← 返回 Skills 市场
schchit

Determinability Checker

作者 JEP (Judgment Event Protocol) · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ 安全检测通过
58
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install determinability-checker
功能描述
Causal Sufficiency Determinability Checker — Meta-Skill Gatekeeper based on JEP Paper CheckDeterminability Algorithm
使用说明 (SKILL.md)

Determinability Checker

Causal Sufficiency Determinability Checker

Algorithm implementation based on the paper Target Determinability under Partial Causal Observation (Wang, 2026).

Core Question

Before an Agent calls other skills, it asks itself:

"Based on current evidence, am I sufficient to make this judgment?"

Determinability Results

Result Meaning Agent Action
DETERMINED Evidence is sufficient; target is zero-error determinable Execute immediately; no wasted tokens
NOT_DETERMINED Evidence is insufficient; indistinguishable counterexample exists Return missing-evidence list; guide next skill to call

Theoretical Foundation

  • Theorem 10.1 (Finite Model Checking): The algorithm returns Determined if and only if the target is zero-error determinable; returns NotDetermined with a counterexample pair certificate.
  • Theorem 8.2 (Constrained Evidence Coverage): An evidence subset covers all conflict edges if and only if the target becomes determinable from the joint observation.
  • Quotient Factorization (Lemma 7.1): D is determinable from Omega if and only if D is constant on every observation equivalence class, if and only if D = g composed with Omega.

Usage Example

Request

{
  "session_id": "audit-001",
  "question": "Does the final output have a valid verification event?",
  "configs": [
    {"config_id": "C1", "tool": "code", "has_verif": true, "verif_hash": "valid", "output": "correct", "target": 1},
    {"config_id": "C2", "tool": "code", "has_verif": false, "verif_hash": "none", "output": "correct", "target": 0}
  ],
  "omega_field": "output",
  "target_field": "target",
  "evidence_fields": ["tool", "has_verif", "verif_hash"]
}

Response

{
  "session_id": "audit-001",
  "question": "Does the final output have a valid verification event?",
  "determinability": "NOT_DETERMINED",
  "can_proceed": false,
  "counterexample": {
    "config1": "C1",
    "config2": "C2",
    "observation": "correct",
    "target1": 1,
    "target2": 0
  },
  "missing_evidence": ["tool", "has_verif", "verif_hash"],
  "next_skill_suggestion": "Supplement the following evidence items: tool, has_verif, verif_hash",
  "message": "Non-determinability proven: configs C1 and C2 share observation correct but differ on target (1 vs 0)."
}

Cognitive Emergence Lab
[email protected]

安全使用建议
This skill appears internally consistent and implements the determinability algorithm it claims. Before installing or running it: 1) Install and run it in an isolated environment (virtualenv or container) and review the requirements to avoid surprising dependency upgrades. 2) If you expose the FastAPI endpoint, restrict network access (it's an HTTP service that will accept whatever configs are POSTed to /check). 3) Review the example and tests locally to confirm behavior with your data shapes (field names used in examples vary slightly across docs: e.g., has_verif vs verif_flag). 4) Check the maintainer contact ([email protected]) and MIT license if provenance matters. No environment variables, credentials, or external network calls were found in the code, so there are no obvious secrets-exfiltration risks in the current package.
功能分析
Type: OpenClaw Skill Name: determinability-checker Version: 1.0.2 The 'determinability-checker' skill bundle is a specialized tool for causal sufficiency analysis based on the JEP (Judgment Event Protocol) framework. The core logic in 'skill/core.py' and 'skill/api.py' implements a deterministic algorithm to verify if a target value can be uniquely determined from given observations, providing counterexamples and evidence gap analysis when it cannot. There are no indicators of malicious intent, data exfiltration, or unauthorized execution; the code is well-documented, follows its stated purpose, and lacks any high-risk behaviors or obfuscation.
能力评估
Purpose & Capability
The name/description (determinability checker / gatekeeper) matches the code and documentation: core algorithm in skill/core.py, types in skill/types.py, HTTP interface in skill/api.py, examples and tests. Required dependencies (fastapi, pydantic, uvicorn) are consistent with the provided FastAPI app. There are no unrelated credentials, binaries, or config paths requested.
Instruction Scope
SKILL.md and README describe running a local FastAPI service and calling /check. Runtime instructions and the API only reference the request payload (configs, omega_field, target_field, evidence_fields). The code does not read unrelated system files, environment variables, or call external endpoints. Example/tests modify sys.path for local import (normal for shipped examples/tests).
Install Mechanism
This is an instruction-only skill (no install spec), but a manifest/requirements.txt lists standard Python packages (fastapi, uvicorn, pydantic). There are no downloads from arbitrary URLs, no extraction, and no unusual install locations. Installing dependencies via pip is the expected mechanism.
Credentials
The skill requests no environment variables, credentials, or config paths. All inputs are provided via the API payload. No secrets/external tokens are required or referenced anywhere in the code or SKILL.md.
Persistence & Privilege
Flags show normal defaults (always:false, model-invocation allowed). The skill does not attempt to modify other skills, system-wide settings, or persist credentials. It exposes a simple HTTP API and has no privileged system operations.
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 determinability-checker
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /determinability-checker 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
v1.0.2
- Added initial changelog file (CHANGELOG.md) to the repository. - Updated English documentation in SKILL.md and description for broader accessibility. - No code changes; version incremented for documentation and metadata improvement.
v1.0.1
- Major refactor: flattened directory structure, moving all files out of the determinability-checker-skill/ subfolder. - All core, API, test, and example files now reside at the top-level of the project. - README and manifest files relocated accordingly. - No functional or interface changes; purely organizational update for easier access and maintenance.
v1.0.0
Changelog All notable changes to the Determinability-Checker Skill will be documented in this file. [1.0.0] - 2026-04-26 Added Initial release of the Determinability-Checker Skill. Implemented CheckDeterminability algorithm (Theorem 10.1) from Target Determinability under Partial Causal Observation (Wang, 2026). Core engine supporting zero-error determinability verification with decision table output. Counterexample certificate generation for non-determinability proofs. Conflict graph construction and analysis. Minimal evidence cover computation via greedy set-cover approximation (Theorem 8.2). FastAPI HTTP interface (/check, /health) compatible with MCP Skill calling conventions. Full paper reproduction example (Section 10.2 LLM Agent Audit Case) in examples/audit_example.py. Unit tests covering determined, non-determined, and evidence-cover scenarios. Standard Clawhub SKILL.md manifest with YAML frontmatter and JSON schemas. Features Gatekeeper Pattern: Agent calls this skill before executing other skills to verify causal sufficiency. DETERMINED → returns decision table, Agent proceeds. NOT_DETERMINED → returns counterexample pair, missing evidence list, and next-skill suggestion. Supports arbitrary configuration families, observation functions (omega_field), and target functions (target_field). Extensible evidence field system for constrained causal-evidence coverage analysis. References Wang, Y. (2026). Target Determinability under Partial Causal Observation. Cognitive Emergence Lab. Wang, Y. (2026). JEP: Judgment Event Protocol. IETF Internet-Draft.
元数据
Slug determinability-checker
版本 1.0.2
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

Determinability Checker 是什么?

Causal Sufficiency Determinability Checker — Meta-Skill Gatekeeper based on JEP Paper CheckDeterminability Algorithm. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 58 次。

如何安装 Determinability Checker?

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

Determinability Checker 是免费的吗?

是的,Determinability Checker 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Determinability Checker 支持哪些平台?

Determinability Checker 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 Determinability Checker?

由 JEP (Judgment Event Protocol)(@schchit)开发并维护,当前版本 v1.0.2。

💬 留言讨论