the user may have changed things meanwhile), starts again what was stopped and is still needed, redoes the interrupted step from its start, then goes on with the next steps in order without redoing what is done and without a recap; closes the checkpoint when the task is over. Without a checkpoint it simply continues the current task of the conversation. Use whenever the user says "continue", "reprends", "on reprend", "vas-y continue", "resume", "go on", "/continue-work" after a pause, or opens a session in a project that has a checkpoint waiting.Stars: 1Updated Claude CodeCodexUnverifiedInstall
pauseTsukiNi22/ai-utilsStop everything cleanly in the middle of a task so that it can go on later - no new step started, the step under way brought to a consistent state (never a file half edited or a build left broken), every background job / monitor / subagent / workflow / build / loop / scheduled wake-up started for the task stopped, nothing committed or pushed that the rules of the user do not allow, then a checkpoint written (goal, rules, done, interrupted, the exact next steps, what was stopped and how to start it again, files changed, decisions) and one short message - the work resumes at the next "continue" (continue-work). Use whenever the user says /pause, "stop tout proprement", "arrête-toi proprement", "mets en pause", "on reprendra plus tard", "stop et reprends au prochain continue", "pause the work", "stop cleanly".Stars: 1Updated Claude CodeCodexUnverifiedInstall
setup-studioTsukiNi22/ai-utilsSet up the creative studio of the user's computer - scans the tools there for audio (music, sound effects, voice), image, video, 3D (modeling, CAD) and simulation / VFX / rendering (programs, flatpaks, Python packages, MCP servers, claude.ai connectors, GPU), asks what to cover and whether the work is commercial, searches online for free tools without subscription for what is missing (license and commercial use checked, MCP servers too) and installs the accepted ones, then generates a /studio router and one studio-audio / image / video / 3d / vfx skill saying which installed tool to use for each task, where, how (MCP, command line, GUI) and why, with commands and license notes - in ~/.claude/skills or as a claude.ai personal skill; run again it refreshes them. Use whenever the user wants to set up, scan or refresh their creative / media / audio / video / 3D / VFX tools or MCP servers, or summons /setup-studio.Stars: 1Updated Claude CodeCodexUnverifiedInstall
dispatching-parallel-agentsParsa-29/loop-configUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 1Updated Claude CodeCodexUnverifiedInstall
find-skillsParsa-29/loop-configHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.Stars: 1Updated Claude CodeCodexUnverifiedInstall
line-voice-agentParsa-29/loop-configBuild voice agents with the Cartesia Line SDK. Supports 100+ LLM providers via LiteLLM with tool calling, multi-agent handoffs, and real-time interruption handling.Stars: 1Updated Claude CodeCodexUnverifiedInstall
linear-agent-workflowParsa-29/loop-configUse when coding from Linear issues, syncing task status, creating implementation plans, posting progress comments, or linking GitHub PRs.Stars: 1Updated Claude CodeCodexUnverifiedInstall
llm-contextParsa-29/loop-configUSE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, local/POI. For AI answers use answers. Recommended for anyone building AI/agentic applications.Stars: 1Updated Claude CodeCodexUnverifiedInstall
plantaskParsa-29/loop-configPlan a feature or bug fix and break it into well-formed, non-mixing Linear tasks — one parent issue per feature with ordered, dependency-linked sub-issues, each with a detailed plan, acceptance criteria, labels, and a branch name — ready for a coding agent to execute. Use when the user runs /plantask, or asks to plan and create Linear issues/tasks for a feature, bug, or piece of work.Stars: 1Updated Claude CodeCodexUnverifiedInstall
subagent-driven-developmentParsa-29/loop-configUse when executing implementation plans with independent tasks in the current sessionStars: 1Updated Claude CodeCodexUnverifiedInstall
using-superpowersParsa-29/loop-configUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questionsStars: 1Updated Claude CodeCodexUnverifiedInstall
graphql-mcpvertivolatam/monorepoStars: 1Updated Claude CodeCodexUnverifiedInstall