Loading...
Loading...
Found 8,857 Skills
Collaboration Process for UI Style Modifications. Used when users request page style changes, layout adjustments, or UI detail tweaks. The structured process of "Screenshot Localization → Current Status Description → Option Selection → Code Modification → Fine-tuning" reduces communication deviations and avoids token waste.
Review current uncommitted git changes with full file context and produce a structured report with severity levels, actionable fixes, and an approval verdict.
Review recent work, identify process gaps and repeated mistakes, and produce specific file edits to prevent them. Not a reflection exercise — outputs config and identity changes. Trigger manually after sprints, or automate weekly.
Add or change allowed commands in AI agent permission configs (OpenCode, Claude Code)
Initialize or update project documentation. Use when setting up docs for a new project (`--init`) or syncing docs to current codebase and architecture changes (`--update`).
Use when marking a task as complete, finishing a feature, or claiming a bug is fixed. Ensures functional resolution is verified with evidence before closing.
This skill is intended for translating academic texts between Chinese and English. It is activated by keywords such as "翻译", "中译英", "英译中", "translate", "paper translation", "academic writing", or when academic documents (including 论文, 文献, 摘要, paper, abstract, manuscript) require translation that adheres to scholarly rigor and consistent terminology.
Feishu (Lark) API Integration Guide. Use this when users request to "create Feishu apps", "manage base tables", "add collaborators", "generate Feishu reports", "set Feishu permissions" or "automate Feishu operations". Prioritize using MCP tools for real-time interactive operations.
Orchestration mode for implementation tasks. Manages the plan → code → review loop. Use /orchestrate <requirements> or let /implement invoke it.
NEVER escalate without investigation first. This is the Iron Law. Use when evaluating whether to escalate models, facing genuine complexity requiring deeper reasoning, novel patterns with no existing solutions, high-stakes decisions requiring capability investment. Do not use when thrashing without investigation - investigate root cause first. DO NOT use when: time pressure alone - urgency doesn't change task complexity. DO NOT use when: "just to be safe" - assess actual complexity instead.
Schedule "research + content production" tasks in A/B/C levels. First define the audience, goal, carrier and perspective, then follow the Research→Synthesis→Content pipeline to output publishable content and evidence chains. It is suitable for writing tasks that require credible conclusions, stable structure and reusable material precipitation.
Maintains CHANGELOG.md following Keep a Changelog format and Semantic Versioning. Use when the user mentions preparing or publishing a new release, or asks to review or refactor CHANGELOG.md.