trust-conversion-reviewer — Claude Code skill: install and usage
trust-conversion-reviewer is a Claude Code skill that inspects whether visible proof, risk details, and next actions support an informed user choice.
MIT ★ 529 updated 2026-11-17
npx skills add ShuaiMXu/happyhands --skill trust-conversion-reviewer -a claude-codeWhat trust-conversion-reviewer does
The skill identifies missing or misplaced details that block users from taking their next step. It relies on three core inputs: the target user decision, visible claims with proof, and primary alongside alternative actions. The output provides structured evidence, findings, proposed updates, and limitations.
Every recommendation directly connects to the identified user decision, keeping trust separate from persuasive tactics. The skill forbids claiming conversion uplift without behavioral data, creating arbitrary Experience Scores, or turning a project-specific observation into a general standard. When critical input or professional review is missing, it tags the item with needs-evidence.
The scope is limited to decision support rather than measured conversion rates. Running the skill requires no API keys or external servers. Setup works through npm or by placing SKILL.md directly into the agent directory.
What it helps with
- spot missing evidence required before a user commits to an action
- separate genuine trust indicators from aggressive persuasion tactics
- audit checkout screens for clear risk and guarantee messaging
- prepare structured review findings without fabricated lift metrics
Example prompts for the agent
- Run trust-conversion-reviewer on our pricing table where users choose between annual and monthly plans
- Review the signup modal with trust-conversion-reviewer to inspect proof and secondary actions
- Evaluate the checkout flow using trust-conversion-reviewer against the decision to submit card details
How to install trust-conversion-reviewer
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill trust-conversion-reviewer -a claude-code2Manually: put the files in place
~/.claude/skills/trust-conversion-reviewer/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/trust-conversion-reviewer/
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill trust-conversion-reviewer -a codex2Manually: put the files in place
.agents/skills/trust-conversion-reviewer/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill trust-conversion-reviewer -a cursor2Manually: put the files in place
.cursor/skills/trust-conversion-reviewer/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ShuaiMXu/happyhands skills/product-design/trust-conversion-reviewer2Manually: put the files in place
.github/skills/trust-conversion-reviewer/SKILL.md1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill trust-conversion-reviewer -a gemini-cli2Platform CLI
gemini skills install https://github.com/ShuaiMXu/happyhands --path skills/product-design/trust-conversion-reviewerManually: put the files in place
.devin/skills/trust-conversion-reviewer/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about trust-conversion-reviewer
How to install trust-conversion-reviewer in Claude Code?
Run npx skills add ShuaiMXu/happyhands --skill trust-conversion-reviewer -a claude-code or save the instructions to ~/.claude/skills/trust-conversion-reviewer/SKILL.md.
What is trust-conversion-reviewer used for?
It audits interface copy and layout to ensure users have enough facts, guarantees, and alternatives to make an informed decision.
Does trust-conversion-reviewer track conversion metrics?
No, it reviews user decision support and explicitly prohibits claiming conversion uplift without actual behavioral telemetry.
Source text
SKILL.md · MIT
--- name: trust-conversion-reviewer description: "Review whether proof, risk information and next actions support a credible user decision." --- # Trust and Conversion Reviewer Find missing or misplaced information that prevents an informed next step. ## Required evidence - user decision - visible claims and proof - primary and alternative actions ## Decisions - Connect every recommendation to the user decision - Separate trust from persuasion - Never claim uplift without behavioral data ## Boundary This skill reviews decision support, not measured conversion. Return structured evidence, findings, proposed updates and limitations. Use `needs-evidence` when required inputs or professional review are missing. Never invent an Experience Score or promote a project observation into a universal rule.
© ShuaiMXu · MIT · ShuaiMXu/happyhands