Loading...
Loading...
Found 3,198 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).
Automatically generate a Chinese session summary when a Claude Code session ends, and save it to .claude/summaries/. It is used when users need to record conversation history, generate work logs, or review context.
Configure des hooks Claude Code pour bloquer les commandes git dangereuses (push, force-push, reset --hard, clean, branch -D, checkout/restore) avant leur exécution. Empêche les opérations git destructrices au niveau de l'agent.
Forensic diagnostic report for LOCI — collects environment state, runs health checks, and writes a timestamped report when analysis fails or doesn't trigger. Invoke when: "bug report", "LOCI isn't working", "exec-trace didn't run", "skill didn't trigger", "MCP not connecting", "results are wrong", "results missing", "generate diagnostic", "something is broken", "debug LOCI", or any LOCI failure the user wants investigated.
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.
Claude Code skill that designs and builds high-converting questionnaire-style app onboarding flows modelled on proven conversion patterns from top subscription apps like Noom, Headspace, and Duolingo.
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 use the 毛选.skill cognitive framework for Claude Code — applies Mao Zedong's strategic mental models (contradiction analysis, protracted war, rural encirclement, united front) to help analyze problems, devise strategies, and cut through complexity.
Internal conversation-entry router for Claude Code. Performs a lightweight intake pass at the start of substantive work: decide whether a more specific skill should be invoked first, whether specialized agent delegation is warranted, how much context is actually needed, and whether the task needs planning or can proceed directly. Not a user-facing slash command.
Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.
Generate a /goal mega prompt for Claude Code or Codex CLI by interviewing the user about their task. Use when the user wants to define a long-horizon autonomous goal — migration, refactor, feature build, optimization loop, test fixing, research project, learning system, or any task where the agent should run end-to-end without hand-holding. Trigger on: "help me write a goal", "I want Claude to keep working until...", "run this autonomously", "set a /goal", or any request that implies sustained agentic execution toward a non-trivial outcome. The skill conducts a structured interview (one question at a time) to extract outcome, context, success criteria, constraints, and quality bar — then outputs a filled-in mega prompt ready to paste into Claude Code or Codex.
Keeps a long Claude Code task on-track — breaks out of looping/circular thinking, watches the context budget, bounds internal reasoning, and triggers a clean handoff before the window fills. Use when the model is repeating steps, re-reading the same files, second-guessing in circles, stuck or spinning, or running a long multi-step task at risk of exhausting context. Also use when the user says it is "looping", "going in circles", "stuck", "repeating itself", or asks for a handoff before running out of context.