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-skill-evolver/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-skill-evolver)<a href="https://agentmods.dev/skills/ptonlix/beeweave/beeweave-writing-skill-evolver"><img src="https://agentmods.dev/badge/skills/ptonlix/beeweave/beeweave-writing-skill-evolver.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.01750 |
| Opus 5 | $0.00056 | $0.00875 |
| Sonnet 5 | $0.00022 | $0.00350 |
| Haiku 4.5 | $0.00011 | $0.00175 |
Grade A, and why
beeweave-writing-skill-evolver 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 8d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BeeWeave 写作 Skill 进化器
这个 skill 的职责是把候选学习结果变成可验证、可回滚、可维护的写作系统变更。它不负责普通写作生成,也不负责创建基础写作 trace。
任务边界
本 skill 只处理写作风格系统的演进:
- pending 规则审阅。
- pending → active。
- pending → rejected。
- active 规则整理和 compaction。
- writer
SKILL.md或 source references 的受控 patch 建议。 - evolution log 记录和回滚说明。
不处理:
- 普通文章写作,交给
beeweave-article-writer或beeweave-social-writer。 - 首次风格初始化,交给
beeweave-writing-style-initializer。 - 文章发布、published 文件移动、wiki ingest、发布 trace 元数据,交给
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。
必读资产
执行前读取:
$BEEWEAVE_WORKBENCH_PATH/writing/style/
├── active_style_rules.md
├── anti_patterns.md
├── pending_rules.md
├── rejected_rules.md
└── evolution_log.md
如果需要验证,还读取:
$BEEWEAVE_WORKBENCH_PATH/writing/eval/
├── article_cases/
├── social_cases/
└── rubric.md
如果 writing/style/ 或关键风格文件缺失,不要在 evolver 中初始化模板。先提示用户使用 beeweave-writing-style-initializer 完成初始化。evolver 只处理已经存在的 pending、active、rejected、evolution log 和 compaction 工作。
三层分类
每条候选必须先分类,再决定写入位置:
- 路由层,修改
name、description或触发边界。用于解决 skill 该不该触发的问题。 - 指令层,修改
SKILL.md主流程、质量检查或稳定规则。用于解决通用流程和判断标准问题。 - 资源层,修改 Workbench 风格资产、examples、references 或 eval case。用于承载用户特定风格、示例、细分场景和证据。
每次进化都必须回答:
- 改了哪一层。
- 解决什么问题。
- 用什么证据证明它更好。
- 如何回滚。
激活流程
- 从
pending_rules.md读取候选。 - 检查
active_style_rules.md和rejected_rules.md,避免重复激活或反复提出已拒绝规则。 - 分类为 route、instruction 或 resource。
- 检查证据是否足够,至少包含 trace、历史文章、用户反馈、发布采纳或 before/after diff。
- 如果
writing/eval/有相关 case,用 case 和rubric.md做验证;如果没有相关 case,明确说明验证缺口。 - 根据目标类型选择执行方式:
- 只改 Workbench style assets:准备 active/rejected/examples/eval 的具体条目。
- 改 writer
SKILL.md:准备目标文件、章节、变更理由和最小 patch 摘要。 - 改 source references:准备目标 reference、使用场景和回滚方式。
- 输出 review summary,包含规则、scope、证据、目标文件或章节、验证结果、风险、回滚方式和准备写入的内容。
- 只有通过验证或用户明确批准后,才能修改 active 规则、rejected 规则、writer
SKILL.md或 source references。 - 修改后记录
evolution_log.md,并在pending_rules.md中标记该候选已处理或移动到对应状态。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 153 lines · 111 tokens per session scan A 764c243a8272
beeweave-writing-skill-evolver is a skill published in the GitHub repository ptonlix/beeweave (6 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 1,750 once invoked, about $0.0006 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…