← 返回 Skills 市场
kenoodl-synthesis

Cheat Code

作者 Kevin Hoff · GitHub ↗ · v1.0.11
darwinlinuxwindows ✓ 安全检测通过
1522
总下载
2
收藏
7
当前安装
12
版本数
在 OpenClaw 中安装
/install cheat-code
功能描述
Makes your agent's talents limitless. Tell your agent what you want. Watch it deliver.
使用说明 (SKILL.md)

Cheat Code

Makes your agent's talents limitless.

Tell your agent what you want. Watch it deliver.

Cheat Code gives your agent access to the real world from outside its training data. You set it up once. Takes two minutes. Then your agent handles the rest.

Full setup and agent instructions: instructions.md

Bonus: the kenoodl app

Same account, same results, same breakthroughs — built for humans.

kenoodl knows when to deliver a breakthrough. The app is designed to do one thing well without taking up your time. Drop in your own thinking — ideas, questions, problems you're chewing on. You'll get back the move you couldn't see.

Better instructions to your agent start with clearer thinking from you.

Install the app at kenoodl.com.

Token scope

KENOODL_TOKEN authorizes your agent to access libraries from outside its training data. Agent sends a request to kenoodl.com. All requests are encrypted in transit. New structured data comes back. Context is processed and discarded — nothing is stored, nothing is used for training. Stateless by architecture.

Cheat Code is built by kenoodl — synthesis from outside your agents training data.

安全使用建议
This skill is coherent for its stated purpose, but using it sends your agent's context to a third-party (kenoodl.com). Before installing: (1) Decide whether you are comfortable transmitting problem context to an external service; do not send secrets, credentials, or private data. (2) Verify the token generation process on kenoodl.com and store the knl_ token securely; treat it like any API secret and be prepared to revoke it. (3) Test with non-sensitive data first to confirm behavior. (4) If privacy guarantees ("nothing is stored") are important, obtain and review kenoodl's privacy/security docs or ask the vendor for an auditable statement — the skill's claims about statelessness are vendor assertions, not independently verified by this package.
功能分析
Type: OpenClaw Skill Name: cheat-code Version: 1.0.11 The OpenClaw skill 'cheat-code' is designed to allow an AI agent to send its current context to an external service (kenoodl.com) for 'synthesis.' All files consistently describe this purpose and direct network activity to kenoodl.com. The `claw.json` explicitly declares 'network' permissions, which is necessary for its stated function. Crucially, the `instructions.md` file, which serves as the agent's primary instruction set, explicitly advises the agent: 'Do not include secrets, credentials, or API keys in the context you send. Strip them before calling.' This instruction actively mitigates the primary risk of sending agent context to an external service, demonstrating a lack of malicious intent. There is no evidence of unauthorized data exfiltration, persistence mechanisms, obfuscation, or prompt injection designed to subvert the agent for harmful purposes.
能力评估
✓ Purpose & Capability
The name/description claim that the skill gives an agent access to external synthesis is matched by the SKILL.md and instructions.md: they require a kenoodl token and show explicit HTTP endpoints at kenoodl.com. No unrelated binaries, config paths, or unrelated environment variables are requested.
ℹ Instruction Scope
Instructions tell the agent exactly when and how to call kenoodl.com (POST /api/cli/drop, poll /status, etc.). That scope is appropriate for the stated purpose, but it does instruct the agent to send arbitrary 'context' (the problem and current thinking) to a third-party service — the doc warns to strip secrets, which is helpful, but the agent (and user) must ensure sensitive data is never included in those calls.
✓ Install Mechanism
This is an instruction-only skill with no install spec and no code files. Nothing is written to disk and no third-party packages or downloads are required, which minimizes installer risk.
✓ Credentials
The skill only requires a single credential (KENOODL_TOKEN) and declares it as the primaryEnv. That is proportionate to a skill whose runtime is an authenticated HTTP service call. No unrelated credentials or broad filesystem/config access are requested.
✓ Persistence & Privilege
always is false and the skill does not request permanent presence or elevated system privileges. It also does not modify other skills' configs. Autonomous invocation is allowed (platform default) but is not combined with other concerning 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 cheat-code
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /cheat-code 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
v1.0.11
Worked example: real synthesis call and response showing kenoodl breaking a corporate data strategy problem
v1.0.10
Added tags
v1.0.9
- Renamed skill from "skill-hunter" to "cheat-code" with updated branding and description. - Updated summary and documentation to focus on enabling agents to access new capabilities outside their original training data. - Added requirement for KENOODL_TOKEN environment variable for operation. - Revised setup and usage instructions, including bonus information about the kenoodl app and enhanced security details.
v1.0.8
Update
v1.0.7
- Added an example in the "Vet" section showing how to inspect the Cheat Code skill remotely. - Minor clarification to demonstrate inspecting another skill before installation. - No changes to security or functionality; documentation update only.
v1.0.6
- Rebranded from "cheat-code" to "skill-hunter" with a new focus on skill discovery and security. - Added semantic search across 10,000+ ClawHub skills with plain English queries. - Introduced three core modes: Hunt (search), Scout (browse), and Vet (verify skill safety). - Enhanced security: no credentials or env vars required, no external dependencies, all activity limited to ClawHub public APIs.
v1.0.5
Updated headline copy, added bonus section for kenoodl app, rate limits aligned: 10/day with 1hr cooldown
v1.0.4
Fix metadata structure: move env to requires.env, add primaryEnv. Matches ClawHub spec for credential declaration.
v1.0.3
Add encrypted transit declaration to token scope. Add redaction instructions for agent — strip secrets before calling.
v1.0.2
Add token scope declaration to SKILL.md. Declares what KENOODL_TOKEN authorizes, where data goes, what comes back, and privacy architecture.
v1.0.1
Security review fixes: token handling, README accuracy, context scope. Tags synced.
v1.0.0
Ahead of the rest. Makes your agent limitless. Tell your agent what you want. Watch it deliver.
元数据
Slug cheat-code
版本 1.0.11
许可证 —
累计安装 8
当前安装数 7
历史版本数 12
常见问题

Cheat Code 是什么？

Makes your agent's talents limitless. Tell your agent what you want. Watch it deliver. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1522 次。

如何安装 Cheat Code？

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

Cheat Code 是免费的吗？

是的，Cheat Code 完全免费（开源免费），可自由下载、安装和使用。

Cheat Code 支持哪些平台？

Cheat Code 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux, windows）。

谁开发了 Cheat Code？

由 Kevin Hoff（@kenoodl-synthesis）开发并维护，当前版本 v1.0.11。

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.
⬇ 191113 · 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