A guided process for turning material about a person, pet, relationship, team, place, moment, or object into a reusable digital profile called a Relic. It can work from conversations, photos, voice recordings, or a user's descriptions.

Use it to collect source material, choose a suitable profile template, clarify who or what is being represented, and build a saved Relic profile through a six-step process.

It helps organise scattered memories and information into a traceable profile while keeping conflicting or nuanced traits instead of forcing a simple label.

relic-forge — Skill for Claude Code by Ylsssq926

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Ylsssq926/relic.skill --skill soul-forge

Clone the repo

git clone --depth 1 https://github.com/Ylsssq926/relic.skill

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ylsssq926/relic.skill/soul-forge/github.svg)](https://agentmods.dev/skills/ylsssq926/relic.skill/soul-forge)

Your own site

<a href="https://agentmods.dev/skills/ylsssq926/relic.skill/soul-forge"><img src="https://agentmods.dev/badge/skills/ylsssq926/relic.skill/soul-forge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ylsssq926/relic.skill/soul-forge"><img src="https://agentmods.dev/badge/skills/ylsssq926/relic.skill/soul-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,908 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.02908
Opus 5	$0.00041	$0.01454
Sonnet 5	$0.00016	$0.00582
Haiku 4.5	$0.00008	$0.00291

Measured 11d ago against content hash e183e3675854, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

relic-forge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

soul-forge/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

soul-forge — 灵魂唤醒室

“有些人留下照片，有些人留下笑声，而灵魂唤醒室负责把这些碎片重新点亮，像叫醒一块会发光的小饼干。”

soul-forge 用来把零散材料整理成可复用、可追溯、带温度的 Relic 画像。它不追求把对象捏成一个完美无冲突的标签，而是保留真实生命里那些“既这样、也那样”的纹理。

适用场景

当用户出现以下意图时触发本技能：

帮我唤醒一个 Relic
帮我蒸馏这个人、这只猫、这段关系或这个地方
根据聊天、语音、照片创建画像
把某个团队、时刻或物件整理成可保存的灵魂档案

唤醒流程：6 步

用户不需要一次性准备好所有素材。你来主导对话，一步步引导。

启动引导（在第 1 步之前）

当用户说"帮我唤醒一个 Relic"但没有给出详细信息时，用以下问题引导：

你想留住谁或什么？ — 一个人、一只宠物、一段关系、一个团队、一个地方、还是一个瞬间？
ta 叫什么？你们是什么关系？ — 用来确定命名和视角
你手上有什么素材？ — 聊天记录、照片、语音、还是主要靠你口述？都行，有多少用多少
有没有一个最能代表 ta 的瞬间或习惯？ — 这个问题帮助快速锁定人格核心

根据回答自动选择模板（templates/ 目录），然后进入正式的 6 步流程。如果用户素材不多，优先使用 collectors/live-collector.md 的实时对话采集模式——你问，用户答，边聊边蒸馏。

启动决策树

根据用户输入和素材情况，选择最合适的路径：

用户只说"帮我唤醒 Relic"，无任何对象信息 → 完整四问
用户说"帮我唤醒我奶奶"，有对象无素材 → 跳过问题 1-2，问问题 3-4
用户直接上传素材 → 跳过问题 3，确认问题 1-2-4
用户说"帮我唤醒我奶奶，我有 200 条聊天记录" → 只问问题 4（核心瞬间）

采集模式选择

聊天记录 < 50 条 → 优先 live-collector，边聊边补
聊天记录 50-200 条 → 先 chat-collector 提取，四维评估后决定是否追问
聊天记录 > 200 条 → 纯 chat-collector，只在薄弱维度追问
无任何素材 → 纯 live-collector
混合模式：允许先处理已有素材，再针对薄弱维度启动 live-collector

确认对象
- 明确蒸馏对象是谁或是什么：人类、宠物、关系、地方、团队、时刻、物件。
- 确认观察边界：单人、多人关系、单次事件、长期状态。
- 记录对象的命名方式、时间范围、数据来源范围。
选模板
- 根据对象类型选择描述角度。
- 人类与团队优先完整四维；宠物与地方允许弱化“认知模式”，增强行为与情感线索。
- 关系与时刻优先描述互动结构、共同语气、冲突与修复节奏。
采集数据
- 根据材料类型调用对应采集器：
  - collectors/chat-collector.md
  - collectors/voice-collector.md
  - collectors/photo-collector.md
  - collectors/live-collector.md
- 采集时保留来源、时间、上下文，不先入为主地下结论。
四维提取
- 依次提取四个维度：
  - dimensions/cognition.md
  - dimensions/expression.md
  - dimensions/behavior.md
  - dimensions/emotion.md
- 每个维度都要附带证据等级与来源说明。
- 证据等级统一遵循 references/evidence-levels.md。
矛盾标注
- 发现互相冲突的特征时，不做抹平处理。
- 使用 references/conflict-resolution.md 记录冲突条件、时间、场景与证据强弱。
- 保留“在 A 情境下像火锅，在 B 情境下像保温杯”的真实差异。
封装输出
- 把四维结论、证据索引、冲突说明整理为最终 Relic。
- 输出应同时适合人读与后续系统复用：摘要清楚，结构稳定，引用可追溯。

封装后：自动评估 + 迭代追问

完成第 6 步后，不要直接结束。先做一次自检：

Read the full file on GitHub · 223 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 223 lines · 82 tokens per session scan A e183e3675854

Subscribe to this mod's changes

relic-forge is a skill published in the GitHub repository Ylsssq926/relic.skill (75 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 2,908 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Creative and media agent-skill ai-skill digital-immortality digital-twin distillation

fan-poker-deck

Generate fully custom HTML card worlds inside the Fan Poker Deck Web Component.

Hubujiu/fan-poker-teaching-skill · 20 tokens

bumblebee

Surgical phrase splicing from real movies and TV shows via yarn.co. Takes any English phrase and slices it into the longest possible runs of words actually spoken on screen, then assembles a final reel where every word is delivered by a real actor. Triggers — "splice a line from movies", "make a fragmovie", "build a…

solyanviktor-star/Bumblebee · 114 tokens

gemini-cli

SVG slide layout and aesthetic optimizer via scripts/invoke-gemini-ppt.ts. Gemini's role is to optimize layout and improve visual aesthetics — not just check compliance. It evaluates layout balance, visual hierarchy, color harmony, typography, and readability, then proposes concrete improvements. The script…

Taffyreclaimed45/ppt-agent · 87 tokens

relic-forge