Immortal Skill

Distills a person's working style from chat logs into an evidence-graded skill

Tested · Works

Test report

Verdict
Tested · Works
Score
8.4/10
Tested
Jul 28, 2026
Environment
Claude Code 2.x (agent harness)

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.

Fed both a no-skill run and a skill run the same 18-message Slack review log and asked each to build a persona of the colleague who wrote it. The no-skill draft invented three things the log never said - it called him a 'senior engineer', set his PR-size limit at 500 lines when he wrote 300 and 900, and swapped behaviour for personality labels. The skill run produced four files with 26 verbatim tags, 38 dated source citations, a conflicts file that caught a genuine tension between his 'no unplanned calls' rule and his own offer to pair, and an explicit 'insufficient material' entry for tools and environment rather than a guess; manifest_tool.py init and stamp both ran clean and SHA-fingerprinted every file. The catch is that everything ships in Chinese - SKILL.md, all seven persona templates, all six extractor prompts - and the README's install line points at ~/.openclaw/skills, not ~/.claude/skills. The README also advertises a third-layer anti-distillation 'poisoning' defence that turns out to be a 59-line script emitting one canary string.

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 3/5

What Immortal Skill does

Turns raw material about a person - chat exports, email, social archives, documents - into a loadable Agent Skill package covering their procedures, interaction style, memories and personality. Every extracted claim is tagged verbatim, artifact or impression, contradictions are routed to a conflicts file, and a Python CLI initializes the directory, fingerprints each file and stamps a manifest. Triggers on requests to build a digital twin, preserve a colleague's or mentor's working method, or turn someone's message history into a persona Claude can load.

How to install Immortal Skill

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 Immortal Skill

  • /immortal-skill Distills a person's working style from chat logs into an evidence-graded skill

It also activates on plain-language prompts like these:

  • 把我导师身上的教学方法和工作习惯,从他这几年的聊天记录和邮件往来里,提炼成一个可以直接加载的技能包
  • 帮我把这位同事在过去半年代码评审里体现出来的风格和习惯,整理成一个带证据标注的数字分身档案
  • 根据这些微信聊天记录和朋友圈内容,为已经过世的爷爷建一个带有记忆和性格的数字人格档案

Frequently asked questions

Is the Immortal Skill skill free?
Yes. The skill itself is free from agenmod/immortal-skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does Immortal Skill work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 28, 2026. Verdict: Tested · Works. Fed both a no-skill run and a skill run the same 18-message Slack review log and asked each to build a persona of the colleague who wrote it. The no-skill draft invented three things the log never said - it called him a 'senior engineer', set his PR-size limit at 500 lines when he wrote 300 and 900, and swapped behaviour for personality labels. The skill run produced four files with 26 verbatim tags, 38 dated source citations, a conflicts file that caught a genuine tension between his 'no unplanned calls' rule and his own offer to pair, and an explicit 'insufficient material' entry for tools and environment rather than a guess; manifest_tool.py init and stamp both ran clean and SHA-fingerprinted every file. The catch is that everything ships in Chinese - SKILL.md, all seven persona templates, all six extractor prompts - and the README's install line points at ~/.openclaw/skills, not ~/.claude/skills. The README also advertises a third-layer anti-distillation 'poisoning' defence that turns out to be a 59-line script emitting one canary string.
What is the Immortal Skill SkillProof Score?
8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.
How do I install Immortal Skill?
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 Immortal Skill 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.