lavey/4th-devs-dotnet48/product-compare
Claude Code and agent skill by lavey/4th-devs-dotnet48
- community
Checking that the SKILL.md file is still in the repository.
Research products into per-product notes under a topic folder, then run a merge script to assemble an overview note. Use when the user asks for structured product research/comparison.
Install
npx vskill@latest install lavey/4th-devs-dotnet48/product-compareSKILL.md
Use this skill when the user asks for structured product research with a final overview.
Goal
Produce a topic research workspace with this strict flow:
- Research each product into its own markdown file.
- Execute the merge script to generate a topic overview file.
Maximum products: 3.
If the user gives more than 3 products, ask them to reduce the scope.
Required Workflow
- Parse arguments with deterministic rules:
- Preferred form:
<topic> | <product-a> | <product-b> | [product-c] - If topic is omitted and only products are present, derive topic as joined product slugs:
notion-airtable-clickup- products must be
2-3
- Use topic folder:
vault/research/<topic>/- do not create placeholder files (
.keep.md) - writing first product file should create missing directories automatically
- For each product, run web research and write:
vault/research/<topic>/<product-slug>.md
- Use
web_searchto gather evidence for each product:
- official product page/docs
- official pricing page (if available)
- at least one independent source per product
- target at least 3 source URLs per product note whenever available
- Write each product file using the required structure below.
- Run
code_modeusing the runtime script:
script_path: "vault/system/skills/product-compare/scripts/merge-overview.js"input: { "topic": "<topic>" }
- Verify output file:
vault/research/<topic>/overview.md
- Confirm what was created.
Required Product File Structure
Each product file (vault/research/<topic>/<product-slug>.md) MUST contain:
# <Product Name>## Positioning## Pricing## Key Features## Integrations## Strengths## Risks## Best Fit## Sources(bullet list of URLs; include at least one real URL)
Use this normalized schema in the content:
- positioning
- key features (3-6)
- pricing model
- deployment model
- integrations/ecosystem
- strengths
- risks/tradeoffs
- best fit
Missing Information Rule (required)
If information is not found, do NOT skip the section. Write one explicit line in that section:
Not found in reviewed sources as of <YYYY-MM-DD>.
If sources conflict, write:
Conflicting information across sources; verification required.
Deterministic tool usage for this skill
- Use
terminalfor folder/file checks and content writes. - In
code_mode, do not attempt web/network retrieval. - Use
code_modeonly for deterministic merge of existing product notes into overview. - Do not create or rely on placeholder files like
.keep.md.
Output Paths
- Product files:
vault/research/<topic>/<product-slug>.md- Merged overview:
vault/research/<topic>/overview.md
Code Mode Guidance
Use this exact code_mode call shape:
Quality Rules
- Keep claims tied to sources.
- Do not fabricate pricing numbers.
- Prefer neutral language over hype.
- If evidence is weak/conflicting, state uncertainty explicitly in the product file.
- Missing information must be explicitly marked ("Not found..." rule above).
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingsrc/04_01_garden/vault/system/skills/product-compare/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/lavey/4th-devs-dotnet48/product-compare)