yskills

In the author's own words, from each skill's SKILL.md.

• cold-read

  Cold-read user-facing words the way a first-time, lazy, hurried reader would, using fresh-context reader subagents that never saw the conversation that produced them: UI copy (a strings-file diff, screenshots, or a who/where/text list), landing pages, profile bios, decks and charts, plans, emails, notifications, application answers, and the options an agent is about to show a human. Finds text th…

  skills/cold-read/SKILL.md on GitHub (opens in a new tab)

• human-context-rebuild

  Rebuild the user's mental model of the current session with a tight recap — what we're doing, why, and where we are. Use this to recover after a break, a tangent, or a long subagent run. Trigger when the user invokes /human-context-rebuild, or says "remind me what we're doing", "我忘了", "我们到哪一步了", "where are we", "what was I doing", "summarize this session", "我们在干啥来着", "这是啥来着", "这个是干嘛的来着", "想不起来这个…

  skills/human-context-rebuild/SKILL.md on GitHub (opens in a new tab)

• stale-check

  Judge whether the current repo / branch / worktree is stale — behind its target branch, already merged (incl. squash-merged via PR), merged but with commits piled on afterwards, abandoned, unpushed, or about to conflict on rebase — and say what to do about it. Read-only (only `git fetch --prune`). Trigger on /stale-check (optionally with a repo path, --target <branch>, or --all-worktrees), or whe…

  skills/stale-check/SKILL.md on GitHub (opens in a new tab)

• whats-next

  Re-orient the user after they return to a session — or after they open a FRESH context pointed at a worktree/branch — and let them decide the next step by answering lightweight structured questions (Yes/No, A/B/C/D via AskUserQuestion) instead of facing a blank prompt. Trigger when the user invokes /whats-next (optionally naming a worktree, branch, or repo path), or asks "接下来做什么", "下一步是什么", "我该做什…

  skills/whats-next/SKILL.md on GitHub (opens in a new tab)

• worktree-cleanup

  Actually remove finished git worktrees and their branches after they have been diagnosed: prove each one is merged (squash merges included) and clean, stop dev servers still running inside, remove the worktree and branch with plain git, prune dead registrations and empty shell folders, and report what was kept and why. Trigger when the user says "clean up my worktrees", "delete the merged ones",…

  skills/worktree-cleanup/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 434k stars · 5 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 298k stars · 30 skills
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 230k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 185k stars · 6 skills
• difyby langgenius Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-h… 160k stars · 7 skills
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 146k stars · 7 skills