Loading…
Showing 5161–5190 of 10177 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| desktop-changearxdsilva/agent-officeChange agent-office's desktop shell — tray menu, native notifications, settings, IPC channels, windows, the auto-updater, packaging/installers or icons. Use for edits under packages/desktop/ (main, preload, electron-builder.yml, e2e) or to core domain tray/attention/update/settings logic. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| interaction-changearxdsilva/agent-officeChange how users talk to agents in agent-office — message states, InboxService, the HTTP inbox/replies routes, the IPC send path, the chat panel, the Claude Code hook (hooks/agent-office-hook.mjs), its wrapper (FsHookRunner) or HookService/installer. Use for edits in core message/hook domain, inbox-service, http-api, ipc-api, panel adapters, hooks/ or scripts/hook-install.ts. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| protocol-changearxdsilva/agent-officeChange agent-office's public contracts — AgentEvent fields, inbox/reply/messages HTTP APIs, the IPC contract (AgentOfficeApi, ServerMessage), or the hook's output. Use whenever packages/shared/src/{protocol,desktop-api,ipc-channels}.ts or an /api route's request/response shape changes. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| coordinate-agentshibeekaey/agent-syncCoordinate a task across multiple AI coding agents (Claude Code, Codex, Gemini, and others). Use when the user asks to delegate work to another agent, get a second opinion or review from a different agent, run agents in parallel on one task, or split a task between agents. The invoking agent becomes the coordinator; other agents are workers. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| implementation-surveytibursocampos/agent-dev-toolkitDescribe what changed and how the implementation appears to work. The report opens with the external observable goal. Descriptive skill, not a code-review mode. Use when invoking /implementation-survey. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| orchestrate-analyzetibursocampos/agent-dev-toolkitOrchestrated Delivery O1: triage a feature, spawn conditional Agent specialists, write FEATURE.md + CONTINUITY + US/TS under features/NNN-slug/. No app code. Use when invoking /orchestrate-analyze. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| sdd-plantibursocampos/agent-dev-toolkitCreate a baby-step PLAN from an existing PRD (agent PLAN .md; language per LANGUAGE.md + preferences). Feeds sdd-develop. Use when creating a plan or invoking /sdd-plan. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| sdd-spectibursocampos/agent-dev-toolkitCreate a PRD for a new feature or change (agent PRD .md; language per LANGUAGE.md + preferences under features/). Feeds sdd-plan. Use when creating a spec or invoking /sdd-spec. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| create-oss-skillurmzd/dotfilesCreate well-formed Agent Skills following the agentskills.io specification. Scaffold directories, write SKILL.md files, bundle scripts, and structure instructions for progressive disclosure. Use when creating a new skill, reviewing skill structure, optimizing a skill description, or setting up evals for skill quality. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| dotfilesurmzd/dotfilesChezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec. Do NOT use for installing tools, running doctor, or updating a machine through the `dotfiles` CLI; use manage-machine. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| orchestrate-agentsurmzd/dotfilesOrchestrate multiple agent CLIs (Claude, Codex, Antigravity) via tmux with a shared fleet store, dispatching one guardian subagent per pane. Survey-first: inspects and adopts existing tmux sessions, windows, and agent panes before creating anything new. Use when running a multi-agent session, dispatching parallel work, or coordinating subagents across panes. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| repo-statusurmzd/dotfilesScan a folder of git repos and report each repo's local dirty/clean state, ahead/behind divergence from upstream, recent activity, and latest CI run status. Read-only: never commits, pushes, or edits. Defaults to the folder argument or your repo root. Use when checking "what's live", "which repos are dirty", or "repo status across my projects". Sibling skills overlap on folder scanning: do NOT use for "what should I work on next" prioritization (use get-work); do NOT use for a recent-activity-only overview without dirty/CI detail (use status). repo-status is the local dirty/ahead/behind + CI-state report. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| elicit-researchodinfree/storm-ecdsa-harnessSearch academic literature through the Elicit API: papers, clinical trials, reports, systematic reviews and Research Agent sessions. Use when a question needs published evidence or an outside, literature-backed view. Needs your own Elicit API key. | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| pip-disciplineodinfree/storm-ecdsa-harnessEvidence-discipline recovery for stalled ecdsa.fail work. Use when the same route, prompt or script has failed twice, an agent keeps tweaking parameters without changing the idea, a failure is blamed on tooling before anyone checked, a completion is claimed without validator output, or a compute request has no owner, validator, kill gate, budget or stop condition. Not for a first pass with a known fix. | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| skill-templateaiskillstore/marketplaceTemplate for production-grade DocEngineering skills | Stars: 488 | Updated | Claude CodeCodex | Verified | Install |
| connectsurface-ai-code/claude-pluginsConnect Claude Code to Surface AI, or fix the connection. Use when the user has just installed the Surface AI plugin, when the surface MCP server's tools are missing, or when /mcp shows the surface server failed (for example a 401 or "Missing or invalid management key"). Not for adding a surface to a page — that's the surfaces skill. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| wayfinderHazmi35/turnfleetPlan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| prompt-optimizertalki-io/prompt-optimizerOptimizes and polishes an existing AI/LLM prompt the user has already written — fixing wording, grammar, structure, redundancy, and clarity — while strictly preserving the original intent, role, scope, capabilities, constraint strength, and every technical detail (commands, paths, URLs, parameters, code blocks). Use whenever the user invokes /prompt-optimizer with a prompt (no extra instruction needed), or pastes a prompt and asks to optimize, refine, polish, clean up, simplify, tighten, restructure, make more professional, or "fix the wording" of it, even without the word "prompt" — e.g. "make this system message clearer", "让这个提示词更专业". Do NOT use for writing a brand-new prompt from scratch, for merely executing a prompt the user provides without asking to optimize it, for polishing ordinary prose (emails, articles, essays), for optimizing source code, or for explaining/teaching prompt-engineering theory. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| gh-wtHikaruEgashira/gh-wtUse this skill whenever the user wants to operate on git worktrees — create, enter, list, remove, or garbage-collect — including parallel agent sessions, side-by-side PR reviews, benchmarking multiple branches, or isolating a dirty tree from a fresh checkout. Trigger even when "worktree" is not said — phrasings like "spin up a fresh copy of branch X", "run claude in a clean checkout", "try this patch without touching my changes", or "open PR-123 side-by-side with main" all qualify. Do NOT trigger for conceptual or educational questions about git worktree (e.g. "what's the difference between git worktree and git clone?") — those are answered from general git knowledge, not this skill. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| agent-onboardingAndrewBrown-USDA/aigb-skills-usdaCreate and maintain AGENTS.md files for project onboarding and grounding. Use when initialized in a new project, when project structure changes significantly, or when creating subfolder-level AGENTS.md files for complex monorepos. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| externalplurigrid/asiExternal skill interface for integration with external systems | Stars: 72 | Updated | Claude CodeCodex | Verified | Install |
| helix-query-from-hqlHelixDB/skillsTranslate legacy HelixDB HQL (.hx QUERY/RETURN syntax) into direct v3 SDK requests (Rust or TypeScript, with Go and Python spellings of the same AST). Use when the input contains HQL concepts such as typed node, edge, or vector sources; AddN/AddE/AddV; Out/In/OutE/InE; FromN/ToN; WHERE/EQ/GT/EXISTS; SearchV/SearchBM25; GROUP_BY/AGGREGATE_BY; ORDER/RANGE; UpsertN/UpsertE; ShortestPathBFS; RerankRRF; Embed; or .hx files. Maps upserts to one conditional write batch and BFS paths to shortest_path, and flags HQL features with no v3 equivalent (reranking, inline embedding, weighted paths, advanced math, EXISTS-in-WHERE, schema defaults, macros). When the target is Helix Cloud, always use helix-mcp first. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| wechat-automationLAVARONG/wechat-automation-api微信发信能力:通过 Windows 桌面微信发送文本、图片URL或本地文件。适合各类 Agent 在本机直接发送一次性消息。触发词:给[某人]发微信、通知[某人]、把这个用微信发给[某人]、用微信发个图片、把本地文件发给[某人] | Stars: 196 | Updated | Claude CodeCodex | Verified | Install |
| memoryopensite-ai/opensite-skillsThe OpenSite persistent long-term memory store. Provides a hierarchical filesystem tree for all agent memories across four cognitive layers: episodic (session history), semantic (project/tech/user knowledge), procedural (decisions, workflows, conventions), and working (active session state). Use this skill to directly read, write, search, or inspect memory entries. For automated session capture use memory-write; for context retrieval before a task use memory-recall; for periodic maintenance use memory-consolidate. | Stars: 15 | Updated | Claude CodeCodex | Verified | Install |
| memory-consolidateopensite-ai/opensite-skillsRuns a background maintenance agent that consolidates, deduplicates, decays confidence, and compresses old sessions in the memory store. Run this skill periodically (weekly or monthly) to keep the memory store lean and high-signal. Also useful after large batches of memory-write operations. Prevents the store from growing stale or bloated over time. | Stars: 15 | Updated | Claude CodeCodex | Verified | Install |
| safe-moderohitg00/pro-workflowPrevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write. | Stars: 2.9k | Updated | Claude CodeCodex | Unverified | Install |
| handofftmusser/ai-engineering-skillsCompress project context into HANDOFF.md with workflow state, analysis checkpoint, next gate, verification, current hypothesis, freshness anchors, optional gotcha references, and a resume packet for the next agent session. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| lean-modetmusser/ai-engineering-skillsCompress routine agent responses to reduce token usage while preserving commands, file paths, assumptions, risks, verification details, and next actions. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| jeecg-uniapp-codegenjeecgboot/skillsJeecgBoot UniApp3 移动端 CRUD 代码生成器。Use when user asks to generate UniApp3/mobile/APP CRUD pages, create mobile list/form pages, or says '生成移动端代码', '生成APP页面', 'uniapp代码生成', '移动端CRUD', '生成uniapp页面', '手机端页面', '移动端模块', 'generate uniapp code', 'mobile CRUD', 'uniapp page', 'APP端代码', '生成小程序页面', '生成H5页面'. Also triggers when user mentions generating mobile pages for an existing backend module, or wants to add mobile support to JeecgBoot modules. Even if user just says '给XX模块加个移动端页面' or '做个手机端的XX功能', this skill should trigger. | Stars: 252 | Updated | Claude CodeCodex | Verified | Install |
| agent-team-harnessai-workspace-lab/xworkspace-core-skillsCoordinate multi-agent work through a tool-neutral contract for authoritative tasks, isolated execution, ownership, handoffs, evidence, acceptance, and archives. Use with harness-workflow for engineering delivery and load matching operations-management standards for operational effects. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |