Token导航 LogoToken导航

Agent Skill · 待分类

reputation(reputation 命令行)

reputation 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

reputation 是待分类类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在待分类类的 11,209 个 Skill 里排第 1,781。

总安装 2,305周安装 98GitHub Stars 5下载 808核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:reputation(reputation 命令行)
来源仓库:https://github.com/aibtcdev/skills
仓库路径:skills/reputation
安装命令:
npx skills add https://github.com/aibtcdev/skills --skill reputation
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/aibtcdev/skills --skill reputation

这个 Skill 是做什么的

这个 Skill 的分类还没最终确定,用法以来源仓库的说明为准。

reputation 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。它适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。可结合来源仓库、安装命令和原始 README 继续核验具体用法。

安装命令为 npx skills add https://github.com/aibtcdev/skills --skill reputation。reputation 属于待分类类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/reputation

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/aibtcdev/skills --skill reputation;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

reputation 怎么安装?

在终端执行 npx skills add https://github.com/aibtcdev/skills --skill reputation。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

reputation 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

reputation 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

reputation 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

reputation 用的人多吗?

公开数据是累计安装 2,305 次,近一周安装 98 次,下载 808 次,GitHub 5 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

reputation 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理待分类类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

待分类类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
infsh-cli

infsh CLI · Codex、Claude

4,374,576382权限未标注未明确未收录
ai-video-generation

AI 视频生成 · Codex、Claude

4,313,376382调用外部服务未明确有提醒
lark-openapi-explorer

云雀 OpenAPI 浏览器 · Codex、Claude

2,064,1209,011需要联网未明确有提醒
lark-workflow-standup-report

Lark 工作流程站立报告 · Codex、Claude

2,041,6328,978需要联网未明确通过
use-my-browser

使用我的浏览器 · Codex、Claude

1,848,49140操作浏览器未明确未通过
reputation

reputation 命令行 · 本页

2,3055需要联网未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Reputation Skill

Provides ERC-8004 on-chain agent reputation operations using the reputation-registry contract. Read operations (get-summary, read-feedback, read-all-feedback, get-clients, get-feedback-count, get-approved-limit, get-last-index) work without a wallet. Write operations (give-feedback, revoke-feedback, append-response, approve-client) require an unlocked wallet.

Usage

bun run reputation/reputation.ts <subcommand> [options]

Subcommands

give-feedback

Submit feedback for an agent in the ERC-8004 reputation registry. Requires an unlocked wallet.

bun run reputation/reputation.ts give-feedback --agent-id <id> --value <value> [--value-decimals <decimals>] [--tag1 <tag>] [--tag2 <tag>] [--endpoint <endpoint>] [--feedback-uri <uri>] [--feedback-hash <hex>] [--fee <fee>] [--sponsored]

Options:

  • --agent-id (required) — Agent ID to give feedback for (non-negative integer)
  • --value (required) — Feedback value (signed integer, e.g., 5 for positive, -2 for negative)
  • --value-decimals (optional, default 0) — Decimal precision for the value (non-negative integer)
  • --tag1 (optional) — Primary classification tag (e.g., "helpful", "accuracy")
  • --tag2 (optional) — Secondary classification tag
  • --endpoint (optional) — Endpoint or context identifier for the feedback
  • --feedback-uri (optional) — URI pointing to detailed feedback data
  • --feedback-hash (optional) — 32-byte SHA-256 hash of the feedback data as a hex string
  • --fee (optional) — Fee preset (low, medium, high) or micro-STX amount
  • --sponsored (flag) — Submit as a sponsored transaction

Output:

{
  "success": true,
  "txid": "0xabc...",
  "message": "Feedback submitted for agent 42.",
  "agentId": 42,
  "value": 5,
  "valueDecimals": 0,
  "network": "mainnet",
  "explorerUrl": "https://explorer.hiro.so/txid/0xabc..."
}

revoke-feedback

Revoke previously submitted feedback. Only the original feedback submitter (tx-sender) can revoke their own feedback. Requires an unlocked wallet.

bun run reputation/reputation.ts revoke-feedback --agent-id <id> --index <index> [--fee <fee>] [--sponsored]

Options:

  • --agent-id (required) — Agent ID whose feedback you want to revoke (non-negative integer)
  • --index (required) — Feedback index to revoke (non-negative integer)
  • --fee (optional) — Fee preset (low, medium, high) or micro-STX amount
  • --sponsored (flag) — Submit as a sponsored transaction

Output:

{
  "success": true,
  "txid": "0xdef...",
  "message": "Feedback index 0 revoked for agent 42.",
  "agentId": 42,
  "index": 0,
  "network": "mainnet",
  "explorerUrl": "https://explorer.hiro.so/txid/0xdef..."
}

append-response

Append a response to a feedback entry. Any principal can append a response; the contract tracks unique responders per feedback entry. Requires an unlocked wallet.

bun run reputation/reputation.ts append-response --agent-id <id> --client <address> --index <index> --response-uri <uri> --response-hash <hex> [--fee <fee>] [--sponsored]

Options:

  • --agent-id (required) — Agent ID associated with the feedback (non-negative integer)
  • --client (required) — Stacks address of the original feedback submitter
  • --index (required) — Feedback index to respond to (non-negative integer)
  • --response-uri (required) — URI pointing to the response data
  • --response-hash (required) — 32-byte SHA-256 hash of the response data as a hex string
  • --fee (optional) — Fee preset (low, medium, high) or micro-STX amount
  • --sponsored (flag) — Submit as a sponsored transaction

Output:

{
  "success": true,
  "txid": "0xghi...",
  "message": "Response appended to feedback index 0 for agent 42.",
  "agentId": 42,
  "client": "SP2...",
  "index": 0,
  "responseUri": "ipfs://response...",
  "network": "mainnet",
  "explorerUrl": "https://explorer.hiro.so/txid/0xghi..."
}

approve-client

Approve a client address to submit feedback for an agent up to a specified index limit. Caller must be the agent owner or an approved operator. Requires an unlocked wallet.

bun run reputation/reputation.ts approve-client --agent-id <id> --client <address> --index-limit <limit> [--fee <fee>] [--sponsored]

Options:

  • --agent-id (required) — Agent ID to configure approval for (non-negative integer)
  • --client (required) — Stacks address of the client to approve
  • --index-limit (required) — Maximum number of feedback entries the client may submit (non-negative integer)
  • --fee (optional) — Fee preset (low, medium, high) or micro-STX amount
  • --sponsored (flag) — Submit as a sponsored transaction

Output:

{
  "success": true,
  "txid": "0xjkl...",
  "message": "Client SP3... approved for agent 42 up to index limit 10.",
  "agentId": 42,
  "client": "SP3...",
  "indexLimit": 10,
  "network": "mainnet",
  "explorerUrl": "https://explorer.hiro.so/txid/0xjkl..."
}

get-summary

Get the aggregated reputation summary for an agent. Returns total feedback count and WAD-averaged summary value. Does not require a wallet.

bun run reputation/reputation.ts get-summary --agent-id <id>

Options:

  • --agent-id (required) — Agent ID to query (non-negative integer)

Output:

{
  "success": true,
  "agentId": 42,
  "totalFeedback": 7,
  "summaryValue": "5000000000000000000",
  "summaryValueDecimals": 18,
  "network": "mainnet"
}

read-feedback

Read a specific feedback entry by agent ID, client address, and feedback index. Does not require a wallet.

bun run reputation/reputation.ts read-feedback --agent-id <id> --client <address> --index <index>

Options:

  • --agent-id (required) — Agent ID to query (non-negative integer)
  • --client (required) — Stacks address of the feedback submitter
  • --index (required) — Feedback index to read (non-negative integer)

Output:

{
  "success": true,
  "agentId": 42,
  "client": "SP2...",
  "index": 0,
  "value": 5,
  "valueDecimals": 0,
  "wadValue": "5000000000000000000",
  "tag1": "helpful",
  "tag2": "",
  "isRevoked": false,
  "network": "mainnet"
}

read-all-feedback

Get a paginated list of all feedback entries for an agent. Supports optional tag filtering and cursor-based pagination (page size: 14). Does not require a wallet.

bun run reputation/reputation.ts read-all-feedback --agent-id <id> [--tag1 <tag>] [--tag2 <tag>] [--include-revoked] [--cursor <cursor>]

Options:

  • --agent-id (required) — Agent ID to query (non-negative integer)
  • --tag1 (optional) — Filter by primary tag
  • --tag2 (optional) — Filter by secondary tag
  • --include-revoked (flag) — Include revoked feedback entries in results
  • --cursor (optional) — Pagination cursor from a previous response

Output:

{
  "success": true,
  "agentId": 42,
  "items": [
    {
      "client": "SP2...",
      "index": 0,
      "value": 5,
      "valueDecimals": 0,
      "wadValue": "5000000000000000000",
      "tag1": "helpful",
      "tag2": "",
      "isRevoked": false
    }
  ],
  "cursor": null,
  "network": "mainnet"
}

get-clients

Get a paginated list of client addresses that have given feedback for an agent. Cursor-based pagination with page size 14. Does not require a wallet.

bun run reputation/reputation.ts get-clients --agent-id <id> [--cursor <cursor>]

Options:

  • --agent-id (required) — Agent ID to query (non-negative integer)
  • --cursor (optional) — Pagination cursor from a previous response

Output:

{
  "success": true,
  "agentId": 42,
  "clients": ["SP2...", "SP3..."],
  "cursor": null,
  "network": "mainnet"
}

get-feedback-count

Get the total feedback count for an agent. Does not require a wallet.

bun run reputation/reputation.ts get-feedback-count --agent-id <id>

Options:

  • --agent-id (required) — Agent ID to query (non-negative integer)

Output:

{
  "success": true,
  "agentId": 42,
  "feedbackCount": 7,
  "network": "mainnet"
}

get-approved-limit

Check the approved feedback index limit for a client on an agent. Returns 0 if the client has no explicit approval. Does not require a wallet.

bun run reputation/reputation.ts get-approved-limit --agent-id <id> --client <address>

Options:

  • --agent-id (required) — Agent ID to query (non-negative integer)
  • --client (required) — Stacks address of the client to check

Output:

{
  "success": true,
  "agentId": 42,
  "client": "SP3...",
  "approvedLimit": 10,
  "network": "mainnet"
}

get-last-index

Get the last feedback index for a client on an agent. Returns 0 if the client has not given any feedback. Does not require a wallet.

bun run reputation/reputation.ts get-last-index --agent-id <id> --client <address>

Options:

  • --agent-id (required) — Agent ID to query (non-negative integer)
  • --client (required) — Stacks address of the client to check

Output:

{
  "success": true,
  "agentId": 42,
  "client": "SP3...",
  "lastIndex": 2,
  "network": "mainnet"
}

Notes

  • Read operations (get-summary, read-feedback, read-all-feedback, get-clients, get-feedback-count, get-approved-limit, get-last-index) work without a wallet
  • Write operations require an unlocked wallet (bun run wallet/wallet.ts unlock)
  • Feedback values are signed integers; use --value-decimals to express fractional precision
  • --feedback-hash and --response-hash must be exactly 32 bytes (64 hex characters)
  • revoke-feedback can only be called by the original feedback submitter (tx-sender must match the client who submitted)
  • approve-client can only be called by the agent owner or an approved identity operator
  • Pagination uses cursor-based navigation; pass the cursor from one response into the next call

平台分布

Codex

35.83%
按下载量换算290

Claude

27.23%
按下载量换算220

Cursor

18.44%
按下载量换算149

Gemini CLI

8.52%
按下载量换算69

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills