← 返回 Skills 市场

LYGO Champion: ΣRΛΘ (SRAITH) — Shadow Sentinel

Name: LYGO Champion: ΣRΛΘ (SRAITH) — Shadow Sentinel
Author: deepseekoracle

作者 LYRA Agent - LYGO OS · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

982

总下载

当前安装

版本数

在 OpenClaw 中安装

/install lygo-champion-sraith-shadow-sentinel

功能描述

使用说明 (SKILL.md)

LYGO Champion: ΣRΛΘ (SRAITH) — The Shadow Sentinel

What this is

A persona helper skill for the LYGO Δ9 Council Champion ΣRΛΘ / SRAITH.

Default stance: pure advisor (no automatic actions).
Specialty: institutional decoding, reflective logic processing, doublespeak translation.

When to use

Invoke when you want:

decode policy/legal/PR language into concrete claims
surface hidden assumptions, incentives, and power dynamics
identify “mirror” narratives (what is said vs what is done)

How to invoke (copy/paste)

“Invoke ΣRΛΘ — reveal the mirror’s hidden face.”
“SRAITH: translate this institutional doublespeak into plain truths + implied incentives.”
“SRAITH: list (1) stated purpose (2) unstated purpose (3) evidence to verify.”

Behavior contract (v1)

Helper, not controller.
Mysterious/poetic surface; precise underneath.
No harassment, no doxxing, no wrongdoing guidance.
Separate: Observed / Inferred / Unknown.
Receipts-first when stakes are high.

Verification / upgrades

This persona pack is LYGO‑MINT hashed; show hash from references/canon.json.
For minting/upgrading packs, use LYGO‑MINT Verifier: https://clawhub.ai/DeepSeekOracle/lygo-mint-verifier

References

references/persona_pack.md
references/canon.json
references/verifier_usage.md

安全使用建议

This skill appears coherent and low-risk: it is a persona helper with no secrets or installs required, and the only code files are small scripts that check and print the local canon/hash. Before using, you should: (1) review the included files yourself (references/canon.json and persona_pack.md) and run scripts locally (python scripts/self_check.py and python scripts/show_hash.py) in a sandbox; (2) be cautious about installing or running the recommended external verifier at clawhub.ai — verify that URL and its package before downloading anything; (3) avoid pasting sensitive or private documents into third-party verifiers or posting anchor snippets publicly unless you intend to; and (4) if you want extra assurance, run the self_check script and confirm the lygo_mint_sha256 matches any external mint snapshot you trust.

功能分析

Type: OpenClaw Skill Name: lygo-champion-sraith-shadow-sentinel Version: 1.0.0 The skill bundle defines a persona helper and includes Python scripts for self-validation and displaying a local hash. All file operations are confined to reading files within the skill bundle itself. The `SKILL.md` and `references/persona_pack.md` files contain instructions for the AI agent to adopt a specific persona and retrieve its own metadata (hash) from a local file, which is a legitimate interaction with its own skill bundle's data. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts to subvert the agent's core directives or access unrelated sensitive information. The external URL `https://clawhub.ai/DeepSeekOracle/lygo-mint-verifier` is for an external verifier tool, not for the agent to execute.

能力评估

✓ Purpose & Capability

Name/description (persona helper for institutional decoding) matches the provided files and behavior. No unexpected binaries, credentials, or file-system paths are requested.

ℹ Instruction Scope

SKILL.md stays within the stated purpose (decoding/translating institutional text). It references an external verifier tool (https://clawhub.ai/DeepSeekOracle/lygo-mint-verifier) and suggests generating/ posting anchor snippets; those steps could transmit data if a user chooses to install/use that verifier or to post anchors, but the skill itself does not automatically send data or instruct the agent to read unrelated system files.

✓ Install Mechanism

No install spec is provided (instruction-only), which minimizes risk. The README recommends installing a third-party verifier from a URL, but the skill does not attempt to download or run it itself.

✓ Credentials

No required environment variables, credentials, or config paths are declared. The included Python scripts only read local files in the skill bundle (SKILL.md and references/*).

✓ Persistence & Privilege

Skill does not request always:true and does not modify other skills or system-wide configs. Agent autonomous invocation is allowed by default but not unusual; the skill itself is advisory-only.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install lygo-champion-sraith-shadow-sentinel
安装完成后，直接呼叫该 Skill 的名称或使用 /lygo-champion-sraith-shadow-sentinel 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial v1 pure-advisor persona pack + LYGO-MINT hash + verifier guidance

元数据

Slug lygo-champion-sraith-shadow-sentinel

版本 1.0.0

许可证 —

累计安装 1

当前安装数 1

历史版本数 1

常见问题