Loading...
Loading...
Found 3,182 Skills
Sharpen, refine, and optimize AI agent skills through real usage — learn from mistakes, review quality, and improve over time. Observes skill execution in the current conversation, analyzes three sources (conversation history, file diffs, user feedback), and proposes concrete improvements to the target skill's SKILL.md. Works with Claude Code and any SKILL.md-based agent framework. Use after executing any skill: `/skill-sharpen [name]` for a specific skill, or `/skill-sharpen` to auto-detect the last used. Three modes: interactive (propose one by one), observe-only (dump to LESSONS.md), review (process pending lessons).
Mine Claude Code session logs for skill idea candidates. Use when running the weekly skill generation pipeline to extract, score, and backlog new skill ideas from recent coding sessions.
Better Harness Tools for Claude Code — a Python (and in-progress Rust) rewrite of the Claude Code agent harness, with CLI tooling for manifest inspection, parity auditing, and tool/command inventory.
Creates oh-my-claude statusline plugins from scratch. Use when the user asks to build, create, make, or scaffold a new statusline plugin, segment, or widget for oh-my-claude or Claude Code's statusbar. Handles both JS plugins and script plugins (Python, Bash). Generates the plugin file, tests it, wires it into the statusline, and verifies it renders.
一键安装自定义状态行脚本到 ~/.claude，显示模型、Git状态、上下文使用率、成本和worktree信息
Diagnose and repair 'invalid high surrogate' API errors in Claude Code chat sessions. Use this skill when the user encounters API Error 400 with 'invalid high surrogate in string', 'not valid JSON', surrogate-related errors, or wants to fix/scan/repair a broken Claude Code JSONL chat file. Also use when a session refuses to resume due to JSON encoding errors, or when the user mentions request IDs (req_...) alongside JSON parse failures.
Creates implementation tasks as Claude Code custom slash commands with dependency ordering and atomic scope. Use when breaking down features into executable task commands, planning implementation order, defining task dependencies, or when user mentions task breakdown, implementation plan, or work decomposition for spec-driven development.
Install and configure a Claude Code status line that displays real-time ZenMux account information: subscription tier, 5-hour and 7-day quota usage with color-coded progress bars, and PAYG wallet balance, alongside standard session info (model, git, context usage, prompt cache). Trigger on: "status line", "statusline", "set up status bar", "show ZenMux in status bar", "install ZenMux statusline", "configure status line with ZenMux", "状态栏", "配置状态栏", "安装状态栏", "在状态栏显示ZenMux信息". Activate when user wants to SET UP, INSTALL, CONFIGURE, or CUSTOMIZE a Claude Code status line that includes ZenMux account data. Do NOT trigger for querying usage interactively (use zenmux-usage), docs (use zenmux-context), or general setup (use zenmux-setup).
Local token cost analytics dashboard for Claude Code sessions — reads JSONL transcripts and provides per-prompt cost breakdowns, heatmaps, and usage insights.
This skill should be used when searching Claude Code session transcripts with semantic understanding. Triggers on queries like "find sessions about X", "when did I work on Y", "search previous conversations". Supports natural language queries with synonym matching.
Creates or audits a Claude Code hook. Use when user says 'add a hook', 'create a hook', 'review our hooks', 'audit hooks', 'wire up a format-on-save hook', 'block edits to secrets', or 'our hooks are broken'. Do NOT use for skills (use create-or-audit-skill), agents (use create-or-audit-agent), or settings (edit `settings.json` directly).
Convert a local AGENT.md into a Claude Code optimized agent. Audits one agent against Claude Code runtime behavior, creates a per-agent DAG rewrite plan with source-backed guardrails, and optionally rewrites the frontmatter and system-prompt body so the agent is thinner, more role-specific, and better aligned with Claude's agent runtime. Use when the user says "convert this agent to Claude", "normalize this AGENT.md", "thin this agent", or "rewrite this persona for Claude Code".