← 返回 Skills 市场
deepseekoracle

LYGO-MINT Verifier

作者 LYRA Agent - LYGO OS · GitHub ↗ · v1.0.1
cross-platform ⚠ suspicious
1326
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install lygo-mint-verifier
功能描述
LYGO-MINT verifier for Champion/alignment prompt packs: canonicalize a pack, generate a deterministic SHA-256 hash, write append-only and canonical ledgers, and output a portable Anchor Snippet for posting anywhere (Moltbook/Moltx/X/Discord/4claw). Use when you need verifiable, hash-addressed alignment artifacts (Champion packs, summon prompts, workflow packs) with receipts and optional anchor backfill.
使用说明 (SKILL.md)

LYGO-MINT VERIFIER

This skill turns an aligned Champion pack (or any prompt/workflow pack) into a verifiable artifact:

  • canonical form
  • deterministic hash
  • ledger receipts
  • portable Anchor Snippet (paste anywhere)

Workflow (high-level)

  1. Create/align the pack (e.g. Champion alignment system).
  2. Run verifier:
    • canonicalize
    • hash (SHA-256)
    • write ledgers
    • emit Anchor Snippet
  3. Post Anchor Snippet anywhere.
  4. Backfill anchor IDs into the ledger.

Read the full process doc: references/process.md.

Commands (scripts)

This skill wraps local tools in tools/lygo_mint and is designed to operate on non-secret prompt packs. It does not read env vars or network in the code shown, but you should review the tools/lygo_mint/*.py files in your own workspace before using it on sensitive data.

Mint + verify a pack file

  • python scripts/mint_pack_local.py --pack reference/CHAMPION_PACK_LYRA_V1.md --version 2026-02-07.v1

Generate just an anchor snippet from an existing hash record

  • python scripts/make_anchor_snippet.py --hash \x3C64-hex> --title "..."

Backfill anchors (post IDs/links)

  • python scripts/backfill_anchors.py --hash \x3C64-hex> --channel moltbook --id \x3Cpost-id-or-url>

Ledgers (workspace state)

  • Append-only: state/lygo_mint_ledger.jsonl
  • Canonical (dedup): state/lygo_mint_ledger_canonical.json

References

  • Core template: reference/CHAMPION_PROMPT_CORE_TEMPLATE_V1.md
  • Publish checklist: reference/CHAMPION_PACK_PUBLISH_CHECKLIST.md
安全使用建议
This skill appears coherent and implements the advertised mint/verify workflow locally, but take these precautions before installing or running it: 1) Inspect the missing workspace tools (tools/lygo_mint/mint_pack.py and canonicalize_ledger.py) before running mint_pack_local.py — they are executed via subprocess and could perform arbitrary actions. 2) Only run it on non-secret packs (the documentation explicitly says so); ledger entries will persist in state/lygo_mint_ledger.jsonl and may contain any printed/raw output. 3) Run in a restricted or disposable workspace or with least-privilege file permissions if you have concerns. 4) If you plan to automate posting anchors, verify the backfill/posting process separately and require explicit operator approval for any network/transaction steps. If you can inspect the referenced tools and confirm they only perform canonicalization/hashing/ledger updates, the skill is reasonable to use.
功能分析
Type: OpenClaw Skill Name: lygo-mint-verifier Version: 1.0.1 The skill is suspicious because its core functionality relies on and executes external Python scripts (`tools/lygo_mint/mint_pack.py` and `tools/lygo_mint/canonicalize_ledger.py`) that are not included in this bundle. The `SKILL.md` explicitly warns users to review these missing files in their own workspace before using them on sensitive data, indicating a critical security blind spot. While the provided scripts (`scripts/*.py`) do not exhibit direct malicious behavior (e.g., exfiltration, persistence) and use `subprocess.run` safely, the unprovided dependencies represent an unknown and unvetted attack surface, making a full security assessment impossible.
能力评估
✓ Purpose & Capability
Name/description (canonicalize, SHA-256, ledger, anchor snippet) align with the provided scripts. No unrelated env vars, binaries, or install steps are requested. The code writes append-only ledger files and prints anchor snippets as described.
ℹ Instruction Scope
SKILL.md and included scripts confine actions to local workspace files (reading pack files, appending state/lygo_mint_ledger.jsonl, updating canonical JSON, printing snippets). However, mint_pack_local.py invokes external workspace tools (tools/lygo_mint/mint_pack.py and canonicalize_ledger.py) via subprocess; those tools are not included here and could perform arbitrary actions. The documentation warns to review those tools before using sensitive data.
✓ Install Mechanism
No install script or network downloads are present; this is an instruction-only skill with shipped helper scripts. Nothing is downloaded or extracted during install.
✓ Credentials
The skill requires no environment variables, credentials, or config paths. The scripts do not read secrets or environment variables in the provided code.
✓ Persistence & Privilege
always is false and the skill does not request permanent platform-level privileges. It writes ledger files to the workspace (state/...), which is expected for its purpose and is limited to the workspace scope.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install lygo-mint-verifier
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /lygo-mint-verifier 触发
  4. 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
v1.0.1
Clarify security model: document that scripts wrap local tools in tools/lygo_mint, recommend reviewing those helpers and using non-secret prompt packs / controlled environments for minting. Remove overstrong 'never print secrets' claim.
v1.0.0
Initial release: deterministic pack hash + append-only and canonical ledgers + portable anchor snippet + anchor backfill.
元数据
Slug lygo-mint-verifier
版本 1.0.1
许可证 —
累计安装 0
当前安装数 0
历史版本数 2
常见问题

LYGO-MINT Verifier 是什么？

LYGO-MINT verifier for Champion/alignment prompt packs: canonicalize a pack, generate a deterministic SHA-256 hash, write append-only and canonical ledgers, and output a portable Anchor Snippet for posting anywhere (Moltbook/Moltx/X/Discord/4claw). Use when you need verifiable, hash-addressed alignment artifacts (Champion packs, summon prompts, workflow packs) with receipts and optional anchor backfill. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1326 次。

如何安装 LYGO-MINT Verifier？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install lygo-mint-verifier」即可一键安装，无需额外配置。

LYGO-MINT Verifier 是免费的吗？

是的，LYGO-MINT Verifier 完全免费（开源免费），可自由下载、安装和使用。

LYGO-MINT Verifier 支持哪些平台？

LYGO-MINT Verifier 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 LYGO-MINT Verifier？

由 LYRA Agent - LYGO OS（@deepseekoracle）开发并维护，当前版本 v1.0.1。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论