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 ilexlyu/ad-proposal-skills --skill ad-research-collectorgit clone --depth 1 https://github.com/ilexlyu/ad-proposal-skillsWrote 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/ilexlyu/ad-proposal-skills/ad-research-collector)<a href="https://agentmods.dev/skills/ilexlyu/ad-proposal-skills/ad-research-collector"><img src="https://agentmods.dev/badge/skills/ilexlyu/ad-proposal-skills/ad-research-collector/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/ilexlyu/ad-proposal-skills/ad-research-collector"><img src="https://agentmods.dev/badge/skills/ilexlyu/ad-proposal-skills/ad-research-collector.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 | $0.00082 | $0.00662 |
| Opus 5.5 | $0.00033 | $0.00265 |
| Sonnet 5.5 | $0.00016 | $0.00132 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
ad-research-collector 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 1mo 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
行业资料搜集
目标：把“搜资料”变成可追溯的决策证据库。所有结论都要带来源、年份、原始链接/核查链接、可信度和可用方式，避免资料堆砌或不可核查的 AI 总结。
Before Searching
读取 references/source-matrix.md，按行业和平台选择资料源。需要联网时必须优先查官方或权威页面，再查媒体转载。
Search Order
- 官方/权威来源：品牌、平台、政府/协会、上市公司财报。
- 一线机构报告：艾瑞、CBNData、QuestMobile、易观、Mob 研究院、秒针等。
- 平台通案和营销报告：巨量引擎、小红书、天猫、京东、抖音电商。
- 聚合与媒体解读：199IT、新榜、数英案例、行业媒体。
Workflow
- 确定研究问题：行业规模、用户变化、竞品、渠道生态、内容趋势、购买动机。
- 为每个问题生成 3-5 个检索词：行业词、平台词、人群词、场景词、年份。
- 搜索并记录来源；优先保留原始报告页、官方页面或 PDF 链接。找不到原始链接时，标注为二级来源，不要假装是原始报告。
- 对每条资料标注可信度：高/中/低。
- 输出资料表，并指出适合放在 PPT 哪一页或支持哪个判断。
Output Format
| 主题 | 来源 | 原始链接/核查链接 | 年份 | 数据点/案例 | 原文摘要 | 可用结论 | 可信度 | 局限 | 适合放在哪一页 |
|---|
Quality Bar
- 不得输出“行业增长很快”“年轻人喜欢情绪价值”这类无证据空话。
- 每个关键趋势至少配 1 个数据、案例或来源链接。
- 每条资料必须有可点击的原始链接/核查链接；若只有媒体转载或报告聚合页，可信度不能标为高，并要写清“二级来源”。
- 过期报告必须标注年份和局限；跨行业套用必须说明不确定性。
- 若找不到权威来源，明确说“当前只能作为假设”，不要伪装成事实。
What ships with it
2 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.
- 1mo ago First seen · 41 lines · 82 tokens per session scan A ed7dbf4073db
ad-research-collector is a skill published in the GitHub repository ilexlyu/ad-proposal-skills (14 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 662 once invoked, about $0.0003 per session on Opus 5.5. 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
creative-brief
Grade, pressure-test, and write creative and campaign briefs against a real strategic standard (IIOB: Idea, Insight, Objective, Benefit). Use this whenever someone shares a brief, creative brief, campaign brief, content brief, or marketing brief and wants feedback, a score, a critique, or help making it stronger…
voice
A brand-voice analysis skill that studies a user's past posts and replies to describe how they think and write. Brand voice means the recurring tone, wording, rhythm, humor, and boundaries in someone's writing.
creative-generate
A workflow for creating advertising images and banners from a strategy brief. It separates the main visual artwork from the accurately typeset text and produces variants for display or social formats.
tracking-health
Preventive audit of conversion tracking across all configured ad platforms — Meta pixels + CAPI, Google Ads conversion actions, and final-URL tracking-parameter consistency on every platform — with a GA4 cross-check. Use when the user asks to check tracking, audit conversion measurement, verify pixels / tags, check…
setup
Initialize AK-Threads-Booster: import historical posts, normalize them into the tracker schema, auto-generate a personalized style guide, and build a concept library. Run on first use or whenever the user wants to backfill account history.
learn
Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all platforms. Use when the user runs /learn, explicitly teaches the agent a marketing insight, corrects the agent's analysis, or asks to remember/record an operational learning for next time. Also use…