← 返回 Skills 市场
bigbadman-lab

GM3 Alertworthy Feed

作者 alexattinger · GitHub ↗ · v1.0.3
cross-platform ⚠ suspicious
1308
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install gm3-alertworthy-feed
功能描述
Read-only access to the GM3 Alertworthy feed, providing real-time token market data for analysis agents.
使用说明 (SKILL.md)

GM3 Alertworthy Feed

--

Overview

This skill provides read-only access to the GM3 Alertworthy feed.

It returns the current snapshot of alertworthy tokens, including valuation, flow, buyer distribution, and market structure signals. The skill is designed to be used by analysis agents that apply their own filtering and decision logic on top of the raw GM3 data.

This skill does not perform filtering, ranking, or trading actions.

Endpoint

GET
https://api.gm3.fun/functions/v1/gm3-api/v1/paid/alertworthy

Authentication

This skill requires a GM3 Developer API key.

Requests must include the following header:

Authorization: Bearer gm3_key_...

The API key should be stored as a secret and never exposed in client-side code.

Headers

Accept: application/json

Inputs

This endpoint does not accept input parameters.

Output

The response is a JSON object containing a data array of alertworthy token snapshots.

Each item may include fields such as:

  • mint
  • rank
  • fdv_usd (current FDV)
  • fdv_at_alert (FDV at first alert)
  • net_sol_inflow
  • buy_ratio
  • buy_count / sell_count
  • unique_buyers
  • capital_efficiency
  • market structure flags
  • timestamps

The exact fields returned are subject to change as the GM3 platform evolves.

Errors

  • 401 Unauthorized – Invalid or revoked API key, or entitlement expired
  • 429 Too Many Requests – Rate limited
  • 500 / 503 – Temporary server error

Notes

  • This skill is intended for analysis-only use.
  • Strategy logic, filtering, and decision-making should be implemented at the agent level.
  • No trading or execution functionality is provided by this skill.
安全使用建议
This skill is small and its behavior (one read-only GET to https://api.gm3.fun/…) is plausible for the described purpose, but there are two issues to address before installing: - Metadata mismatch: The SKILL.md says a GM3 Developer API key is required (Authorization: Bearer gm3_key_…), yet the registry entry declares no required env vars or primary credential. Ask the publisher to declare the exact secret name (e.g., GM3_API_KEY) in requires.env and mark it as the primary credential. That makes the credential usage explicit and auditable. - Provenance and trust: The source/homepage are unknown. Because the skill needs a secret (an API key), only install it if you trust the publisher or can test it in a restricted environment. Confirm how the agent will retrieve the secret (platform secret store vs. prompting the user) and that the skill will only use the key for this endpoint. If the publisher updates the registry to explicitly declare the required env var/primary credential and you can verify the skill originates from a trusted source, the inconsistency is resolved and this skill is likely benign. Until then treat it as suspicious and prefer to test in a sandbox or request the missing metadata.
功能分析
Type: OpenClaw Skill Name: gm3-alertworthy-feed Version: 1.0.3 The skill bundle is benign. It provides read-only access to an external API endpoint (`https://api.gm3.fun`) for market data, as clearly stated in `SKILL.md`. The documentation explicitly limits the skill to 'analysis-only use' and disclaims any trading or execution functionality. There is no evidence of prompt injection, data exfiltration beyond the stated API call, malicious execution, persistence, or obfuscation. The requirement for an API key is standard for accessing authenticated services.
能力评估
ℹ Purpose & Capability
The name/description match the SKILL.md instructions: it is a read-only feed that returns token snapshots from a single GM3 API endpoint. There is no functionality unrelated to the stated purpose in the instructions.
⚠ Instruction Scope
The SKILL.md instructs the agent to call a single GET endpoint and to include an Authorization: Bearer gm3_key_... header. Instructions are otherwise limited and do not ask the agent to read local files or other secrets. However the doc does not specify the exact env var name or mechanism the agent should use to access the API key (it only states the API key should be stored as a secret), leaving behavior ambiguous.
✓ Install Mechanism
No install spec and no code files are present; this is instruction-only, so nothing is written to disk or downloaded during install.
⚠ Credentials
The SKILL.md explicitly requires a GM3 Developer API key for Authorization, but the registry metadata lists no required env vars and no primary credential. That mismatch is disproportionate and ambiguous: the skill will need a secret at runtime but does not declare which environment variable or secret name it expects.
✓ Persistence & Privilege
The skill does not request persistent/always-on presence and does not modify system or other skill configuration. Autonomous invocation is allowed (platform default) but is not combined with other high privileges.
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 gm3-alertworthy-feed
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /gm3-alertworthy-feed 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
v1.0.3
- Added front-matter metadata (name and description) to SKILL.md for improved documentation format. - No changes to functionality or API usage.
v1.0.2
- Added a concise "Summary" section at the beginning of the documentation for clearer and quicker understanding of the skill's purpose. - No functional or API changes; documentation update only.
v1.0.1
- Documentation formatting updated for improved readability - No changes to functionality or source code
v1.0.0
GM3 Alertworthy Feed skill – initial release: - Provides read-only access to the GM3 Alertworthy feed via a secure API endpoint. - Returns up-to-date snapshots of alertworthy tokens, including valuation, flow, buyer activity, and market structure signals. - Requires a GM3 Developer API key for authentication. - Does not support input parameters, filtering, ranking, or trading actions. - Designed for analysis by external agents; output format and fields may evolve with the GM3 platform.
元数据
Slug gm3-alertworthy-feed
版本 1.0.3
许可证 —
累计安装 0
当前安装数 0
历史版本数 4
常见问题

GM3 Alertworthy Feed 是什么？

Read-only access to the GM3 Alertworthy feed, providing real-time token market data for analysis agents. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1308 次。

如何安装 GM3 Alertworthy Feed？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install gm3-alertworthy-feed」即可一键安装，无需额外配置。

GM3 Alertworthy Feed 是免费的吗？

是的，GM3 Alertworthy Feed 完全免费（开源免费），可自由下载、安装和使用。

GM3 Alertworthy Feed 支持哪些平台？

GM3 Alertworthy Feed 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 GM3 Alertworthy Feed？

由 alexattinger（@bigbadman-lab）开发并维护，当前版本 v1.0.3。

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...
⬇ 463556 · 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.
⬇ 259610 · 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...
⬇ 200551 · 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.
⬇ 191226 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190235 · by oswalpalash

💬 留言讨论