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 skills add aaronartistzhang-afk/DailyWork --skill audience-briefgit clone --depth 1 https://github.com/aaronartistzhang-afk/DailyWorkWrote 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/aaronartistzhang-afk/dailywork/audience-brief)<a href="https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/audience-brief"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/audience-brief/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/aaronartistzhang-afk/dailywork/audience-brief"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/audience-brief.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 | $0.00157 | $0.02271 |
| Opus 5 | $0.00078 | $0.01136 |
| Sonnet 5 | $0.00031 | $0.00454 |
| Haiku 4.5 | $0.00016 | $0.00227 |
Grade A, and why
audience-brief 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 12d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audience-brief — 受众分层话术打包器
把当前上下文里的发现 / 改动 / 状态 / 计划,按目标受众打包成一段可直接复制粘贴进飞书的消息。纯编排、零基建:不拉数、不落盘、不发送——只出稿、停在预览、等用户自己发。
这个 skill 解决的是一个反复出现的返工:给 RD 要英语、给运营要中文人话、给老板要短,证据要带版本号和路径——这些偏好过去每条消息都要用户第二轮补纠(「用英语」单独作为一条纠正消息出现过 ~6 次)。这里把档位固化,力争零补纠。
什么时候用
- 用户已经在当前会话里拿到了要传达的内容(一个发现、一次修复、一个版本状态、一个计划),只是要「包装成一段话发出去」。
- 触发词:「整理一段话我发给研发」「给运营的人话版」「发老板」「我发研发用」「share 给运营」「发飞书群」。
- 不适用:需要先做分析/归因/审计才有内容的场景(先去做那件事);需要真正发送到某个群/某个人(本 skill 只出稿到预览,发送由用户手动完成 or 另走发送通道 skill);妙记会议纪要总结(走 meeting-notes)。
核心流程(5 步)
1. 识别受众
从触发语和上下文判定目标受众,落到四档之一:RD / 运营 / 老板 / local team。
- 明确说了「研发 / RD / eng / 研发用」→ RD 档。
- 说了「运营 / ops」→ 运营档。
- 说了「老板 / leadership / 汇报 / 上级」→ 老板档。
- 说了「local team / 本地团队 / 区域 review」→ local team 档(本质是 RD 档的事实陈述式 + 保留字段名,但语气面向非工程受众,默认英文或双语,视 local team 语言而定)。
- 含混时只问一句(不要连环追问):例如「这条是发给研发(英文、带版本号/路径)还是运营(中文人话)?」,拿到答案立即出稿。
2. 按档位出稿
三档模板见下方「档位规格」。每档的语言 / 语气 / 长度 / 证据密度都是硬约束。
3. 运营 / 老板档强制 humanizer 收尾
运营档和老板档出稿后,必须调用 humanizer skill(v2.8.0)过一遍再交给用户——去掉 AI 腔(rule-of-three、em dash 滥用、空洞 -ing 分析、promotional 词、negative parallelism 等)。
- RD 档不过 humanizer:RD 档要的是事实陈述式的英文,humanizer 反而可能软化掉技术精确性。
- humanizer 有度:过一遍是为了「像人写的」,不是为了「口语化到丢字段名」。见下方 guardrail「有点人话过度了」——涉及 eval 里明确声明的字段名,直接引用原文,不要意译、不要拆成大白话。
4. 支持变体
用户常在同一条消息上要变体,主动支持、也在预览里提示可切换:
- 5 行版:压到 5 行以内(老板档默认即此)。
- 一段话版:不分点,一整段(发飞书群/私聊常用)。
- 中英双语单发:中英各一段,用于单发私聊场景(一条消息里中英都给到)。
5. 输出即贴 + send-gate 停在预览
- 输出即贴:交付的正文无 markdown 残留——不要
**加粗**、不要#标题、不要 ``` 代码围栏、不要 markdown 列表符号(飞书粘贴进去会变成裸星号/井号)。要分点就用中文顿号编号或纯换行。证据里的路径 / 版本号 / trace_id 直接写明文。 - send-gate:出稿后停在预览,明确说「这是预览,确认后你自己复制发出 / 告诉我要调哪里」。绝不代发、不调发送通道。这是与用户「停在最后一步我来提交」纪律一致的硬闸门。
档位规格
RD 档(研发 / eng)
- 语言:英文。(这是最高频的补纠点——见 guardrail「用英语,然后我是发飞书消息」,过去 ~6 次都是第二轮才补。本档默认直接英文,不要先出中文再等纠。)
- 长度:2–4 句。精炼。
- 语气:事实陈述式 = 「我发现的问题 + 建议」,不是技术细节堆砌、不是长篇报告。(配套纠正原话:「不用带这么多技术细节,更多是描述我发现的问题和建议」。)
- 证据(必带):版本号、trace_id、文件路径 / 文件名。缺任何一个就是不合格——见 guardrail「给我具体的文件路径,文件名,版本号」。若上下文里拿不到某个证据字段,先问用户或去查,不要糊过去。
- humanizer:不过。
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.
- 12d ago First seen · 100 lines · 157 tokens per session scan A 0db88d6ad87d
audience-brief is a skill published in the GitHub repository aaronartistzhang-afk/DailyWork (1 stars, last pushed 14d ago), licensed MIT. It adds 157 tokens to every session and 2,271 once invoked, about $0.0008 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
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
ab-test-generator
Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improve click-through rate", "test my landing page copy", "headline alternatives", "CTA variations", "which version is better", "optimize conversions"…
authoring-ci-workflows
Use when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under .github/ — new CI jobs, triggers, matrices, checkout/clone tuning, action pinning, GitHub App token auth, concurrency groups, timeout-minutes, paths filters, caching, or runner choice. Covers PostHog's workflow-authoring…
debugging-mcp-analytics
Debug, support, and build PostHog MCP Analytics — product analytics for MCP servers (the @posthog/mcp and posthog.mcp SDKs plus the mcpanalytics product). Use when MCP analytics data looks wrong or missing ("events aren't showing", "intent clusters are empty", "sessions are missing", "per-tool numbers look wrong")…
debugging-ci-failures
Debugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches, and answers broad CI-health questions ("is CI red?", "is master green today?", "what's broken right now?"). Use when the user asks why CI is red, asks for the current CI or master status, or mentions a failing check, GitHub Actions run…
monitoring-capture-service
Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production. Use when investigating latency, event loss, Kafka backpressure, Redis issues, rate limiting, Envoy proxy issues, or any capture health question. Covers prod-us and prod-eu environments.