Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/zju-real/easel/skill-algorithm-updatesnpx skills add ZJU-REAL/Easel --skill skill-algorithm-updatesgit clone --depth 1 https://github.com/ZJU-REAL/EaselWhat 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 | $0.00101 | $0.01400 |
| Opus 5 | $0.00051 | $0.00700 |
| Sonnet 5 | $0.00020 | $0.00280 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
skill-algorithm-updates 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 3d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
平台算法动态追踪
聚合中文社媒平台的算法更新、推荐机制变化与流量规则调整，输出结构化简报。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| platforms | 否 | 目标平台列表（默认全部 6 个：抖音/小红书/B站/微博/知乎/视频号） |
| time_range | 否 | 时间范围："近一周" / "近一月" / "近三月"（默认"近一月"） |
| focus | 否 | 关注方向："流量分发" / "内容审核" / "变现规则" / "全部"（默认"全部"） |
输出
# 平台算法动态简报
更新日期: {date}
覆盖平台: {platforms}
时间范围: {time_range}
关注方向: {focus}
## {平台名}
### 近期变化
- **{变化标题}**: {具体说明}（来源: {source}，时间: {date}）
- ...
### 对创作者的影响
- {影响说明}
### 应对建议
- {可操作的建议}
（每个目标平台各一节，结构相同）
## 跨平台趋势
- {多个平台共同出现的规则变化方向}
## 信息来源
- [{来源标题}]({URL})
- ...
执行步骤
第一步：确定范围
- 解析输入参数，确定目标平台列表、时间范围和关注方向
- 有 Profile 时读取
profiles/<画像>/platforms.md，优先覆盖创作者活跃平台 - 无 Profile 时覆盖全部 6 个平台
第二步：多维度搜索 — 平台官方与创作者社区
对每个目标平台，执行 2-3 组 web_search 查询：
"{平台名} 算法 更新 {当前年}""{平台名} 推荐机制 变化 创作者""{平台名} 流量 规则 最新"
若 focus 非"全部"，追加定向查询：
- 流量分发：
"{平台名} 流量池 分发 调整" - 内容审核：
"{平台名} 内容审核 规则 变化" - 变现规则：
"{平台名} 变现 政策 更新"
读取 references/platform-sources.md 获取各平台官方来源 URL 和搜索模板。
第三步：第三方信息源搜索
补充行业视角，执行以下查询：
"社媒平台 算法 变化 {当前年}"限定 newrank.cn / woshipm.com / 36kr.com"{平台名} 创作者 吐槽 算法"— 捕捉社区讨论中的实际感知"中国社交媒体 推荐算法 趋势"— 获取跨平台综合分析
第四步：抓取与提取
对第二步和第三步中相关度最高的 3-5 个结果（每平台），执行 web_fetch：
- 提取具体的算法变化描述、生效时间、官方声明原文
- 读取
references/algorithm-vocabulary.md辅助理解平台专有术语 - 区分信息来源层级：
- 官方确认：平台官方公告、创作者中心通知
- 行业报道：新榜、36kr 等媒体报道
- 社区感知：创作者社区讨论、个人观察（标注为未经证实）
第五步：合成简报
将提取的信息按平台聚合为结构化简报：
- 逐平台整理：按时间倒序列出每个变化，附来源 URL 和日期
- 影响分析：每条变化对创作者的具体影响（流量、内容策略、变现）
- 应对建议：针对每条变化给出可操作的调整建议
- 跨平台趋势：识别多个平台共同出现的规则变化方向（如"短视频平台集体提升完播率权重"）
- 信息来源汇总：列出所有引用的 URL
第六步：输出
将简报保存到 outputs/ 目录。
规则
- 每条声明必须附来源 URL — 无来源的信息不纳入简报
- 区分确认与传闻 — 官方公告标注"已确认"，社区讨论标注"未经证实/社区反馈"
- 标注时间 — 每条变化注明发生时间；6 个月以前的变化归入"背景信息"而非"近期变化"
- 不预测未来 — 只报告已发生的变化，不推测平台接下来会怎么调整
- 如实报告空结果 — 某平台未发现近期变化时明确写"未发现近期算法变化"，不编造
Profile 感知
有 Profile 时：
- 读取
profiles/<画像>/platforms.md确定创作者活跃平台，优先覆盖这些平台 - 影响分析结合创作者的内容类型（如"你主做知识科普，完播率权重提升对你有利"）
- 应对建议针对创作者的具体情况定制
- 非活跃平台仅提供摘要级信息
What ships with it
3 files 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.
- 3d ago First seen · 133 lines · 101 tokens per session scan A 5bca22eb33be
skill-algorithm-updates is a skill published in the GitHub repository ZJU-REAL/Easel (56 stars, last pushed 3d ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,400 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…