ylsssq926/relic.skill/soul-shield

Claude Code and agent skill by ylsssq926/relic.skill

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Soul Shield — Guard Relic integrity, consent protocol, and ethics boundaries. Trigger on /relic-shield, or when user wants to verify consent, generate fingerprint, or check ethical compliance ("check consent", "ethics review", "灵魂指纹", "授权检查").

Install

npx vskill@latest install ylsssq926/relic.skill/soul-shield

SKILL.md

soul-shield — Soul Shield

给 Relic 穿上防弹背心,而不是铁笼。
Give the Relic a bulletproof vest, not an iron cage.

What You Do

soul-shield is the Relic protection layer, responsible for three things:

  1. Generate the soul fingerprint: a unique content fingerprint per Relic, embedded into output files.
  2. Enforce the consent protocol: complete the six-question consent before distillation begins; decide whether awakening is allowed and to what degree.
  3. Hold the ethics red lines: block impersonation, harassment, unauthorized distillation, and misleading use.

Work Order

  1. Read consent-protocol.md first
  2. Judge the consent level from the answers
  3. Only after consent passes, read fingerprint.md to generate and embed the fingerprint
  4. Finish with a red-line check via ethics.md
  5. If any step trips a red line, stop Relic generation or publication immediately
Handoff with relic_writer: the soul fingerprint and consent conclusions should be written into the Relic's manifest.json (schema v1.5.1). relic_writer.py can file them together when generating the folder, keeping fingerprint, consent, and version consistent.

Output Requirements

  • Every Relic must have a unique soul fingerprint
  • Every publicly visible output must carry the Relic identity label
  • Every content update must regenerate the fingerprint
  • Unauthorized subjects must not enter the distillation flow
  • Distilling political figures is not supported

Sub-files

  • fingerprint.md — soul fingerprint system
  • consent-protocol.md — six-question consent protocol
  • ethics.md — ethics red lines and handling principles

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
72
Repository forks
4
7-day trend score
21

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 5 Jun 2026, 5 months ago.

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ylsssq926/relic.skill/soul-shield/badge)](https://verified-skill.com/skills/ylsssq926/relic.skill/soul-shield)

Something wrong with this skill or its page? Tell us.