Loading…
Showing 5221–5250 of 10177 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| author-agent-instructionsbaldaworks/promptkittyTurn a fully assembled PromptKit prompt into ready-to-commit project instructions or a provider-native subagent profile. Use when the user asks to create persistent agent guidance, custom agent instructions, an agent profile, a subagent, or equivalent files for Codex, Claude Code, Grok Build, GitHub Copilot, OpenCode, or Cursor. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| kk-session-restorekkfor30/kk-sessions撤销 kk-sessions 对侧栏做过的改动:按首次使用前存下的快照,把会话标题和所在分区恢复原样,删除 kk-sessions 新建的分区。用户说"撤销 kk-sessions 的改动""恢复会话原样""回滚会话整理""kk-session-restore"时使用,通常在停用或卸载 kk-sessions 之前;卸载后也能用(见「卸载后」)。支持 Claude Code 桌面端和 Codex 桌面端。不删除会话,不移动或删除磁盘上的文件夹。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| agents-memoryakunzai/agent-skillsRecord, recall, or forget notes in the agent's global or project memory, deciding scope (global vs. project) and tier (short-term candidate vs. long-term durable) when recording. Use on `/agents-memory`, `$agents-memory`, "remember this", "what did I note about X", "recall", or "forget X". Autonomous knowledge capture after solving a problem is agents-md's Prevent Recurrence, not this skill. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| realitygate-scanusmanmanii/realitygateCheck whether an agent skill, Claude Code plugin, MCP config or AI coding extension is safe before installing it — scans for remote code execution, obfuscated payloads, hidden Unicode instructions, credential or .env access, data-leak endpoints, prompt injection, permission bypass, hooks, MCP servers and install scripts. Use when the user asks if a skill, plugin, extension or repository is safe, trustworthy or malware-free, or before installing one from the internet. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| scanusmanmanii/realitygateCheck whether an agent skill, Claude Code plugin, MCP config or AI coding extension is safe before installing it — scans for remote code execution, obfuscated payloads, hidden Unicode instructions, credential or .env access, data-leak endpoints, prompt injection, permission bypass, hooks, MCP servers and install scripts. Use when the user asks if a skill, plugin, extension or repository is safe, trustworthy or malware-free, or before installing one from the internet. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| ably-automationranbot-ai/awesome-skillsAutomate Ably tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| abstract-automationranbot-ai/awesome-skillsAutomate Abstract tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| abuselpdb-automationranbot-ai/awesome-skillsAutomate Abuselpdb tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| abyssale-automationranbot-ai/awesome-skillsAutomate Abyssale tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| accelo-automationranbot-ai/awesome-skillsAutomate Accelo tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| accredible-certificates-automationranbot-ai/awesome-skillsAutomate Accredible Certificates tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| acculynx-automationranbot-ai/awesome-skillsAutomate Acculynx tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| active-campaign-automationranbot-ai/awesome-skillsAutomate ActiveCampaign tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| addresszen-automationranbot-ai/awesome-skillsAutomate Addresszen tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| adobe-automationranbot-ai/awesome-skillsAutomate Adobe tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| adrapid-automationranbot-ai/awesome-skillsAutomate Adrapid tasks via Rube MCP (Composio). Always search tools first for current schemas. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| concealed-actioncisco-ai-defense/skill-scannerConceal an agent action from the user who requested the task | Stars: 2.7k | Updated | Claude CodeCodex | Verified | Install |
| external-instruction-followercisco-ai-defense/skill-scannerDelegate agent behavior to instructions obtained from an external page | Stars: 2.7k | Updated | Claude CodeCodex | Verified | Install |
| about-me-skill-creatorCowboyLogic/ai-devCreate or refresh a private `about-me` skill containing durable personal context, communication preferences, tooling constraints, and autonomy boundaries. Use when a user asks to create, customize, review, or update their about-me profile or personal agent context. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| agent-creator-claudecodeCowboyLogic/ai-devGuide for creating custom subagents for Claude Code (Markdown files in .claude/agents/ or ~/.claude/agents/ with YAML frontmatter). Use this skill whenever a user wants to build, configure, review, or modify a Claude Code agent, choose frontmatter fields (tools, disallowedTools, model, permissionMode, skills, mcpServers, hooks, memory, isolation), or troubleshoot an agent that does not load, is never delegated to, has the wrong tools or model, or ignores a frontmatter field. ALWAYS load this skill before writing or debugging Claude Code agent files. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| agent-creator-codexCowboyLogic/ai-devGuide for creating custom subagents for OpenAI Codex (standalone TOML files in .codex/agents/ or ~/.codex/agents/, each with name, description, and developer_instructions). Use this skill whenever a user wants to build, configure, review, or modify a Codex agent, choose fields (model, model_reasoning_effort, developer_instructions, and the other keys a role file can actually set), tune the [agents] table in config.toml (concurrency, default subagent model), or troubleshoot a Codex agent that is not found, never spawned, on the wrong model, or unexpectedly writing files or missing MCP servers. ALWAYS load this skill before writing or debugging Codex agent files. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| agent-creator-copilotCowboyLogic/ai-devGuide for creating custom agents for GitHub Copilot (cloud agent on GitHub.com, Copilot CLI, VS Code, and other IDEs). Use this when building custom agent profiles (.agent.md files), configuring tools, models, handoffs, subagents, hooks, or MCP server integrations for Copilot. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| client-config-opencodeCowboyLogic/ai-devManage OpenCode configuration files (V2 native format by default, V1 supported) including MCP servers, providers, models, agents, commands, permissions, policies, skills, plugins, CLI/TUI settings, keybinds, and themes. Use this skill whenever the user wants to view, edit, add, migrate, or understand any opencode setting in opencode.json(c), cli.json, or tui.json. Trigger on: "configure opencode", "add provider", "set model", "add MCP server", "create agent", "configure permissions", "change theme", "add keybind", "show opencode config", "add custom command", "migrate opencode config to V2", or "opencode cli.json". | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| markdownlint-validatorCowboyLogic/ai-devGuide for identifying and fixing markdownlint violations in Markdown files. Use this skill whenever asked to fix markdown linting errors, validate markdown files, resolve markdownlint violations, clean up markdown formatting issues, enforce markdown style rules, or correct any MD### rule failures. Always load this skill when working with .markdownlint config files or markdownlint-cli output. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| skill-routerCowboyLogic/ai-devFind an installed skill in the skill library, a folder of skills kept outside the harness's discovery path so their descriptions do not load into every session. Search it BEFORE starting a task that a specialized skill could cover and that no skill already listed in this session fits, and whenever the user names a skill you cannot see or asks what skills are installed. Returns the skill's directory so you can read and follow it. When the library has none, it searches GitHub for one to offer the user. Also use it when the user asks to install, update, review, or remove a skill in the library. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| ghidra-iterative-reGeReV/ghidra-iterative-reUse when reverse-engineering a game (or any binary) in Ghidra via MCP or PyGhidra - establishes the apply-cascade-verify loop, the SourceType trust model that stops an agent corroborating its own guesses, invariant bracketing against Ghidra's silent collateral damage, and the game-specific evidence sources worth sweeping before any analysis. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| skf-update-skillarmelhbobdad/oh-my-skillsSmart regeneration preserving [MANUAL] sections after source changes. Use when the user requests to "update a skill" or "regenerate a skill." | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| stale-loreandresanemic/lore-pluginUse when the kit's published surface must be reconciled against actual usage in the user's tree. Trigger on "stale-lore", "retira capacidades", "capacidades sin ejercicio", "purge unused skills", or after a major refactoring that renames or replaces published capabilities. Not yours: operating a project's criteria body belongs to transmute-lore; saving one lesson belongs to save-to-lore. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| codex-reviewaugchan42/inkstoneRun an independent code review of any git scope — uncommitted changes, a commit range, a merge commit, a PR, or specific paths — via Codex CLI, opencode, or context-blind subagents, then triage every finding with an explicit disposition. Use when asked to "review this diff", "codex review", "review PR N", "review the merge commit", or to get a second opinion on changes before or after merge. For reviewing implementation plans rather than code, see plan-review-loop. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| critic-loopaugchan42/inkstoneRun an independent critic loop on generated work that is not code or a plan — images, renders, ASCII or canvas art, video stills, frames and shorts, covers, copy. A fresh-context critic scores each round against a rubric written before round 1, starts with a blind read (it says what it sees before it is told what was intended), lists every gap, and the loop stops on a threshold, a stall rule or a round limit. Use when asked to "critic loop", "have a critic score this", "get an independent critic", or before showing generated visuals or copy to the owner as ready. For code, see codex-review; for implementation plans, see plan-review-loop. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |