hashgraph-online/awesome-codex-plugins / plugins/BlockchainHB/launchfast_codex_plugin/skills/launchfast-ppc-research
launchfast-ppc-research
VerifiedCodex-native Amazon PPC keyword research using LaunchFast MCP. Use when the user wants competitor keyword discovery, keyword tiering, or a ready-to-upload Amazon Sponsored Products bulk file from 1-15 ASINs. Requires the LaunchFast MCP tool `amazon_keyword_research`.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.1 KB |
SKILL.md
View on GitHub---
name: launchfast-ppc-research
description: |
Codex-native Amazon PPC keyword research using LaunchFast MCP. Use when the
user wants competitor keyword discovery, keyword tiering, or a ready-to-upload
Amazon Sponsored Products bulk file from 1-15 ASINs.
Requires the LaunchFast MCP tool `amazon_keyword_research`.
argument-hint: "[ASIN1] [ASIN2] [ASIN3]"
---
# LaunchFast PPC Research
## Inputs
If needed, ask once for:
- 1-15 ASINs
- optional campaign name
- optional default CPC bid
- optional daily budget
- optional output path
Defaults:
- campaign name: `LaunchFast-PPC-[YYYY-MM-DD]`
- default bid: `0.75`
- daily budget: `25`
- output path: `./artifacts/launchfast/ppc/launchfast-ppc-[YYYY-MM-DD].tsv`
## Workflow
### 1. Run keyword research
Run one keyword-research call across all ASINs when possible:
```text
amazon_keyword_research(asins=[...], limit=50)
```
If the ASIN set is too large or results are unwieldy, batch them, but do not require delegation.
### 2. Normalize and tier keywords
For each keyword:
- deduplicate across ASIN overlaps
- keep overlap count
- capture search volume, CPC, purchase rate, relevance, and ranking coverage
Tiering:
- Tier 1: high-value terms with strong overlap or standout volume and conversion
- Tier 2: mid-volume growth terms
- Tier 3: discovery and long-tail terms
Match mapping:
- Exact: Tier 1
- Phrase: Tier 1 and Tier 2
- Broad: Tier 2 and Tier 3
Bid guidance:
- Exact: default bid * 1.2
- Phrase: default bid * 1.0
- Broad: default bid * 0.7
### 3. Present a preview
Show:
- ASINs analyzed
- unique keywords found
- tier breakdown
- top 15 keywords preview
- negative keywords or exclusions if obvious
### 4. Generate the bulk file
If the user wants the export, create the parent directory and write a TSV.
Use a deterministic writer such as Python `csv.writer` with a tab delimiter.
Required output:
- one campaign
- ad groups split by tier and match type
- keyword rows with bids
Default to this exact tab-separated header and column order:
```text
Product Entity Operation Campaign ID Ad Group ID Portfolio ID Ad ID Keyword ID Product Targeting ID Campaign Name Ad Group Name Start Date End Date Targeting Type State Daily Budget SKU ASIN Ad Group Default Bid Bid Custom Text Campaign Type Targeting Expression
```
Deterministic campaign structure:
- `Tier1-Exact`: Tier 1 keywords as Exact
- `Tier1-Phrase`: Tier 1 keywords as Phrase
- `Tier2-Phrase`: Tier 2 keywords as Phrase
- `Tier3-Broad`: Tier 2 and Tier 3 keywords as Broad
Generate three row types only:
- Campaign row: one per campaign
- Ad Group row: one per ad group
- Keyword row: one per keyword and match-type pair
Use:
- `Start Date`: current date in `YYYYMMDD`
- `Targeting Type`: `Manual`
- `State`: `enabled`
- `Campaign Type`: `Sponsored Products`
If the user requests a different Amazon bulk format, switch only with explicit confirmation.
## Output
Default answer structure:
- short summary of keyword landscape
- preview table
- export path and row count if a file was written
If no export is requested, stop after the preview and recommendations.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |