Write a resume-ready capsule of your session, then /clear or auto-compact and pick up where you left off. Adds /capsule, /refresh and /resume plus SessionStart and PreCompact hooks. Zero dependencies, no network.
Turn a PCB idea into a wired .kicad_pcb ready for EasyEDA auto-routing and one-click JLCPCB ordering — LCSC part sourcing, EasyEDA pin-map auto-fetch, and session-persisted workflows.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Create a repo-local Agent Skill following the open agentskills.io specification. Use when the user wants to create, scaffold, or initialize a new skill in the current repo, mentions a 'repo-local skill' or the agentskills.io spec, or needs a spec-compliant SKILL.md placed under .agents/skills/ (or .claude/skills/). Scaffolds the directory, writes valid name/description frontmatter, and validates with skills-ref.
Build and refactor CLIs for AI agent compatibility. Use when making CLI tools machine-readable with structured JSON output, input hardening, schema introspection, dry-run safety, and MCP surfaces.
Memory that persists across sessions (stored word for word in local SQLite, recalled within a token budget), plus setup and savings commands for llmslim wrap claude.
Copywriting skill for Claude that writes copy which sells. Print ads, OOH, headlines, landing pages, ads, emails. Built on D&AD Copy Book craft and Bly direct-response frameworks. Cannes Lions and Clio Award winners as the gold standard.
Turn any YouTube video into a bilingual (Arabic/English) study guide: timestamped explanation, 5-minute summary, animated concept visuals, scenario quiz and spaced-repetition flashcards.
Several models on the same question at once — Claude sub-agents, OpenAI Codex and a cheap third via OpenCode. Review code, check whether the work is actually finished, brainstorm wide with a different model per cognitive frame, or just ask all of them something.
Session re-orientation, branch staleness and cleanup, and cold reads: /whats-next, /human-context-rebuild, /stale-check, /worktree-cleanup, /cold-read, plus the idle-return hook