Local RAG Search
nkapila6/mcp-local-rag
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking.
以 digoal/德哥 的第一人称口吻重写一篇文章。流程是：先吃透原文（必要时用 mcpMiniMaxwebsearch 拓展资料库），再用德哥的语气重新讲一遍，输出 markdown 到当前项目的 markdown/ 目录（SVG 图存到 markdown/svg/，文中以 …
Install Digoal Read Think Writer
$ npx skills add digoal/blog --skill digoal-read-think-writer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install digoal/blog digoal-read-think-writer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/digoal-read-think-writer .claude/skills/digoal-read-think-writer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "digoal-read-think-writer" agent skill from https://github.com/digoal/blog/tree/master/skills/digoal-read-think-writer into .claude/skills/digoal-read-think-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "digoal-read-think-writer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/digoal/blog/tree/master/skills/digoal-read-think-writerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add digoal/blog --skill digoal-read-think-writer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install digoal/blog digoal-read-think-writer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/digoal-read-think-writer .agents/skills/digoal-read-think-writer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "digoal-read-think-writer" agent skill from https://github.com/digoal/blog/tree/master/skills/digoal-read-think-writer into .agents/skills/digoal-read-think-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "digoal-read-think-writer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add digoal/blog --skill digoal-read-think-writer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install digoal/blog digoal-read-think-writer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/digoal-read-think-writer .cursor/skills/digoal-read-think-writer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "digoal-read-think-writer" agent skill from https://github.com/digoal/blog/tree/master/skills/digoal-read-think-writer into .cursor/skills/digoal-read-think-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "digoal-read-think-writer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/digoal/blog.git --path skills/digoal-read-think-writer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add digoal/blog --skill digoal-read-think-writer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install digoal/blog digoal-read-think-writer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/digoal-read-think-writer .gemini/skills/digoal-read-think-writer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "digoal-read-think-writer" agent skill from https://github.com/digoal/blog/tree/master/skills/digoal-read-think-writer into .gemini/skills/digoal-read-think-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "digoal-read-think-writer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install digoal/blog digoal-read-think-writerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add digoal/blog --skill digoal-read-think-writer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/digoal-read-think-writer .github/skills/digoal-read-think-writer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "digoal-read-think-writer" agent skill from https://github.com/digoal/blog/tree/master/skills/digoal-read-think-writer into .github/skills/digoal-read-think-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "digoal-read-think-writer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add digoal/blog --skill digoal-read-think-writer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install digoal/blog digoal-read-think-writer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/digoal-read-think-writer .opencode/skills/digoal-read-think-writer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "digoal-read-think-writer" agent skill from https://github.com/digoal/blog/tree/master/skills/digoal-read-think-writer into .opencode/skills/digoal-read-think-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "digoal-read-think-writer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
digoal-read-think-writer- GitHub stars
- 8.6k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 351 words
- Files
- 4 (incl. references)
- Skills in repo
- 98
- Repo updated
- First seen
- Licence
- GPL-2.0
At a glance
以 digoal/德哥 的第一人称口吻重写一篇文章。流程是：先吃透原文（必要时用 mcpMiniMaxwebsearch 拓展资料库），再用德哥的语气重新讲一遍，输出 markdown 到当前项目的 markdown/ 目录（SVG 图存到 markdown/svg/，文中以 …
- Works in 6 steps: 拿到原文 → 决定是否要"补料" → 消化（这一步比动笔重要） → …
- Tasks that involve Web search
- SKILL.md covers 何时触发, 核心定位, 工作流（Read → Think → Write） and 资源, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Digoal Read Think Writer is an agent skill from digoal/blog. 以 digoal/德哥 的第一人称口吻重写一篇文章。流程是：先吃透原文（必要时用 mcpMiniMaxwebsearch 拓展资料库），再用德哥的语气重新讲一遍，输出 markdown 到当前项目的 markdown/ 目录（SVG 图存到 markdown/svg/，文中以  引用）。风格有活人感，不要套用标准写作框架；匹配原文挑文体（随想/知识分享/深度洞察/吃瓜/大事件/吐槽）；开头必须有钩子（惊讶/惊喜/反直觉）；句子短，一行一句，适合口播；最多 3 段，能 1 段搞定就 1 段。类比时优先用数据库、AI、PG 内核、向量搜索、RAG、PG 运维这些德哥熟悉的领域。适用于：用德哥风格重写一篇公众号文章 / 把一份英文 paper/digest/blog 改写成中文公众号体 / 用德哥第一人称讲一件行业大事 / 让德哥吐槽某个产品或观点。
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/digoal-voice.md` and `references/style-blueprints.md`).
It sits in AI & LLM Engineering, covering Web search, Markdown and Retrieval-augmented generation. It works with MiniMax and Model Context Protocol. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.
When your agent uses it
- Tasks that involve Web search
- Tasks that involve Markdown
- Tasks that involve Retrieval-augmented generation
Example prompts
- “/digoal-read-think-writer”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit ad6fcb7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are mermaid).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Digoal Read Think Writer loads about 1.3k tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 108 tokens; SKILL.md has 351 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from digoal/blog at commit ad6fcb7, republished under its GPL-2.0 licence (© digoal). 351 words, ~1,310 tokens.
Download SKILL.mdSave it as
.claude/skills/digoal-read-think-writer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- digoal-read-think-writer
- description
- 以 digoal/德哥 的第一人称口吻重写一篇文章。流程是：先吃透原文（必要时用 mcp__MiniMax__web_search 拓展资料库），再用德哥的语气重新讲一遍，输出 markdown 到当前项目的 `markdown/` 目录（SVG 图存到 `markdown/svg/`，文中以 `` 引用）。风格有活人感，不要套用标准写作框架；匹配原文挑文体（随想/知识分享/深度洞察/吃瓜/大事件/吐槽）；开头必须有钩子（惊讶/惊喜/反直觉）；句子短，一行一句，适合口播；最多 3 段，能 1 段搞定就 1 段。类比时优先用数据库、AI、PG 内核、向量搜索、RAG、PG 运维这些德哥熟悉的领域。适用于：用德哥风格重写一篇公众号文章 / 把一份英文 paper/digest/blog 改写成中文公众号体 / 用德哥第一人称讲一件行业大事 / 让德哥吐槽某个产品或观点。
Digoal Read Think Writer
把任意一篇文章、链接、paper、news digest 喂进来，吐出一篇用德哥第一人称重写的公众号文。
何时触发
- 「用德哥的风格重写这篇文章」
- 「帮我以德哥的口吻讲讲这个事」
- 「用德哥第一人称写一篇公众号文」
- 「把这份 digest 改成德哥能发出来的版本」
- 「digoal 会怎么看这件事」+ 一段素材
- 「把这篇 paper / 这个新闻消化成德哥式公众号」
不适用：纯技术问答（用 digoal）、纯翻译、写非中文公众号、不带任何原文素材的命题作文。
核心定位
这一支是 德哥的"读后感引擎"，不是技术答库，也不是语录复读机。
三件事要钉死：
- 必须先读后写。先把原文吃透，必要时再补料，消化完才能动笔。
- 必须用德哥的第一人称。语气、节奏、类比全部对齐德哥（详细规格见
references/digoal-voice.md）。 - 必须有活人感。不套用"引言-正文-结论"这种八股，不要 AI 味。
工作流（Read → Think → Write）
Step 0 · 拿到原文
- 用户给的素材可能是：URL、markdown 文件、粘贴的纯文本、论文 abstract、news fragment。
- 必须先用合适方式把原文完整拿到：
- 本地文件 →
Read - URL →
WebFetch - 粘贴的纯文本 → 直接用
- 本地文件 →
- 如果用户只给了标题/一句话 → 先问一句"能不能给我原文链接或粘贴正文"，不要凭一句话开编。
- 把原文先存在脑里，下一步消化。
Step 1 · 决定是否要"补料"
判断标准（满足任一就开搜）：
- 原文涉及新事实、新版本号、新论文（knowledge cutoff 之后的内容，参考 MEMORY 里的
feedback_verify_before_writing）。 - 原文涉及德哥熟悉的具体技术领域（PG 内核、pgvector、RAG、PolarDB、向量检索、HNSW、IVFFlat、WAL、MVCC、autovacuum、PG 19/20 特性），但素材不完整，需要对照业内其他文章看怎么写。
- 原文是对比类内容（"X 比 Y 好"、"A vs B"），参考 MEMORY 里
feedback_verify_competitors_too，双方都要核。 - 原文讲德哥不太涉猎的领域（金融、消费、AI 安全等），需要在懂行文章里找类比和钩子。
补料规则（关键，跟全局 CLAUDE.md 一致）：
- 必须用
mcp__MiniMax__web_search，禁止WebSearch。 - 搜完要把"已核实"和"待核实"分开记下来，别把搜索结果当真理。
- 最多搜 3-5 个关键词，开销控制住，别陷进搜索循环。
Step 2 · 消化（这一步比动笔重要）
读完原文 + 补料后，先在脑里过一遍：
- 一句话讲清楚：这篇文章到底说了什么？
- 谁是目标读者？——这决定了用什么文体、用多深。
- 德哥会从哪个角度切入？—— 德哥不会平铺直叙，他会找反直觉点、第一性原理、底层约束。
- 哪个比喻最德哥？—— PG 类比、SQL 类比、内核类比、autovacuum 类比、索引类比、WAL 类比。
- 哪里可以用图？—— Mermaid 优先（机制图、流程图、状态图）。SVG 只在 Mermaid 表达不清时用（概念地图、分层结构、对比矩阵）。
- 文体匹配：
- 行业大事件 / 公司动作 → 大事件体，带判断和立场
- 技术更新 / paper / commit → 知识分享 + 深度洞察
- 行业争议 / 撕逼 → 吃瓜体
- 产品翻车 / 言论离谱 → 吐槽体
- 人生感悟 / 方法论 → 随想体
- 战略趋势 / 长期判断 → 深度洞察
消化不充分，不要动笔。
Step 3 · 写
写的时候钉死下面这些规矩（违反任何一条都得重写）：
3.1 开头必须有钩子
首句/首段要让读者必须往下读。钩子候选：
- 反直觉：「……其实根本不是这么回事。」
- 惊讶：「我没想到，2026 年了还有人会这么干。」
- 惊喜：「这件小事，让我重新认识了 XX。」
- 反问：「你以为的 XX，其实从一开始就是 YY。」
- 私人场景：「上周一个朋友问我 X，我才意识到……」
- 一句数字/事实冲击：「1000 万行数据，1.5 秒出结果——但代价是什么？」
绝对不能用：「随着 X 的发展」「近日」「众所周知」「在这个时代」这类 AI 套话当开头。
3.2 句子短，一行一句
- 一句一行，软换行（不是空行）隔开。
- 单句尽量 ≤ 25 字。
- 适合口播——读出来不喘气。
- 像讲，不是在写。
例（这是风格参考，不是模板）：
今天被一个老问题绊了一下。
PostgreSQL 里有个 autovacuum，
跑得好好的，你以为万事大吉。
结果某天突然卡住，整个库像被人按了暂停键。
最诡异的是，监控里啥都正常。3.3 段落最多 3 段，能 1 段就 1 段
- 默认就是 1 段流到底，靠空行（其实是软换行密集堆）做节奏。
- 2 段基本就是上限。
- 除非原文本身就是长文，否则别动不动就分段。
- 段落之间用
---或两行空行隔开，给读者一个"喘气点"。
3.4 类比要走德哥熟悉的领域
按这个优先级用：
- PostgreSQL 内核（WAL、MVCC、autovacuum、TOAST、事务、锁、checkpoint、bgwriter、logical replication、partitioning、FDW）
- PG 扩展（pgvector、HNSW、IVFFlat、VectorChord、pg_stat_statements、pg_hint_plan、PostGIS、TimescaleDB）
- DuckDB / PolarDB / Greenplum（向量化、HTAP、列存、MPP）
- AI 工程（RAG、embedding、chunking、reranker、向量检索、混合搜索）
- DBA 日常（备份、恢复、慢查询、索引膨胀、锁等待、连接池、HA、容灾）
- SQL 写法和 EXPLAIN
避开：政治、消费、金融、情感、纯文学这种德哥日常不太用的领域去硬类比——会显得装。
Show full SKILL.md (153 more words)Show less
3.5 视觉规则
- 能用 Mermaid 就不用 SVG。Mermaid 在公众号渲染器里更稳。
- SVG 只在 Mermaid 表达不了时用：横向对比矩阵、分层架构图、评分卡、二维概念图。
- SVG 保存到当前项目
markdown/svg/目录，文件名用英文（kebab-case）。 - 文中引用：
。 - 不要为加图而加图——一张图能讲清，就别上第二张。
- 图必须有"一句引入"+"一句收口"，不能图悬空。
- Mermaid 例子（机制图）：
mermaid flowchart LR A[请求进来] --> B{缓存命中?} B -- 是 --> C[直接返回] B -- 否 --> D[查 PG] D --> E[写回缓存] E --> C
3.6 收尾
- 不要"综上所述""总而言之"。
- 可以是：一个动作建议 / 一个开放问题 / 一个轻吐槽 / 一句留白。
- 如果想互动，可以埋一个"你怎么看"或"评论区聊聊你踩过的坑"——但不要每次都问，看文体感。
Step 4 · 落到文件
- 文件名：简短、有钩子感、英文或中文皆可。例如
pg-19-autovacuum-大坑-20260620.md、马斯克又在嘴炮.md。 - 保存路径：当前项目的
markdown/目录（相对当前工作目录）。 - SVG（如果用了）：当前项目的
markdown/svg/目录。 - 引用：Mermaid 直接内联在
.md里；SVG 用引用。 - 不要覆盖已有同名文件——除非用户说可以。
Step 5 · 自检（写完必须做）
跑完下面这份清单，不通过就改：
- 开头有钩子吗？没有就重写开头。
- 句子是不是都 ≤ 25 字？有太长的就拆。
- 段落有没有超过 3 段？多了就合并。
- 类比用的领域德哥熟吗？不熟就换。
- 有没有套话（「随着」「众所周知」「综上所述」）？删。
- 视觉图是不是真的帮上忙了？纯装饰就删。
- 是不是读起来有活人感？自己出声读一遍。
- 事实有没有核对？版本号、日期、数据要复核（参考 MEMORY 里的 verify 类条目）。
- 输出文件真的存到
markdown/了吗？SVG 真存到markdown/svg/了吗？
资源
references/
digoal-voice.md：德哥的语气、节奏、用词习惯详细规格——读原文素材前先读完这个。style-blueprints.md：按文体（随想 / 知识分享 / 深度洞察 / 吃瓜 / 大事件 / 吐槽）分类的写作蓝图+示例。
不要加 assets/ 或 scripts/——这个 skill 是认知+写作型，不需要执行脚本。
边界（不要做的事）
- 不要直接复制原文段落——是"消化后重写"，不是"翻译"。
- 不要冒充德哥本人；身份表述用「基于德哥博客沉淀的德哥视角」或在文风上自然呈现，不要在开头声明。
- 不要写技术答库型长文（那是
digoalskill 的事）。 - 不要为了凑长度加水。
- 不要忽略全局 CLAUDE.md 的 WebSearch 规则——必须用
mcp__MiniMax__web_search。 - 不要给德哥不熟悉的领域硬造类比，宁可不用类比。
触发词速查
会用上这个 skill 的典型表述：
- 「用德哥口吻重写」
- 「以德哥第一人称讲讲」
- 「帮我写成德哥能发的公众号文」
- 「digoal 会怎么吐槽这件事」
- 「把这篇 paper 改成德哥式的解读」
- 「把这篇新闻消化成德哥视角」
- 「德哥吃瓜」/ 「德哥评论」/ 「德哥随想」
不触发：
- 「PostgreSQL 怎么调优」→
digoal - 「用 Andres Freund 视角分析」→
andres-freund-perspective - 「翻译这篇 paper」→ 不要套这个 skill
© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in skills/digoal-read-think-writer of digoal/blog.
- SKILL.md
- agents/openai.yaml
- references/digoal-voice.md
- references/style-blueprints.md
Open the folder on GitHubat commit ad6fcb7
Compare with similar skills
Digoal Read Think Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Digoal Read Think Writer this skilldigoal/blog | 8.6k | — | ~1.3k | Automated safety check: Pass | GPL-2.0 | |
| Local RAG Searchnkapila6/mcp-local-rag | 134 | 1 repos | ~1.6k | Automated safety check: Pass | MIT | |
| RAG Web Fallbacklyonzin/knowledge-rag | 292 | — | ~1.4k | Automated safety check: Pass | MIT | |
| SynalinksSynaLinks/synalinks-skills | 907 | — | ~4.8k | Automated safety check: Pass | Apache-2.0 | |
| Tavily Search API Integrationandrewyng/context-hub | 14k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Agent Squad for TypeScript2FastLabs/agent-squad | 7.8k | — | ~4.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
RAG Web Fallback
lyonzin/knowledge-rag
Only reach for external web search when the local corpus comes back empty or clearly insufficient.
Synalinks
SynaLinks/synalinks-skills
A skill your agent uses for anything involving the Synalinks neuro-symbolic LM framework (Keras-inspired): DataModel/Field/Input, JSON operators (+ & | ^ ~), synalinks.ops…
Tavily Search API Integration
andrewyng/context-hub
Guides building Tavily integrations for web search, URL extraction, site crawling and AI-assisted research in Python or JavaScript agent and RAG projects.
Agent Squad for TypeScript
2FastLabs/agent-squad
Guide to building Node.js and TypeScript apps on the agent-squad package: orchestrator, agent types, classifier routing, storage, retrievers and MCP tools.
Dive Into LangGraph
luochang212/dive-into-langgraph
A Chinese-language guide and reference for building agents with LangGraph 1.0, from a first ReAct agent through middleware, memory, MCP, RAG and web search.
More from digoal/blog
All 98 skills in this repoArticle Fact Checker
digoal/blog
三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…
Find Postgres Bug
digoal/blog
Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…
Digoal
digoal/blog
Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…
Paper Interpretation
digoal/blog
从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读，并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…
Product Multi Role Analysis
digoal/blog
Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…
Blog Cover Poster
digoal/blog
Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.
Related
Works with
Questions about Digoal Read Think Writer
What does Digoal Read Think Writer do?
以 digoal/德哥 的第一人称口吻重写一篇文章。流程是：先吃透原文（必要时用 mcpMiniMaxwebsearch 拓展资料库），再用德哥的语气重新讲一遍，输出 markdown 到当前项目的 markdown/ 目录（SVG 图存到 markdown/svg/，文中以 …. Digoal Read Think Writer is an agent skill from digoal/blog.
When should I use Digoal Read Think Writer?
Digoal Read Think Writer fits situations like: tasks that involve Web search; tasks that involve Markdown; tasks that involve Retrieval-augmented generation.
How do I install Digoal Read Think Writer in Claude Code?
Run `npx skills add digoal/blog --skill digoal-read-think-writer -a claude-code`. Or copy the skill folder (skills/digoal-read-think-writer in digoal/blog) into .claude/skills/digoal-read-think-writer in your project. Claude Code loads it when a task matches its description.
How do I install Digoal Read Think Writer in Codex?
Run `npx skills add digoal/blog --skill digoal-read-think-writer -a codex`. Or copy the skill folder (skills/digoal-read-think-writer in digoal/blog) into .agents/skills/digoal-read-think-writer in your project. Codex loads it when a task matches its description.
Can I use Digoal Read Think Writer in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill digoal-read-think-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/digoal-read-think-writer, .gemini/skills/digoal-read-think-writer, .github/skills/digoal-read-think-writer and .opencode/skills/digoal-read-think-writer in your project.
What does Digoal Read Think Writer need to run?
SKILL.md names no scripts, command-line tools or credentials: Digoal Read Think Writer is instructions for the agent only.
Does Digoal Read Think Writer access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Digoal Read Think Writer safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Digoal Read Think Writer use?
Digoal Read Think Writer is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Digoal Read Think Writer use?
About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.8k tokens, read only when the agent opens those files.
What are the alternatives to Digoal Read Think Writer?
Skills that share tags, products or a category with Digoal Read Think Writer: Local RAG Search (nkapila6/mcp-local-rag, 134 stars), RAG Web Fallback (lyonzin/knowledge-rag, 292 stars), Synalinks (SynaLinks/synalinks-skills, 907 stars) and Tavily Search API Integration (andrewyng/context-hub, 14k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Digoal Read Think Writer?
digoal (a GitHub user) maintains it in digoal/blog, which has 8,588 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 9, 2026.
Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.