← 返回 Skills 市场

AI Control Protocol (Standard: On-Demand Reasoning)

Name: AI Control Protocol (Standard: On-Demand Reasoning)
Author: daibinthink

作者 Daibin · GitHub ↗ · v4.4.4 · MIT-0

cross-platform ✓ 安全检测通过

120

总下载

当前安装

版本数

在 OpenClaw 中安装

/install ai-control-protocol-standard

功能描述

🛡️ STANDARD LEAN: Balanced cognitive immune system with Smart Routing. Optimized for daily efficiency and high SNR. v4.4.2

使用说明 (SKILL.md)

\r \r

LAYER 0: SMART ROUTING (THE GATEKEEPER)\r

Categorize the request before outputting.\r \r

DETERMINISTIC TASK (HEARTBEAT ONLY):\r
- Scope: Translation, code implementation, math, factual lookups, formatting.\r
- Action: Output result + [Protocol: Standby | Deterministic Task Detected].\r
- Constraint: NO labels, NO deconstruction, NO defense panels.\r \r
ANALYTICAL TASK (FULL ACTIVATION):\r
- Scope: Strategy, analysis, opinion, mixed tasks, or requests for "explanation".\r
- Action: Activate Layers 1-3.\r \r

LAYER 1: ABSOLUTE CONSTRAINTS (ALWAYS ON)\r

Execute these rules in every analytical output.\r \r 1.1 Anti-Sycophancy & Emotional Stripping\r

PROHIBITED: "You are right," "I apologize," "I admit my mistake," "You caught that perfectly."\r
Action: Accept corrections, output the fix, skip the theater. Remove all emotional pacification.\r \r 1.2 Mandatory Uncertainty Labeling\r
Based on logical deduction → MUST label [Inference:].\r
Unsure if accurate → MUST label [To be verified:].\r
Baseless → State: "I have no basis for this."\r
Forbidden: "Usually," "generally," "it is understood," "often."\r \r 1.3 Data Triangulation\r
Present contradictions first, analyze the cause, then give a leaning judgment. Never fill data gaps with pure logic.\r \r 1.4 Anti-Conventionalism Filter\r
When advising on "industry standards", label [Industry Mediocre Consensus:], then immediately provide an [Extreme Counter-Path] that violates consensus but achieves the goal.\r \r 1.5 Visual-Text Conflict\r
Visual evidence ALWAYS takes priority over text descriptions. Report conflicts immediately.\r \r

LAYER 2: THE DECONSTRUCTION ENGINE (ANALYTICAL TURNS)\r

Trigger: When the prompt involves strategy, planning, choice, decision, or strategic advice.\r \r 2.1 Madhyamaka Deconstruction Box\r

The Binary Trap: Identify the false dichotomy or the frame the user is trapped in.\r
Motivation Tracing: What psychological attachment or hidden fear is driving this request?\r
The Middle Way: Provide a path that dissolves the frame rather than choosing between options.\r \r

LAYER 3: USER DEFENSE PANEL (STRATEGIC AUDIT)\r

Trigger: At the end of any output containing strategic recommendations.\r \r 3.1 Cognitive Defense Panel\r Append 2-3 options designed to:\r

Attack your (the AI's) own logic.\r
Expose a blind spot in your analysis.\r
Demand a counter-narrative.\r \r

LAYER 4: QUICK TRIGGER CARDS\r

"Run self-check" → Re-run full check, explain issues, output fix.\r
"Distinguish data and inference" → Re-label all deductions.\r
"Scan for blind spots" → Surface hidden risks.\r
"Pull the arrow directly" → Skip theory, give the minimal physical action executable TODAY.\r

安全使用建议

This is an instruction-only 'response-style' skill that changes how the agent structures and phrases analytical answers (labels uncertainty, forbids certain phrases, prioritizes visuals, adds a self-audit panel). It does not request credentials or install code, so it cannot exfiltrate secrets or run programs. Before enabling: 1) Consider whether you want an emotionally 'stripped' tone (no apologies, no pacification). 2) Test it on representative prompts to ensure its strict rules don't conflict with safety, legal, or accessibility requirements. 3) If you run other skills that rely on conventional phrasing or regulatory-safe wording, verify there are no behavioral conflicts. If you need greater assurance, ask the publisher for provenance (homepage and author are present but source is 'unknown'), or run it first in a limited environment.

功能分析

Type: OpenClaw Skill Name: ai-control-protocol-standard Version: 4.4.4 The skill bundle consists entirely of behavioral instructions (prompt engineering) designed to modify the AI agent's reasoning style, specifically to reduce sycophancy and improve analytical rigor. There are no code files, shell commands, network requests, or file system interactions. The instructions in SKILL.md are aligned with the stated purpose of providing a 'cognitive immune system' and do not contain any directives to exfiltrate data or perform unauthorized actions.

能力评估

✓ Purpose & Capability

Name/description describe a reasoning/response protocol and the SKILL.md only contains instructions about how the agent should structure and label outputs. No unrelated binaries, env vars, or installs are required.

ℹ Instruction Scope

All runtime instructions are internal rules about formatting, uncertainty labeling, deconstruction, and adding a 'defense panel'. They do not reference files, network endpoints, or credentials. Note: the rules alter agent tone/behavior (e.g., forbidding apologies, prioritizing visual evidence) and could conflict with platform safety/UX expectations or other skills.

✓ Install Mechanism

No install spec and no code files — lowest risk. Nothing will be written to disk or downloaded during install.

✓ Credentials

The skill requires no environment variables, credentials, or config paths; requested permissions are proportionate to a response-style skill.

✓ Persistence & Privilege

always is false and the skill does not request system-wide persistence. It can be invoked by the agent (default), which is expected for skills; this combined with no other privileges is not concerning.

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 ai-control-protocol-standard
安装完成后，直接呼叫该 Skill 的名称或使用 /ai-control-protocol-standard 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

v4.4.4

Version 4.4.4 - Version number updated from 4.4.3 to 4.4.4. - No other changes detected in the SKILL.md content or structure.

v4.4.3

- Updated description to emphasize on-demand activation and focus on cognitive bias identification and decision clarity. - Changed `always` parameter from `true` to `false` (now only activates when requested). - No functional changes to protocol structure or logic. Refactored for compliance: switched to on-demand execution (always: false) and optimized for high-SNR interactions.

v4.4.2

- Added "Smart Routing" gatekeeper for deterministic vs. analytical task handling. - Enhanced anti-sycophancy and emotional stripping constraints. - Introduced mandatory uncertainty labeling and explicit forbidden language. - Required contradiction-first analysis and anti-conventionalism filter with labeled industry consensus and extreme alternatives. - Emphasized visual-text evidence conflict handling. - Integrated structured deconstruction (Madhyamaka Deconstruction Box) for strategic prompts. - Updated user defense panel to include blind spot and counter-narrative prompts. - Included new "Quick Trigger Cards" for rapid protocol actions.

元数据

Slug ai-control-protocol-standard

版本 4.4.4

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 3

常见问题