Loading…
Showing 6211–6240 of 10177 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reviveGeiserX/sstackBring cut-off work back exactly where it stopped after a usage limit, a crash, a restart or a compaction, without doing anything twice. Use when a session resumes after a limit or crash, when agents or background tasks died mid-work, or when asked to continue, resume or revive. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| mastromastro-hq/mastro-connectCore conventions for the mastro CLI — connectors that let agents drive web apps through the apps' own APIs, replayed with the user's own browser session. Read this before using any mastro provider command, or when the user mentions mastro, asks to log in to a connector, or a mastro command fails with an auth error. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| mastro-authormastro-hq/mastro-connectBuild a new mastro connector for a web app — capture how the app talks to its own backend, find the minimal session auth, and write the auth.manifest.json + OpenAPI 3.1 spec + skills that turn it into `mastro <app> <command>`. Use when the user wants mastro (or an agent) to work with a site that has no connector yet, says "make a mastro connector for X", "add X to mastro", "reverse-engineer X's API", or asks to add a command to an existing connector or fix one that drifted. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| ax-extract-workflowMarvellbrazil/my-agentic-skillsReconstruct workflow behind a past coding-agent artifact using local ax sessions/commits/skills/tool traces. Use when asked how X was built. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| global-chat-agent-discoveryMarvellbrazil/my-agentic-skillsDiscover and search 18K+ MCP servers and AI agents across 6+ registries using Global Chat's cross-protocol directory and MCP server. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| orca-cliMarvellbrazil/my-agentic-skillsOperate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| orchestrationMarvellbrazil/my-agentic-skillsCoordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator loops, and decomposing work across agents. Use `orca-cli` for full ownership handoffs — "hand off", "handoff", "handover", "give this to another agent", "another worktree" — unless asked to supervise, monitor, or coordinate a DAG, and for terminal control, lightweight terminal prompts, shell commands, Orca worktree management, and reading or waiting on terminals. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| cloudflare-email-serviceMarvellbrazil/my-agentic-skillsSend and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing). Use when building email sending (Workers binding or REST API), email routing, Agents SDK email handling, or integrating email into any app — Workers, Node.js, Python, Go, etc. Also use for email deliverability, SPF/DKIM/DMARC, wrangler email setup, MCP email tools, or when a coding agent needs to send emails. Even for simple requests like "add email to my Worker" — this skill has critical config details. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| walk-playbookmr-kelly/skills遛狗手册(做事手册):Agent 每天定遛狗钟点之前先读这本手册,按「规则卡」选钟点。手册只能通过变更请求修改,主人合并才算数。 | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| eval-evolutionMiaoDX/roboclawsPrepare, run, review, and explicitly promote bounded Skill or existing-MCP Eval Evolution campaigns through the canonical eval facade. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| eval-harnessMiaoDX/roboclawsSelect and run Roboclaws validation, product, eval-suite, and live-agent eval rows from a plan, diff, or explicit capability request. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| household-worldMiaoDX/roboclawsComplete household-world goals through public household MCP tools. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| report-performance-analysisMiaoDX/roboclawsUse this skill whenever the user asks whether a Roboclaws live-agent report run is faster, wants to compare Agent SDK/Codex/Claude cleanup reports, asks about model-call work, residual latency, speedup validity, or report performance under provider/network variance. The skill extracts sanitized JSON metrics first and answers only from generated metric/comparison artifacts, not from report.html scraping or raw prompts. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| scene-gaussian-map-alignmentMiaoDX/roboclawsAlign scene Gaussian/splat, USD/mesh, and robot map assets into an honest digital-twin evidence workflow. Use when a new Gaussian scene arrives, when B1/Map12-style assets need to be connected, when map anchors are being projected into a 3D scene, or when an agent must decide whether an alignment is candidate, verified, runtime-proven, or planner-backed. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| god-imagegencumabozkurt/god-of-designIllustration and image-generation prompting for Midjourney, GPT Image, Gemini/Imagen, FLUX, Stable Diffusion, Ideogram, Recraft and Firefly - prompt anatomy, style vocabulary (techniques, photography, lighting, camera, materials), aspect ratios, consistency, negative prompts, text-in-image, editing and ethics. Use when the user needs illustrations, photos, mockups, textures or reference boards generated by AI. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| figurea554b554/ReactantReactant tag-only figure generation. Use only when execute or execute-one dispatches an exact <@figure> tag from a document; never activate from ordinary chat or another skill. | Stars: 54 | Updated | Claude CodeCodex | Verified | Install |
| plota554b554/ReactantReactant tag-only data visualization. Use only when execute or execute-one dispatches an exact <@plot> tag from a document; never activate from ordinary chat or another skill. | Stars: 54 | Updated | Claude CodeCodex | Verified | Install |
| thanks-momgoogool2/thanks-momTidies a messy project folder without breaking anything. Deletes regenerable bloat (node_modules, .venv, caches), boxes agent leftovers (tmp scripts, *_old files, logs, duplicates, screenshots) into a recoverable zip, asks the user about anything uncertain, merges repeated one-off scripts into one reusable tool, and writes PROJECT_MAP.md so agents can find files after a context reset. Use when the user says "thanks mom", "clean up / tidy / organize this project", "shrink this folder", "this repo is a mess", asks for a project map, asks which projects or worktrees take up space, or wants old git worktrees cleaned up. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| reflectolibyte/jev-traderSpawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| agent-markdown-best-practicesNetFabric/intelligentiumALWAYS use when writing or reviewing agent-facing Markdown, including project instructions, skills and references, and custom-agent definitions. Covers only their shared content style: compact executable instructions, scannable information, active language, factual precision, and token efficiency. DO NOT USE FOR: artifact-specific structure, routing descriptions, metadata schemas, or prompt-body requirements; general Markdown documents; Markdown syntax or rendering rules. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| find-BotAdd_CommandHandlermrc4tt/CS2_VibeSignaturesAgent fallback for BotAdd_CommandHandler (auto-generated, category: func). Locate CCSBotManager::BotAddCommand in the CS2 server module via IDA Pro MCP and emit a fresh, minimal-unique artifact. The deterministic preprocessor could not resolve this symbol on the current gamever - your job is the re-sign. Trigger: BotAdd_CommandHandler, CCSBotManager::BotAddCommand | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| find-BotKill_CommandHandlermrc4tt/CS2_VibeSignaturesAgent fallback for BotKill_CommandHandler (auto-generated, category: func). Locate CCSBotManager::BotKillCommand in the CS2 server module via IDA Pro MCP and emit a fresh, minimal-unique artifact. The deterministic preprocessor could not resolve this symbol on the current gamever - your job is the re-sign. Trigger: BotKill_CommandHandler, CCSBotManager::BotKillCommand | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| find-BotProfile_Aggressionmrc4tt/CS2_VibeSignaturesLocate BotProfile::Aggression in CS2 server.dll / libserver.so via IDA Pro MCP and emit a fresh, minimal-unique signature or offset for the local gamedata entry "BotProfile::Aggression" (symbol BotProfile_Aggression). This is a VIRTUAL function - resolve the BotProfile::Aggression vtable via RTTI and identify the slot, then emit the slot. Verify by xrefs from expected call sites. vtable slots commonly differ between platforms - never assume identical indices. Trigger: BotProfile_Aggression, BotProfile::Aggression | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| find-BotProfile_AttackDelaymrc4tt/CS2_VibeSignaturesLocate BotProfile::AttackDelay in CS2 server.dll / libserver.so via IDA Pro MCP and emit a fresh, minimal-unique signature or offset for the local gamedata entry "BotProfile::AttackDelay" (symbol BotProfile_AttackDelay). This is a VIRTUAL function - resolve the BotProfile::AttackDelay vtable via RTTI and identify the slot, then emit the slot. Verify by xrefs from expected call sites. vtable slots commonly differ between platforms - never assume identical indices. Trigger: BotProfile_AttackDelay, BotProfile::AttackDelay | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| find-BotProfile_Costmrc4tt/CS2_VibeSignaturesLocate BotProfile::Cost in CS2 server.dll / libserver.so via IDA Pro MCP and emit a fresh, minimal-unique signature or offset for the local gamedata entry "BotProfile::Cost" (symbol BotProfile_Cost). This is a VIRTUAL function - resolve the BotProfile::Cost vtable via RTTI and identify the slot, then emit the slot. Verify by xrefs from expected call sites. vtable slots commonly differ between platforms - never assume identical indices. Trigger: BotProfile_Cost, BotProfile::Cost | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| find-BotProfile_Difficultymrc4tt/CS2_VibeSignaturesLocate BotProfile::Difficulty in CS2 server.dll / libserver.so via IDA Pro MCP and emit a fresh, minimal-unique signature or offset for the local gamedata entry "BotProfile::Difficulty" (symbol BotProfile_Difficulty). This is a VIRTUAL function - resolve the BotProfile::Difficulty vtable via RTTI and identify the slot, then emit the slot. Verify by xrefs from expected call sites. vtable slots commonly differ between platforms - never assume identical indices. Trigger: BotProfile_Difficulty, BotProfile::Difficulty | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| find-BotProfile_LookAngleDampingAttackingmrc4tt/CS2_VibeSignaturesLocate BotProfile::LookAngleDampingAttacking in CS2 server.dll / libserver.so via IDA Pro MCP and emit a fresh, minimal-unique signature or offset for the local gamedata entry "BotProfile::LookAngleDampingAttacking" (symbol BotProfile_LookAngleDampingAttacking). This is a VIRTUAL function - resolve the BotProfile::LookAngleDampingAttacking vtable via RTTI and identify the slot, then emit the slot. Verify by xrefs from expected call sites. vtable slots commonly differ between platforms - never assume identical indices. Trigger: BotProfile_LookAngleDampingAttacking, BotProfile::LookAngleDampingAttacking | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| find-BotProfile_LookAngleMaxAccelAttackingmrc4tt/CS2_VibeSignaturesLocate BotProfile::LookAngleMaxAccelAttacking in CS2 server.dll / libserver.so via IDA Pro MCP and emit a fresh, minimal-unique signature or offset for the local gamedata entry "BotProfile::LookAngleMaxAccelAttacking" (symbol BotProfile_LookAngleMaxAccelAttacking). This is a VIRTUAL function - resolve the BotProfile::LookAngleMaxAccelAttacking vtable via RTTI and identify the slot, then emit the slot. Verify by xrefs from expected call sites. vtable slots commonly differ between platforms - never assume identical indices. Trigger: BotProfile_LookAngleMaxAccelAttacking, BotProfile::LookAngleMaxAccelAttacking | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| find-BotProfile_LookAngleStiffnessAttackingmrc4tt/CS2_VibeSignaturesLocate BotProfile::LookAngleStiffnessAttacking in CS2 server.dll / libserver.so via IDA Pro MCP and emit a fresh, minimal-unique signature or offset for the local gamedata entry "BotProfile::LookAngleStiffnessAttacking" (symbol BotProfile_LookAngleStiffnessAttacking). This is a VIRTUAL function - resolve the BotProfile::LookAngleStiffnessAttacking vtable via RTTI and identify the slot, then emit the slot. Verify by xrefs from expected call sites. vtable slots commonly differ between platforms - never assume identical indices. Trigger: BotProfile_LookAngleStiffnessAttacking, BotProfile::LookAngleStiffnessAttacking | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| find-BotProfile_ReactionTimemrc4tt/CS2_VibeSignaturesLocate BotProfile::ReactionTime in CS2 server.dll / libserver.so via IDA Pro MCP and emit a fresh, minimal-unique signature or offset for the local gamedata entry "BotProfile::ReactionTime" (symbol BotProfile_ReactionTime). This is a VIRTUAL function - resolve the BotProfile::ReactionTime vtable via RTTI and identify the slot, then emit the slot. Verify by xrefs from expected call sites. vtable slots commonly differ between platforms - never assume identical indices. Trigger: BotProfile_ReactionTime, BotProfile::ReactionTime | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |