Borrowing it
Nothing to install: this file belongs to ptonlix/beeweave. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ptonlix/beeweave/main/.skills/workbench/beeweave-writing-style-learner/SKILL.mdgit clone --depth 1 https://github.com/ptonlix/beeweaveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ptonlix/beeweave/beeweave-writing-style-learner)<a href="https://agentmods.dev/skills/ptonlix/beeweave/beeweave-writing-style-learner"><img src="https://agentmods.dev/badge/skills/ptonlix/beeweave/beeweave-writing-style-learner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ptonlix/beeweave/beeweave-writing-style-learner"><img src="https://agentmods.dev/badge/skills/ptonlix/beeweave/beeweave-writing-style-learner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00105 | $0.01712 |
| Opus 5 | $0.00053 | $0.00856 |
| Sonnet 5 | $0.00021 | $0.00342 |
| Haiku 4.5 | $0.00011 | $0.00171 |
Grade A, and why
beeweave-writing-style-learner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BeeWeave 写作风格学习器
这个 skill 只做学习和复盘。它把真实写作材料转化为可审阅的候选风格资产。
它不负责:
- 初始化
writing/style/模板。 - 创建 8 个固定风格资产文件。
- 普通写作生成。
- 修改 writer
SKILL.md。 - 激活或拒绝规则。
- 发布文章或触发 wiki ingest。
这些任务分别交给 beeweave-writing-style-initializer、writer、beeweave-writing-skill-evolver 和 beeweave-article-publisher。
工作区定位
如果用户请求里包含 @<name>,只从 ~/.beeweave/config.<name> 读取 BEEWEAVE_WORKBENCH_PATH。否则只从 ~/.beeweave/config 读取 BEEWEAVE_WORKBENCH_PATH。
如果配置文件不存在、没有配置 BEEWEAVE_WORKBENCH_PATH,或 Workbench 无法访问,先向用户说明无法找到 BeeWeave workbench,不要猜测其它路径。
初始化完整性检查
每次学习前必须检查 writing/style/ 是否已经初始化。
必须存在:
$BEEWEAVE_WORKBENCH_PATH/writing/style/
├── author_profile.md
├── active_style_rules.md
├── anti_patterns.md
├── article_examples.md
├── social_examples.md
├── pending_rules.md
├── rejected_rules.md
└── evolution_log.md
如果缺少任一文件,停止学习,不要自己创建模板文件,不要生成 author-writing-style.md、writing-style.md 或其它汇总文件。最终回复必须列出缺失文件,并提示先运行 beeweave-writing-style-initializer。
如果存在 author-writing-style.md、writing-style.md、style-summary.md 等 legacy 文件,但 8 个固定文件不完整,仍然视为未初始化。只有在 8 个固定文件完整后,才可以把 legacy 文件作为普通输入材料读取,并把有价值内容迁移为 pending、examples 或作者画像摘要。
输入类型
可学习输入包括:
- 历史文章、博客、公众号稿、发布稿。
- 社交短内容、thread、朋友圈短文。
writing/traces/下的 trace bundle。- AI 初稿和用户改稿的 before/after。
- 用户明确反馈,例如“这个开头太宏大”“别写得像报告”“我喜欢这种结尾”。
- 用户指令驱动的 AI 改稿,例如“把开头改成真实经历切入”。
- legacy 风格汇总文件,例如旧的
author-writing-style.md。
输入分支
- 用户提供 trace 目录:读取
trace.json和trace.md,再按revision_events判断学习信号。 - 用户提供 before/after 两个文件:对比改动方向,提炼用户偏好的结构、语气、删改习惯和反模式。
- 用户只提供改后稿:把它作为正向样本,但标记证据不足;优先写 examples 或 pending。
- 用户只给一句反馈:把反馈转成候选规则或反模式候选,confidence 通常为 low 或 medium。
- 用户提供历史文章目录:读取其中明确存在的 Markdown/text 文件,区分 article、social 和不确定材料;输出默认进入 pending 或 examples。
- 用户提供 legacy 汇总文件:只把它当作参考材料,迁移摘要到固定文件,不继续写入 legacy 文件。
学习前检查
初始化完整后,读取:
active_style_rules.md,避免重复提出已经生效的规则。anti_patterns.md,理解已有禁忌。rejected_rules.md,避免重复提出已拒绝规则。- 相关 trace 的
trace.json和trace.md,如果用户提供了 trace。
学习流程
- 明确学习范围,区分
article、social、all、methodology。 - 收集证据,优先使用用户终稿、发布稿、手动改稿、明确反馈和被采纳版本。
- 对比 before/after,提炼改动方向,而不是机械记录每个句子差异。
- 把一次性表达抽象成稳定候选规则。
- 给每条候选标注 scope、suggested_layer、confidence、evidence 和 validation。
- 默认写入
pending_rules.md。 - 在用户明确要求时,可补充
author_profile.md、article_examples.md、social_examples.md或anti_patterns.md的证据化条目。 - 可把候选规则编号或学习摘要回写到相关 trace 的学习区,但不要替代 writer 创建基础 trace。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 143 lines · 105 tokens per session scan A 548082b3d2d0
beeweave-writing-style-learner is a skill published in the GitHub repository ptonlix/beeweave (6 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,712 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…