Skip to content
cccskills
FreePublished on GitHub

launchfast-full-research-loop

End-to-end Codex-native Amazon FBA research workflow using LaunchFast MCP. Use when the user wants a single report covering product research, IP risk, supplier sourcing, and PPC keyword intelligence. Requires `research_products`, `ip_check_manage`, `supplier_research`, and `amazon_keyword_research`.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md2.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

LaunchFast Full Research Loop

Inputs

If needed, ask once for:

  • keyword or keyword list
  • target selling price
  • first order quantity
  • optional competitor ASINs
  • optional report path

Default report path:

./artifacts/launchfast/reports/launchfast-report-[keyword]-[YYYY-MM-DD].html

Workflow

1. Product research

  • Run research_products for each keyword with focus="balanced" and product_limit=20.
  • Score each keyword using the same logic as launchfast-product-research.
  • Pick winners for deeper analysis.

2. IP check

For promising keywords, run:

ip_check_manage(action="ip_conflict_check", keyword="<keyword>")
ip_check_manage(action="trademark_search", keyword="<keyword>")

Extract:

  • conflict level
  • notable active marks
  • patent concerns if present
  • final risk posture: CLEAR, CAUTION, or BLOCKED

3. Supplier research

For the strongest keyword, run:

supplier_research(keyword="<keyword>", goldSupplierOnly=true, tradeAssuranceOnly=true, maxResults=10)

Summarize the top suppliers with:

  • company name
  • quality score
  • price band
  • MOQ
  • years in business
  • trust signals

4. PPC research

If you have competitor ASINs, or can responsibly infer 2-3 strong ASINs from product research, run:

amazon_keyword_research(asins=[...], limit=20)

Summarize:

  • keyword count
  • top search-volume terms
  • high-intent terms by purchase rate
  • indicative CPCs
  • suggested campaign structure

If there are no usable ASINs, state that this phase was skipped.

5. Build the report

Create a standalone HTML report with:

  • executive verdict banner
  • market scorecard
  • product findings
  • IP findings
  • supplier findings
  • PPC findings
  • concise recommendation section

Design should match the existing LaunchFast visual language:

  • clean light theme
  • neutral palette
  • card layout
  • compact tables
  • clear GO / INVESTIGATE / PASS styling

Write the file to the requested path and report the final file location.

Output

Always return:

  • overall verdict
  • key blockers or strengths
  • report path if the file was written

Do not pad the response with generic “next steps” unless the evidence clearly supports a specific recommendation.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Use AtomLane to compile and execute safe atomic parallel plans on macOS and native Windows Preview for worthwhile independent argv tasks, dependency DAGs, supported platform entrypoints, or Apple-silicon operators. Use at task start or an execution boundary when structured local work may contain two or more worthwhile units; skip plain answers, one quick command, and work whose effects cannot be safely bounded.

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.3KUpdated Oct 18, 2026

add

Free

Register a deferred decision in the debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you defer work, or when the user invokes $add. Over-register freely; the developer drops with "drop A", "drop A,C", or "drop all".

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.3KUpdated Oct 18, 2026

ADK 框架适配层。为 LangChain / EINO / AutoGen / AgentScope / CrewAI 提供框架特定的 代码模板、惯用模式、API 映射和项目结构,供 agent-dev-workshop Phase 5 代码生成使用。 每个框架 reference 文件标注 verified_date 用于版本锁定。

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.3KUpdated Oct 18, 2026

中文调试修复技能。用于报错、测试失败、页面异常、功能不符合预期、需要定位根因并做最小修复时。触发语包括"进入调试模式""帮我修问题""报错了""测试失败""页面坏了""找根因"。

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.3KUpdated Oct 18, 2026

交互式 AI Agent 开发工作坊:通过 6 阶段深度协作对话,引导用户完成 Agent 需求分析、架构设计、 工具定义、Prompt 与编排设计、代码生成、验证迭代,产出可直接运行的 Agent 项目。 框架无关设计优先,支持 LangChain / EINO / AutoGen / AgentScope / CrewAI 等 ADK 框架。

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.3KUpdated Oct 18, 2026

中文漂移审计技能。用于项目或学习过程变乱、上下文漂移、任务分叉、多个方案冲突、命名不一致、Codex 可能顺手改多了时。触发语包括"漂移检查""感觉跑偏了""项目变乱了""检查是否失控""分叉太多""上下文漂移"。

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.3KUpdated Oct 18, 2026

See all skills by hashgraph-online

Report a problem with this skill