Loading...
Loading...
Found 20 Skills
Orchestrate GitHub issue authoring by classifying request type, routing to a type-specific issue-author skill, and enforcing shared safety gates before mutation.
通过分析提交历史、分类更改并将技术提交转换为清晰的、面向客户的发布说明，自动从 git 提交创建面向用户的更新日志。将数小时的手动更新日志编写工作缩短为几分钟的自动生成。
Use this when you need to create text card images. It includes generating card HTML and calling the underlying HTML-to-image capability to output the final image. Suitable for scenarios such as WeChat Official Account long article covers, Xiaohongshu/Xiaolvshu graphic covers, etc.
Scaffolds new projects with README.md, AGENTS.md, and CI/CD (GitLab CI, GitHub Actions). Handles project type (generic / Flask backend / React frontend / Taro miniapp), tech stack, coding standards, quality level, and SDD (OpenSpec, SpecKit, GSD). All init flows (Flask, React, Taro) and conventions (backend-python-cicd, frontend-codegen, flask-backend-codegen, QA/testing, agent-roles/subagents) are built-in; no separate skills. Docs default to Chinese. Use when creating a project, initializing a repo, or setting up CI/CD/SDD.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
Convert between Skill (SKILL.md) and Prompt (chat box instruction) formats. Supports two-way conversion between Skill→Prompt and Prompt→Skill with zero loss of core information. Use this when users mention Skill to Prompt conversion, Prompt to Skill conversion, format mutual conversion, or SKILL.md conversion.
Extract a learned skill from the current conversation
Given a domain, identify the few independent forces that truly underpin it. Reduce dozens of phenomena to the minimal set of generators—only when you can regenerate all phenomena from these generators does it count. Use this when the user says 'rank reduction', 'find rank', 'what is rank', 'what supports this domain', 'what lies behind it', or wants to decompose any domain into its irreducible generators.
Automatically suggests optimal files to preload based on the user's task description and historical context patterns. Activates when the user starts a new task, mentions reading files, or when session context is being set up.
Use when beo learnings need a manual consolidation pass across multiple completed features, especially when learnings have gone stale, repeated patterns are accumulating, or the user asks to consolidate, clean up, merge, or promote existing learnings. This is the periodic learnings-sweep skill, not the per-feature compounding step. Use for prompts like "run dream", "consolidate learnings", "merge repeated learnings", or "do a learnings pass".
Ultra-compressed Thai+English communication mode. Cuts ~60-75% of tokens by speaking simple Thai while preserving technical accuracy. Triggers: - "/pordee" / "/pordee full" / "พอดี" / "พอดีโหมด" / "พูดสั้นๆ" → enable full - "/pordee lite" → enable lite - "/pordee stop" / "หยุดพอดี" / "พูดปกติ" → disable - "/pordee-stats" / "/pordee-stats --share" → show token usage stats
Comprehensive research combining web search and AI synthesis. Use for deep research on topics, comparing technologies, investigating libraries, and finding GitHub issues related to problems.