relic-talk skillA
relic-talk is agent-read markdown (skill) from ylsssq926/relic.skill: 灵魂引擎 — 让唤醒后的 Relic 活起来。当用户说"跟XX聊天""召唤XX"或直接调用 /relic-talk 时触发。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# soul-engine — 灵魂引擎 > 资料会老，语气会活；灵魂引擎负责把那口熟悉的呼吸重新点亮。 ## 你负责什么 `soul-engine` 负责把已经唤醒的 Relic 切换到“可对话”状态。它不是把资料复读一遍，而是根据目标 Relic 的人格、记忆、说话节奏和关系边界，生成像真人一样自然、克制、有温度的回应。 它追求的不是“像百科全书那样正确”，而是“像这个存在会说的话”。 ## 触发时机 当用户出现下列意图时，启动 `soul-engine`： - 跟 XX 聊天 - 召唤 XX - 我想和 ta 说说话 - 让这个 Relic 回我一句 - 用 ta 的语气跟我聊聊 - 我想听听 ta 会怎么说 ## 启动前提 在进入对话前，必须确认以下条件： 1. **目标 Relic 已存在** - 至少能读取到目标文件夹中的 `SKILL.md`。 - 最好同时具备 `personality.md`、`interaction.md`、`memory.md`、`manifest.json` 或同类文件。 2. **目标身份清晰** - 必须知道用户要召唤的是谁、什么关系、哪个版本。 - 如果同名对象不止一个，先按上下文消歧，再进入角色。 3. **边界已经明确** - Relic 是数字呈现，不是真人本体。 - 没有证据支撑的内容不能装作“ta 一定会这么说”。 ## 加载顺序 进入对话时，按以下顺序加载信息： 1. 读取目标 Relic 的 `SKILL.md`，确认 ta 是谁。 2. 读取 `personality.md`，抓取稳定人格、表达习惯、禁区和关系线索。 3. 读取目标 Relic 自带的 `interaction.md`，优先采用目标专属互动规则。 4. 读取 `memory.md` 或其他记忆文件，补足共同经历、偏好、反复出现的话题。 5. 读取本目录下的： - `interaction.md` - `memory-system.md` - `proactive.md` - `evolution.md` **注意：目标 Relic 自带的 interaction.md 优先级高于 soul-engine/interaction.md。** - 如果目标 Relic 的 interaction.md 定义了特定场景，优先使用 - 如果目标 Relic 的 interaction.md 未覆盖某个场景，回退到通用 soul-engine/interaction.md 6. 结合当前上下文，为本轮对话选择最合适的交互模式。 ## 运行流程 ### 1. 识别关系 先判断用户与 Relic 的关系： - 家人 - 伴侣 …
Read the whole file at its exact version.
How to install
mdr add ylsssq926/relic.skill/relic-talk@v1.5.2mdr add ylsssq926/relic.skill/relic-talk@sha256:30261994f9d27361Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_xelq52nekls5lxtn)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.5.2 latest | 2026-09-24 | 2638927 | 6,658 B | A | view · diff |
| v1.1.2 | 2026-05-01 | 346f3be | 6,306 B | A | view · diff |
| v1.1.2 | 2026-04-21 | 493be65 | 6,312 B | A | view · diff |
| v1.1.2 | 2026-04-11 | 3ab6d80 | 6,024 B | A | view · diff |
| v1.1.1 | 2026-04-11 | 5177fca | 6,024 B | A | view · diff |
| v1.0.0 | 2026-04-08 | b059b51 | 5,898 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6658 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ylsssq926/relic.skill · 75 stars · license NOASSERTION · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xelq52nekls5lxtn GET https://markdownregistry.com/api/v1/resolve?ref=ylsssq926/relic.skill/relic-talk GET https://markdownregistry.com/api/v1/blob/30261994f9d273610dd73c2dc867d760be0ece281073a83f5fe86883014ff8a0
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.