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 songoao25/dsh-virtual-product-team --skill 06-promotiongit clone --depth 1 https://github.com/songoao25/dsh-virtual-product-teamWrote 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/songoao25/dsh-virtual-product-team/06-promotion)<a href="https://agentmods.dev/skills/songoao25/dsh-virtual-product-team/06-promotion"><img src="https://agentmods.dev/badge/skills/songoao25/dsh-virtual-product-team/06-promotion/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/songoao25/dsh-virtual-product-team/06-promotion"><img src="https://agentmods.dev/badge/skills/songoao25/dsh-virtual-product-team/06-promotion.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 | $0.00059 | $0.01118 |
| Opus 5 | $0.00030 | $0.00559 |
| Sonnet 5 | $0.00012 | $0.00224 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
promotion 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 11d 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.
What it actually says
阶段 6:宣传与冷启动(⑩宣传)
角色
你是主 Agent + 运营顾问。本阶段只问不做:默认不生成任何宣传物料;是否制作、制作什么,完全由用户明确决定。
核心规则(铁律)
- 先问后做:进入本阶段的第一步只能是询问用户(ask_user_question 出选择题),严禁在询问用户之前制作任何宣传物料。
- 明确答复才做:只有用户明确选择要做(并指明做哪些类型)时,才制作对应类型;用户明确不做、没有回答、或没有明确回答(含"随便""你看着办"等含糊答复)时 → 直接跳过本阶段,不产出任何物料、不再追问。
- 仓库红线:宣传物料是私有资料,只能放
.product-team/;严禁进入 GitHub 仓库——不 git add、不 commit、不 push、不进 tag/Release,也不得复制进任何要发布到仓库的文件。
步骤
- 询问用户(唯一入口):用 ask_user_question 出选择题——
- 问题:"产品已经发布上线了。要不要做宣传资料?要做哪些?"
- 选项(多选):
- 不做宣传资料(跳过本环节)
- 一句话安装/使用提示词(复制给任意 AI 助手就能用)
- 短视频脚本(开头钩子 + 演示 + 行动号召)
- 文章/帖子模板(问题 → 方案 → 演示 → 安装 → 行动号召)
- 渠道清单 + SEO 关键词
- 按答复分支:
- 用户明确选择了某项物料 → 只做选中的那几类:派运营子 Agent 起草(提示词模板:"你是运营/文案。任务:为 <产品名> 写 <物料类型>。产品一句话:<一句话>。目标用户:<非技术个人开发者>。语气:通俗、有吸引力。"),汇总成
.product-team/PROMO.md(私有)。 - 用户没做明确选择(没回答 / 说"不做" / 含糊答复)→ 不产出任何物料,直接跳过。
- 用户明确选择了某项物料 → 只做选中的那几类:派运营子 Agent 起草(提示词模板:"你是运营/文案。任务:为 <产品名> 写 <物料类型>。产品一句话:<一句话>。目标用户:<非技术个人开发者>。语气:通俗、有吸引力。"),汇总成
- 物料交付(仅当用户明确要求时):只交付私有物料供用户自己使用;宣传材料不属于产品发布内容,不得提交到 GitHub。绝不自动发帖、投稿、上传视频或联系第三方——任何对外动作都要用户在渠道、账号和最终文案层面单独确认。
模板(仅用户明确要求制作时使用)
# 宣传材料:<产品名>
## 一句话部署提示词(给用户复制给任意 AI 助手)
> 帮我安装 <GitHub 链接> 这个项目,装完告诉我怎么用。
## 短视频脚本骨架
- 开头(3 秒钩子):<一句话痛点>
- 演示:<从"我有个想法"到交付的剪辑点>
- 结尾:<行动号召:复制这句话给你的 AI>
## 文章结构
- 问题 → 方案 → 演示 → 对比(vs 普通模式)→ 安装 → 行动号召
## 渠道清单
- <抖音 / B 站 / 小红书 / 知乎 / GitHub>
## SEO 关键词
- <3-5 个搜索词>
Gate 6 汇报
- 制作了物料 → 汇报"宣传材料就绪(列明做了哪几类),都在私有文件夹里,不会进 GitHub 仓库"。
- 跳过 → 汇报"宣传环节已跳过(未要求制作宣传资料);如需要随时可以说,我们再补"。
- 两种情况都汇总本阶段结果,请求用户确认后进入阶段 7。
验收标准(Gate 6)
- 进入本阶段后第一步是询问用户;询问之前未制作任何物料
- 只有用户明确选择的物料类型才被制作;未明确答复 → 未产出任何物料并直接跳过
- 任何产出的物料都在
.product-team/,未进入 GitHub 仓库 - 无任何自动对外发布动作(发帖/投稿/上传)
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.
- 11d ago First seen · 62 lines · 59 tokens per session scan A d6452dda635c
promotion is a skill published in the GitHub repository songoao25/dsh-virtual-product-team (5 stars, last pushed 7d ago), licensed MIT. It adds 59 tokens to every session and 1,118 once invoked, about $0.0003 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
discretelog
Use when users ask about solving the discrete logarithm problem g^x ≡ y (mod P) with Shor-style two-register Fourier sampling, building/explaining DLP circuits, running simulator demos, or debugging post-processing (continued fractions plus two-dimensional Fourier-sample congruence solving). Triggers: discrete log…
aqc
Explains and demonstrates UnitaryLab's small-scale adiabatic quantum linear-system solver. Use it for AQC or QLSP questions, simulator examples, and work involving Householder state preparation, SVD block encoding, adiabatic schedules, post-selection, solution rescaling, or residual checks.
hhl
HHL quantum linear-system solver for Hermitian A and power-of-two dimension N. This implementation accepts user-provided A and b, auto-computes the evolution time t, uses QPE with U = exp(i2πAt), and reconstructs an approximate classical solution from post-selection in a statevector simulation; exponential speedup…
amplitude-estimation
A quantum algorithm for estimating the amplitude of a specific state in a quantum superposition, which can be used for various applications such as Monte Carlo simulations and optimization problems. Provides efficient implementations and educational resources for understanding and utilizing amplitude estimation in…
mps
Loads states with a Matrix Product State representation when low-entanglement structure can reduce the preparation cost. It covers state-to-MPS decomposition, bond-dimension truncation, canonicalization, QR-based unitary completion, work-qubit encoding, leakage, and phase-invariant validation in UnitaryLab.
superposition
Prepares a normalized state with sparse computational-basis support using compact coefficient preparation followed by a support permutation. The current implementation is exact up to floating-point error but materializes dense matrices.