Back to Details

blog-flow

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

FLOW Framework for Bloggers (Find, Optimize, Win)

FLOW Framework for Bloggers (Find, Optimize, Win)

Framework and prompts (c) Daniel Agrici, CC BY 4.0. Source: github.com/AgriciDaniel/flow
FLOW is an evidence-led operating model built for the AI-search era. Claude Blog integrates the FLOW prompt library so writers can drive their workflow with structured, source-backed AI prompts instead of improvised queries.
This skill exposes the three blog-relevant stages (Find, Optimize, Win) and keeps the single Leverage prompt available through the prompts index. The local-SEO prompts (GBP, citations, local audits) are intentionally excluded because they target brick-and-mortar work, not blogs.
Runtime context. Load 
references/flow-framework.md
on every 
/blog flow
activation. Load prompt files on demand only, scoped to the stage the user requests.
Framework and prompts (c) Daniel Agrici, CC BY 4.0. Source: github.com/AgriciDaniel/flow
FLOW是为AI搜索时代打造的基于证据的运营模型。Claude Blog集成了FLOW提示词库，让创作者可以借助结构化、有来源支持的AI提示词来推进工作流，而非使用即兴查询。
本技能开放了三个与博客相关的阶段（Find、Optimize、Win），并保留了单个Leverage提示词可通过提示词索引访问。本地SEO提示词（GBP、引用、本地审计）被有意排除，因为它们针对的是实体业务而非博客。
运行时上下文。每次激活
/blog flow
时加载
references/flow-framework.md
。仅根据用户请求的阶段按需加载提示词文件。

Commands

命令

CommandWhat it does
/blog flow
Show FLOW overview and stage menu
/blog flow find [topic|url]
Find-stage: keyword discovery, intent mapping, gap analysis (5 prompts)
/blog flow optimize [url]
Optimize-stage: select 2 to 3 most relevant prompts of 21 based on context
/blog flow win [url]
Win-stage: BOFU, conversion, dual-surface scorecard (3 prompts)
/blog flow prompts
Full index of all 30 blog-applicable prompts (Find, Leverage, Optimize, Win)
/blog flow sync
Pull latest prompt files from github.com/AgriciDaniel/flow
The single Leverage prompt (off-site authority) is reachable through 
/blog flow prompts
and is not promoted to a top-level command, since most blog workflows route off-site work elsewhere.
命令功能
/blog flow
显示FLOW概述及阶段菜单
/blog flow find [topic|url]
Find阶段：关键词挖掘、意图映射、差距分析（5个提示词）
/blog flow optimize [url]
Optimize阶段：根据上下文从21个提示词中选择2-3个最相关的
/blog flow win [url]
Win阶段：BOFU、转化、双界面评分卡（3个提示词）
/blog flow prompts
所有30个适用于博客的提示词完整索引（Find、Leverage、Optimize、Win）
/blog flow sync
从github.com/AgriciDaniel/flow拉取最新提示词文件
单个Leverage提示词（站外权威）可通过
/blog flow prompts
访问，未设为顶级命令，因为大多数博客工作流会将站外工作交由其他工具处理。

Orchestration Logic

编排逻辑

On 
/blog flow
(no sub-command)

执行
/blog flow
（无子命令）

  1. Read 
    references/flow-framework.md
    .
  2. Show the FLOW stage overview with a one-line description of each stage.
  3. Ask the user which stage matches their current situation.
  1. 读取
    references/flow-framework.md
    。
  2. 展示FLOW阶段概述，每个阶段配一行描述。
  3. 询问用户当前情况匹配哪个阶段。

On 
/blog flow find [topic|url]

执行
/blog flow find [topic|url]

  1. Read all files in 
    references/prompts/find/
    .
  2. Apply each prompt to the topic or URL, capturing demand and intent signals.
  3. Cross-reference: "For deeper briefs and outlines, see 
    /blog brief <topic>
    , 
    /blog outline <topic>
    , and 
    /blog cannibalization
    to detect overlap with existing posts."
  1. 读取
    references/prompts/find/
    下的所有文件。
  2. 将每个提示词应用于主题或URL，捕捉需求和意图信号。
  3. 交叉引用：“如需更详细的简报和大纲，请查看
    /blog brief <topic>
    、
    /blog outline <topic>
    ，以及
    /blog cannibalization
    以检测与现有文章的重叠。”

On 
/blog flow optimize [url]

执行
/blog flow optimize [url]

  1. Read the file names in 
    references/prompts/optimize/
    .
  2. Read prior context (target URL, niche, any prior skill output in this conversation, scoring deltas from 
    /blog analyze
    ).
  3. Select 2 to 3 most relevant prompts, then load only those files.
  4. Apply the selected prompts; note that the rest are accessible via 
    /blog flow prompts
    .
  5. Cross-reference: "For deeper rewrites and validation, see 
    /blog rewrite <file>
    , 
    /blog seo-check <file>
    , 
    /blog geo <file>
    , 
    /blog schema <file>
    , and 
    /blog factcheck <file>
    ."
  1. 读取
    references/prompts/optimize/
    下的文件名。
  2. 读取历史上下文（目标URL、细分领域、本次对话中之前的技能输出、
    /blog analyze
    的评分差异）。
  3. 选择2-3个最相关的提示词，仅加载这些文件。
  4. 应用所选提示词；说明其余提示词可通过
    /blog flow prompts
    访问。
  5. 交叉引用：“如需深度重写和验证，请查看
    /blog rewrite <file>
    、
    /blog seo-check <file>
    、
    /blog geo <file>
    、
    /blog schema <file>
    以及
    /blog factcheck <file>
    。”

On 
/blog flow win [url]

执行
/blog flow win [url]

  1. Read all files in 
    references/prompts/win/
    .
  2. Apply each prompt to the URL's conversion and BOFU context.
  3. Cross-reference: "For repurposing, full-site health, and quality scoring, see 
    /blog repurpose <file>
    , 
    /blog audit
    , and 
    /blog analyze <file>
    ."
  1. 读取
    references/prompts/win/
    下的所有文件。
  2. 将每个提示词应用于URL的转化和BOFU上下文。
  3. 交叉引用：“如需内容复用、全站健康检查和质量评分，请查看
    /blog repurpose <file>
    、
    /blog audit
    以及
    /blog analyze <file>
    。”

On 
/blog flow prompts

执行
/blog flow prompts

  1. Read 
    references/prompts/README.md
    .
  2. Display the full index: 30 prompts grouped by stage (Find, Leverage, Optimize, Win) with name and trigger conditions.
  3. State that local-SEO prompts are excluded by design; point users to 
    claude-seo
    (
    /seo flow local
    ) if they need them.
  1. 读取
    references/prompts/README.md
    。
  2. 展示完整索引：30个提示词按阶段（Find、Leverage、Optimize、Win）分组，包含名称和触发条件。
  3. 说明本地SEO提示词已被有意排除；如果用户需要，可指向
    claude-seo
    （
    /seo flow local
    ）。

On 
/blog flow sync

执行
/blog flow sync

  1. Run: 
    python3 scripts/sync_flow.py
    .
  2. Display the JSON summary (files added, updated, unchanged).
  3. Show the attribution notice after the sync completes.
  1. 运行：
    python3 scripts/sync_flow.py
    。
  2. 展示JSON摘要（新增、更新、未变更的文件）。
  3. 同步完成后显示归属声明。

Context Matching (Optimize stage)

上下文匹配（Optimize阶段）

The optimize stage has 21 prompts. Dumping all 21 is noise. Select by priority:
  1. Niche (SaaS or B2B blog leans on-page plus technical; lifestyle leans freshness plus E-E-A-T; publisher leans authority plus citations).
  2. Prior skill output (
    /blog analyze
    E-E-A-T gap routes to authority prompts; 
    /blog seo-check
    failures route to on-page prompts; 
    /blog geo
    gaps route to extraction-format prompts).
  3. URL signals (commercial pages need conversion prompts; informational posts need freshness plus answer-first prompts).
Always surface exactly 2 to 3 prompts. State which prompts you chose and why.
Optimize阶段有21个提示词。全部输出会产生冗余信息，需按优先级选择：
  1. 细分领域（SaaS或B2B博客倾向于页面优化加技术优化；生活方式博客倾向于内容新鲜度加E-E-A-T；出版商博客倾向于权威性加引用）。
  2. 历史技能输出（
    /blog analyze
    检测到的E-E-A-T差距会导向权威性提示词；
    /blog seo-check
    的失败项会导向页面优化提示词；
    /blog geo
    的差距会导向提取格式提示词）。
  3. URL信号（商业页面需要转化提示词；信息类文章需要新鲜度加优先解答提示词）。
始终只展示2-3个提示词，并说明选择这些提示词的原因。

Reference Files

参考文件

Load on demand. Do NOT load all at startup.
  • references/flow-framework.md
    . FLOW operating model. Load on every 
    /blog flow
    activation.
  • references/bibliography.md
    . Evidence sources. Load when citing studies or statistics.
  • references/prompts/README.md
    . Prompt index. Load for 
    /blog flow prompts
    .
  • references/prompts/find/
    . 5 prompts. Load for 
    /blog flow find
    .
  • references/prompts/leverage/
    . 1 prompt. Load only when surfaced through 
    /blog flow prompts
    .
  • references/prompts/optimize/
    . 21 prompts. Load selectively for 
    /blog flow optimize
    .
  • references/prompts/win/
    . 3 prompts. Load for 
    /blog flow win
    .
If 
references/
is missing, instruct the user to run 
/blog flow sync
first.
按需加载。请勿在启动时全部加载。
  • references/flow-framework.md
    ：FLOW运营模型。每次激活
    /blog flow
    时加载。
  • references/bibliography.md
    ：证据来源。引用研究或统计数据时加载。
  • references/prompts/README.md
    ：提示词索引。执行
    /blog flow prompts
    时加载。
  • references/prompts/find/
    ：5个提示词。执行
    /blog flow find
    时加载。
  • references/prompts/leverage/
    ：1个提示词。仅当通过
    /blog flow prompts
    展示时加载。
  • references/prompts/optimize/
    ：21个提示词。执行
    /blog flow optimize
    时选择性加载。
  • references/prompts/win/
    ：3个提示词。执行
    /blog flow win
    时加载。
如果
references/
目录缺失，请指导用户先执行
/blog flow sync
。

Sync Script

同步脚本

scripts/sync_flow.py
pulls prompt files from github.com/AgriciDaniel/flow and writes them under 
skills/blog-flow/references/
. Stdlib only, HTTPS only, host-allowlisted to 
api.github.com
, 5 MB response cap, atomic writes, path-traversal guarded.
Modes:
  • python3 scripts/sync_flow.py
    . Sync the latest version of every blog-relevant stage to disk and refresh the lockfile.
  • python3 scripts/sync_flow.py --dry-run
    . Report planned changes without writing.
  • python3 scripts/sync_flow.py --ref <sha>
    . Pin fetches to a specific FLOW commit SHA for reproducible installs.
The lockfile lives at 
skills/blog-flow/references/flow-prompts.lock
and uses sha256sum-compatible format. Drift between the on-disk content and the lockfile is reported on every sync run.
The script syncs only blog-applicable stages (
find
, 
leverage
, 
optimize
, 
win
). The 
local
stage is intentionally skipped to keep the references directory aligned with the skill's surface area.
GitHub API calls are anonymous by default. If 
GITHUB_TOKEN
is set in the environment, or 
gh auth token
returns a token after a 403 response, the script retries the request with that token. No tokens are written to disk.
scripts/sync_flow.py
从github.com/AgriciDaniel/flow拉取提示词文件，并写入
skills/blog-flow/references/
目录。仅使用标准库，仅通过HTTPS通信，主机白名单为
api.github.com
，响应上限5MB，原子写入，防止路径遍历。
模式：
  • python3 scripts/sync_flow.py
    ：将所有与博客相关阶段的最新版本同步到磁盘，并刷新锁定文件。
  • python3 scripts/sync_flow.py --dry-run
    ：报告计划的变更但不写入磁盘。
  • python3 scripts/sync_flow.py --ref <sha>
    ：将拉取内容固定到特定的FLOW提交SHA，实现可复现的安装。
锁定文件位于
skills/blog-flow/references/flow-prompts.lock
，使用与sha256sum兼容的格式。每次同步运行都会报告磁盘内容与锁定文件之间的差异。
脚本仅同步适用于博客的阶段（
find
、
leverage
、
optimize
、
win
）。
local
阶段被有意跳过，以保持参考目录与技能的覆盖范围一致。
GitHub API调用默认是匿名的。如果环境中设置了
GITHUB_TOKEN
，或在403响应后
gh auth token
返回了令牌，脚本会使用该令牌重试请求。令牌不会写入磁盘。

Attribution

归属声明

Every 
/blog flow
activation (any sub-command) outputs before analysis:
Framework and prompts (c) Daniel Agrici, CC BY 4.0. Source: github.com/AgriciDaniel/flow
Do not omit or modify the attribution. Synced files also carry an HTML comment license header injected by the sync script.
每次激活
/blog flow
（任何子命令）时，在分析前输出：
Framework and prompts (c) Daniel Agrici, CC BY 4.0. Source: github.com/AgriciDaniel/flow
请勿省略或修改归属声明。同步文件还包含由同步脚本注入的HTML注释许可证头。

Error Handling

错误处理

ScenarioAction
references/flow-framework.md
missing		"FLOW reference files not synced. Run: 
/blog flow sync
."
Prompt file missing"Run 
/blog flow sync
to pull the latest prompts from the FLOW repo."
sync_flow.py
network error		Display the script's stderr. Check rate limits with 
gh api rate_limit
if 
gh
is installed.
sync_flow.py
403 after retry		Set 
GITHUB_TOKEN
or run 
gh auth login
, then retry.
Path-traversal abortThe sync target tried to escape the references directory. Inspect the upstream repo and pin to a known-good 
--ref
.
场景操作
references/flow-framework.md
缺失		"FLOW参考文件未同步。请执行：
/blog flow sync
。"
提示词文件缺失"请执行
/blog flow sync
从FLOW仓库拉取最新提示词。"
sync_flow.py
网络错误		显示脚本的stderr输出。如果安装了
gh
，请用
gh api rate_limit
检查速率限制。
sync_flow.py
重试后仍403		设置
GITHUB_TOKEN
或执行
gh auth login
，然后重试。
路径遍历中止同步目标试图逃离参考目录。检查上游仓库并固定到已知可信的
--ref
。