Is the Think Like Me skill free?

Yes. The skill itself is free from kakha13/think-like-me. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Think Like Me SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Think Like Me?

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 Think Like Me 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.

Think Like Me

Curated engineering rules that Claude consults before it writes any code

by kakha13 · kakha13/think-like-me

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 28, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · 0eff5c1

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 28, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ran an Expo task twice - Google sign-in via expo-auth-session plus a verified badge on a profile row inside a tab FlatList - and the skill's rule files caught three concrete mistakes the no-skill run made: it left the expo-auth-session PKCE default on with ResponseType.IdToken (Google rejects that with 400 invalid_request), it styled a component inside a tab-navigator FlatList with a NativeWind className, and it used a check-mark emoji as the status glyph. The skill run replaced all three and added the `expo prebuild --clean` step the baseline skipped entirely. The catch comes from the ten pre-seeded rules, which are the author's own Expo/Laravel gotchas, so how much you get on day one depends on whether you share his stack - one shipped rule even admits its mechanism is unclear. The capture side is gated: every rule is shown as a draft and needs an explicit yes before it is written to the rule file and mirrored into project memory.

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

Installs cleanly 5/5
Triggers reliably 4/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Think Like Me does

Stores your engineering gotchas as structured When/Do/Why rule blocks in per-domain files and makes Claude read the matching ones before it drafts code, instead of surfacing them after the fact like passive memory. Adds rules through /learn-this after a correction, /new-rule from a description, or an auto-detect offer when you push back, always behind an approval gate. Ships with ten of the author's own mobile, backend and UI rules as a starting set.

How to install Think Like Me

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Think Like Me

/think-like-me Curated engineering rules that Claude consults before it writes any code

It also activates on plain-language prompts like these:

Add Google sign-in to my Expo app the way I always want it built
/new-rule never edit the ios directory directly on any Expo project
Fix this Laravel middleware ordering bug using my usual conventions

Frequently asked questions

Is the Think Like Me skill free?: Yes. The skill itself is free from kakha13/think-like-me. SkillProof publishes the install command and an independent test verdict at no cost.
Does Think Like Me work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 28, 2026. Verdict: Tested · Works. Ran an Expo task twice - Google sign-in via expo-auth-session plus a verified badge on a profile row inside a tab FlatList - and the skill's rule files caught three concrete mistakes the no-skill run made: it left the expo-auth-session PKCE default on with ResponseType.IdToken (Google rejects that with 400 invalid_request), it styled a component inside a tab-navigator FlatList with a NativeWind className, and it used a check-mark emoji as the status glyph. The skill run replaced all three and added the `expo prebuild --clean` step the baseline skipped entirely. The catch comes from the ten pre-seeded rules, which are the author's own Expo/Laravel gotchas, so how much you get on day one depends on whether you share his stack - one shipped rule even admits its mechanism is unclear. The capture side is gated: every rule is shown as a draft and needs an explicit yes before it is written to the rule file and mirrored into project memory.
What is the Think Like Me SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Think Like Me?: 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 Think Like Me 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.