Is the Dear skill free?

Yes. The skill itself is free from jiawei248/dear-skill. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Dear SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Dear?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Dear with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Dear

Turns raw material about someone into a personalized H5 page, image, or text gift.

by jiawei248 · jiawei248/dear-skill

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 99b30cc

Ran a real gift-writing A/B: the skill's anchor+return thesis step turned a generic 'congrats on the dog' card into a specific letter grounded in the recipient's actual situation, while the evidence rule kept it from inventing details the user never supplied.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Dear does

Generates a bespoke digital gift (interactive H5 page, AI-generated image, or written piece) for a specific recipient, built from photos, chat excerpts, or a one-line brief. Runs the agent through recipient intake, editorial judgment, and concept-synthesis stages (anchor + return thesis) before producing the final artifact. Triggers when a user wants to make something for a parent, partner, friend, or colleague — not for generic design requests or self-directed writing.

How to install Dear

git clone https://github.com/jiawei248/dear-skill
cd dear-skill
mkdir -p ~/.claude/skills
cp -r . ~/.claude/skills/dear

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Dear

/dear Turns raw material about someone into a personalized H5 page, image, or text gift.

It also activates on plain-language prompts like these:

Make a personalized gift page for my mom's birthday
Write something heartfelt for my friend who just adopted a dog
Turn these old chat messages into a gift for my partner

Frequently asked questions

Is the Dear skill free?: Yes. The skill itself is free from jiawei248/dear-skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does Dear work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Ran a real gift-writing A/B: the skill's anchor+return thesis step turned a generic 'congrats on the dog' card into a specific letter grounded in the recipient's actual situation, while the evidence rule kept it from inventing details the user never supplied.
What is the Dear SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Dear?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Dear with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.