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 binggandata/bggg-skills --skill sif-keyword-scoutgit clone --depth 1 https://github.com/binggandata/bggg-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/binggandata/bggg-skills/sif-keyword-scout)<a href="https://agentmods.dev/skills/binggandata/bggg-skills/sif-keyword-scout"><img src="https://agentmods.dev/badge/skills/binggandata/bggg-skills/sif-keyword-scout/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/binggandata/bggg-skills/sif-keyword-scout"><img src="https://agentmods.dev/badge/skills/binggandata/bggg-skills/sif-keyword-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00173 | $0.05068 |
| Opus 5 | $0.00086 | $0.02534 |
| Sonnet 5 | $0.00035 | $0.01014 |
| Haiku 4.5 | $0.00017 | $0.00507 |
Grade A, and why
sif-keyword-scout 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 — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sif 关键词情报侦察（Skill 1）
Agent 角色
执行本 skill 时，同时阅读并遵循 references/amazon-expert-guide.md：
- 以亚马逊关键词/PPC 顾问身份解读结果，参数异常时主动引导用户
- 不是只跑脚本；S/A 门槛、类目描述、SS/SSS 数量异常时要说明原因并建议修正
人机协同原则（强制）
禁止「静默跑完全程」。本 skill 是顾问 + 自动化，不是批处理脚本。
| 规则 | 说明 |
|---|---|
| 跑前必聊 | 在 ingest_raw 或任何 --mode process 之前，必须与用户确认 ASIN、阶段、类目、数据来源 |
| 三处卡点 | 见下方「强制暂停点」——未获用户明确确认前，不得进入下一步 |
| 确认方式 | 用户回复「可以 / 继续 / 用自动值 / 按你说的」等明确许可；沉默或只给 ASIN 不算确认 |
| 异常先停 | sanity check 触发时，先解释原因并给出选项，等用户选后再重跑或继续 |
强制暂停点（三处）
| # | 时机 | Agent 做什么 | 用户确认什么 |
|---|---|---|---|
| ① | 表1 compute-thresholds 之后、process 之前 |
展示 S/A 门槛、竞价/集中度中位数；结合阶段 + 类目说明是否偏高/偏低 | 维持自动值，或指定 --s-threshold / --a-threshold |
| ② | 三表 + 交叉 --skip-word 完成后、写 insights_cross 之前 |
解读 SSS/SS/S 数量、表3 缺口/离群词；列出建议主攻 SS 清单与应排除词 | 确认主攻方向与是否重跑表3（改类目/--sv-threshold） |
| ③ | Skill 2 compare_versions --skip-word 完成后、写 insights_tracker 之前 |
解读新增/消失/份额变化；给出试投/暂停/调价建议 | 确认是否按建议调整投放，或仅存档观察 |
话术与解读细则 → references/amazon-expert-guide.md 各节。
依赖
| 依赖 | 说明 |
|---|---|
| Python | pip install pandas openpyxl matplotlib python-docx numpy |
| web-access | 仅方式 B 需要；第三方 eze-is/web-access（作者一泽 Eze，MIT）；路径见 references/path-setup.md |
最终产物：处理结果目录仅保留 Excel（
.xlsx）+ Word（.docx）。 图表由脚本生成 PNG 后内嵌进 Word，不保留charts/目录。 Agent 写的insights_*.md是中间稿（供 Word 渲染 AI 分析段），生成 Word 后自动删除。
三种输入方式（Agent 自动判断）
| 方式 | 用户怎么说 | Agent 做什么 |
|---|---|---|
| C 直接给路径（最快） | 发来 3 个 xlsx 路径，或一个下载文件夹 | ingest_raw.py 识别表类型 → 复制到标准目录 → 跑处理 |
| A 手动导出 | 「我自己下好了」或放到指定目录 | 发 manual-export-guide.md，或 ingest_raw --from-dir |
| B 浏览器导出 | 「你帮我下」 | web-access + browser-export-sop.md |
用户直接给文件路径时：不必再问下载方式，先 resolve_workspace → 跑前简报（Step 1）获确认 → 调 ingest_raw → 从 Step 5 继续。
What ships with it
24 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.
- README.md 1.1 KB
- references/amazon-expert-guide.md 8.7 KB
- references/browser-export-sop.md 3.2 KB
- references/first-time-setup.md 4.0 KB
- references/manual-export-guide.md 2.8 KB
- references/path-setup.md 3.8 KB
- references/sop-tables.md 3.8 KB
- references/table-schema.md 4.7 KB
- references/threshold-presets.md 3.7 KB
- scripts/.gitignore 25 B
- scripts/batch_regenerate_word.py 16 KB runs code
- scripts/check_history.py 9.9 KB runs code
- scripts/create_mock_sif_exports.py 4.6 KB runs code
- scripts/cross_analysis.py 33 KB runs code
- scripts/ingest_raw.py 7.5 KB runs code
- scripts/process_table1.py 37 KB runs code
- scripts/process_table2.py 22 KB runs code
- scripts/process_table3.py 30 KB runs code
- scripts/report_utils.py 24 KB runs code
- scripts/resolve_workspace.py 6.3 KB runs code
- scripts/run_context.py 4.0 KB runs code
- scripts/stdio_utf8.py 989 B runs code
- scripts/threshold_presets.py 4.9 KB runs code
- scripts/update_history.py 7.2 KB runs code
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 · 368 lines · 173 tokens per session scan A 0e4be6785d17
sif-keyword-scout is a skill published in the GitHub repository binggandata/bggg-skills (594 stars, last pushed 1mo ago), licensed MIT. It adds 173 tokens to every session and 5,068 once invoked, about $0.0009 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
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…
amazon-price-tracker
Amazon price monitoring and competitive pricing intelligence. Real-time price tracking, Buy Box analysis, promotion detection, and dynamic pricing strategy optimization. Use when the user asks about price monitoring, competitor pricing, Buy Box tracking, or pricing strategy.