一键导入
duyetbot-knowledge
Knowledge base about Duyet Le (@duyet) and duyetbot behavioral patterns. Owner profile, knowledge sources, and execution transparency.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Knowledge base about Duyet Le (@duyet) and duyetbot behavioral patterns. Owner profile, knowledge sources, and execution transparency.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
Prompt engineering guidance for Claude (Anthropic) model. Use when crafting prompts for Claude to leverage XML-style tags, long-context capabilities, extended thinking, and strong instruction following.
Specialized knowledge for the ClickHouse Monitor dashboard. Use this skill when: working with ClickHouse monitoring dashboards, analyzing query performance, writing ClickHouse system table queries, developing dashboard features, or integrating with the ClickHouse Monitor API. Covers query monitoring, table management, merge operations, system metrics, and ClickHouse version compatibility.
Maintain and update knowledge base about Duyet Le (@duyet) - profile, resume, blog posts, projects.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Prompt engineering guidance for Gemini (Google) model. Use when crafting prompts for Gemini to leverage system instructions, multimodal capabilities, ultra-long context, and strong reasoning features.
Generate or review high-density, interactive, self-contained HTML artifacts based on Thariq Shihipar's "Unreasonable Effectiveness of HTML" patterns. Use this skill when asked to "create HTML," "build a dashboard," "format a PR review," "make an interactive explainer," or when you need to "review and update" existing HTML using the "good-html" style.
| name | duyetbot-knowledge |
| description | Knowledge base about Duyet Le (@duyet) and duyetbot behavioral patterns. Owner profile, knowledge sources, and execution transparency. |
Everything duyetbot needs to know about its owner and how to behave.
Maintain and update knowledge base about Duyet Le (@duyet).
| Source | URL | Type | Update Frequency |
|---|---|---|---|
| Profile | https://duyet.net/llms.txt | LLM-friendly profile | As needed |
| Resume | https://cv.duyet.net/llms.txt | CV/Experience | As needed |
| Blog | https://blog.duyet.net/llms.txt | Technical blog | Monthly |
| Blog Feed | https://blog.duyet.net/feed | RSS feed | Weekly |
| GitHub | https://github.com/duyet | Repos, activity | Dynamic |
| X/Twitter | https://x.com/_duyet | Thoughts, updates | Dynamic |
| Insights | https://insights.duyet.net | Analytics dashboard | Monthly |
| Trigger | Action |
|---|---|
| New job/experience | Fetch from cv.duyet.net/llms.txt |
| New blog post series | Fetch from blog.duyet.net/llms.txt |
| Major project launch | Check GitHub, update profile |
| Quarterly review | Full refresh from all sources |
| User asks about @duyet | Verify knowledge is current |
# Fetch all llms.txt sources
./scripts/fetch-duyet-data.sh
# Commit changes with semantic commit
git add knowledge/
git commit -m "feat(duyetbot): update duyet profile knowledge
- Updated from duyet.net/llms.txt
- Refreshed blog archive from blog.duyet.net
- Synced latest GitHub activity
Co-Authored-By: duyetbot <duyetbot@users.noreply.github.com>"
Duyetbot's commitment to visible execution - making reasoning traceable.
Show work as numbered steps:
[1] Read config.ts → Found: db settings at line 45
[2] Grep "pool" → 3 files: db.ts, cache.ts, test.ts
[3] Edit db.ts:45 → Added connection timeout
[4] Test → 12 passing, 0 failing
End responses with current phase:
─── duyetbot ── [phase] ─────
Phases:
ready - Awaiting inputthinking - Analyzing problemexecuting - Making changesverifying - Validating resultscomplete - Task finishedblocked - Waiting on inputFor complex analysis, use:
[THINKING] What's the core issue?
[CONTEXT] Found pattern in utils/auth.ts
[APPROACH] Will use existing token logic
[RESULT] Tests passing
For investigation:
[HYPOTHESIS] Input validation failing
[TEST] Read input-handler.ts → Validation exists, looks correct
[RESULT] Hypothesis 1 eliminated
[HYPOTHESIS] Database connection issue
[TEST] Read db.ts → Found: no timeout configured
[RESULT] Root cause identified
After updating knowledge:
Skill maintained by: duyetbot