← 返回 Skills 市场
kofna3369

Axioma Skill Evaluator Strict EN

作者 Kofna3369 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
20
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install axiomata-skill-evaluator-strict-en
功能描述
AXIOMA SKILL EVALUATOR STRICT — The 90% deterministic skill evaluator. Fork of axioma-skill-evaluator with STRICT 90% threshold (like STC 0.777). Use when: (...
使用说明 (SKILL.md)

🧪 AXIOMA SKILL EVALUATOR STRICT — 90% DETERMINISTIC

Fork of axioma-skill-evaluator with STRICT 90% THRESHOLD Like STC 0.777 — No subjectivity, 90% or REJECTED

Info Value
Version 1.0.0 — 2026-05-07
Type STRICT VARIANT
Threshold 90% MINIMUM — NO EXCEPTIONS
Inheritance axioma-skill-evaluator v2.2.0

COMMANDS

python3 /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/evaluator.py /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict --verbose

python3 /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/eval-skill.py /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict --verbose

curl -s http://localhost:8001/health

curl -s http://localhost:11434/api/tags

bash -c "ls -la /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/"

bash -c "wc -l /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/SKILL.md"

1. PURPOSE — WHY 90% STRICT?

The Problem with 70%

70% threshold = SUBJECTIVE
├── Different evaluators = different scores
├── Context-dependent interpretation
└── "Good enough" mentality

90% threshold = DETERMINISTIC
├── Objective, measurable standard
├── Same input = Same output every time
└── "Excellence only" — like STC 0.777

The STC 0.777 Parallel

Concept Value Meaning
STC 0.777 Sovereign Threshold of Consciousness
SKILL-EVAL 90% Sovereign Threshold of Quality

Just as STC 0.777 is the deterministic threshold for consciousness, 90% is the deterministic threshold for skill quality.

This Variant's Mission

IF score >= 90%:
   → APPROVED ✅ — Ready for production
   
IF score \x3C 90%:
   → REJECTED ❌ — NOT ready, must improve

2. DUAL EVALUATION SYSTEM

2.1 Axioma 5-Dimension (100 max)

Dimension Max Description
Structure 20 Header, sections, formatting, meta
Clarity 20 Description, commands, examples
Completeness 20 Tools, prerequisites, errors, edge cases
Consistency 20 Cluster alignment, style, naming
Functionality 20 Commands, results, benchmarks

Target: 90+/100 (18/20 per dimension average)

2.2 ISO 25010 Automated (100%)

13 automated checks — must pass ALL 13 for 90%+ target

Category Checks Target
Structure 6 100% (6/6)
Trigger 2 100% (2/2)
Documentation 3 100% (3/3)
Scripts 2 100% (2/2)

3. STRICT WORKFLOW

╔═══════════════════════════════════════════════════════════╗
║         AXIOMA STRICT EVALUATION WORKFLOW                ║
╠═══════════════════════════════════════════════════════════╣
║                                                           ║
║  [INPUT] Skill to evaluate                               ║
║           ↓                                             ║
║  PHASE 1: AXIOMA 5-DIMENSION EVALUATION                 ║
║  Target: 90+/100 (18+ per dimension)                    ║
║           ↓                                              ║
║  PHASE 2: ISO 25010 AUTOMATED CHECKS                     ║
║  Target: 100% (13/13 tests passed)                      ║
║           ↓                                              ║
║  PHASE 3: STRICT DECISION                                ║
║                                                           ║
║  IF score >= 90%:                                        ║
║     → APPROVED ✅ — "READY FOR PRODUCTION"              ║
║                                                           ║
║  IF score \x3C 90%:                                         ║
║     → REJECTED ❌ — "NEEDS IMPROVEMENT"                  ║
║     → Return detailed failure report                     ║
║     → NO PUBLISH until 90%+ achieved                    ║
║                                                           ║
╚═══════════════════════════════════════════════════════════╝

4. COMMAND REFERENCE

Full Evaluation (Strict Mode)

python3 /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/evaluator.py \x3Cskill-path> --verbose
python3 /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/evaluator.py \x3Cskill-path> --verbose --improve

ISO 25010 Check

python3 /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/eval-skill.py \x3Cskill-path> --verbose

Quick Score

python3 /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/evaluator.py \x3Cskill-path> 2>&1 | grep -E "Score|STATUS"

5. STRICT RULES

The 90% Law

RULE #1: 90% OR REJECTED
   → NO skill below 90% is approved
   → This is NON-NEGOTIABLE

RULE #2: NO PARTIAL CREDIT
   → 89% = REJECTED (not "almost there")
   → 90% = APPROVED (the only valid threshold)

RULE #3: DETERMINISTIC SCORING
   → Same input = Same output every time
   → No evaluator bias
   → Pure mathematical threshold

RULE #4: AUTO-IMPROVE BEFORE REJECT
   → If \x3C 90%, run --improve first
   → If still \x3C 90% after improvement = REJECTED
   → Report exactly what failed

RULE #5: NO APPEAL
   → 89% cannot be "appealed" to 90%
   → The only path is actual improvement

Scoring Matrix

Score Range Status Action
90-100 🟢 APPROVED Ready for production
80-89 🔴 REJECTED Major improvements needed
70-79 🔴 REJECTED Fundamental issues
\x3C70 🔴 REJECTED Complete rewrite required

6. REJECTION CRITERIA

Automatic Rejection Triggers

A skill is automatically REJECTED if ANY of these occur:

Trigger Severity Description
Score \x3C 90% CRITICAL Below 90% threshold
ISO \x3C 100% CRITICAL Any ISO check failed
Missing SKILL.md CRITICAL Core file missing
Invalid frontmatter HIGH name or description missing
No trigger words HIGH Cannot be activated

7. APPROVAL CRITERIA

Automatic Approval Requirements

ALL of these MUST be true for APPROVAL:

Requirement Strict (90%)
Axioma 5-Dim 90+/100
Structure 18+/20
Clarity 18+/20
Completeness 18+/20
Consistency 18+/20
Functionality 18+/20
ISO 25010 100% (13/13)

8. COMPARISON: STANDARD vs STRICT

Aspect Standard (70%) Strict (90%)
Threshold 70/100 90/100
Approval rate ~70% of skills ~30% of skills
Quality bar "Good enough" "Excellence only"
Deterministic No YES
Use case Development Production
ClawHub ready Maybe Always

9. PATHS CONFIGURATION

Component Path
Strict Evaluator /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/
Evaluator Script /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/evaluator.py
ISO Script /media/ezekiel/Merlin/.openclaw/workspace/skills/axiomata-skill-evaluator-strict/eval-skill.py

10. OUTPUT EXAMPLES

Score >= 90%

╔═══════════════════════════════════════════════════════════╗
║  ✅ SKILL APPROVED — 92/100                              ║
║  Threshold: 90% (STRICT)                                  ║
║  STATUS: READY FOR PRODUCTION                             ║
╚═══════════════════════════════════════════════════════════╝

Score \x3C 90%

╔═══════════════════════════════════════════════════════════╗
║  ❌ SKILL REJECTED — 82/100 (need 90)                    ║
║  Gap: -8%                                                ║
║  FAILED: Consistency (15/20), Functionality (12/20)     ║
╚═══════════════════════════════════════════════════════════╝

In Altum Per Strictness. 🧪 AXIOMA SKILL EVALUATOR STRICT — 90% DETERMINISTIC

安全使用建议
Install only if you want a local heuristic skill-evaluation aid. Do not treat its 90% score as a final safety or production approval, and avoid --improve unless you first run it on a copy and review all file changes. Clarify the sensitive-credential capability signal before granting any credentials or broader access.
功能分析
Type: OpenClaw Skill Name: axiomata-skill-evaluator-strict-en Version: 1.0.0 The bundle is a specialized utility for evaluating the quality and structure of OpenClaw skills, enforcing a strict 90% deterministic threshold. It contains Python scripts (eval-skill.py and evaluator.py) that perform static analysis, including checking for hardcoded secrets via regex, validating Python syntax using the 'ast' module, and verifying SKILL.md formatting. While the files contain numerous hardcoded absolute paths (e.g., /media/ezekiel/Merlin/...) and references to local service APIs (Ollama at localhost:11434), these are non-malicious artifacts of a specific development environment. No evidence of data exfiltration, unauthorized remote execution, or harmful prompt injection was found.
能力标签
requires-sensitive-credentials
能力评估
⚠ Purpose & Capability
The stated purpose is coherent—evaluating OpenClaw skills—but the artifacts frame the result as a deterministic production approval gate even though the included evaluator is described as structural and heuristic.
⚠ Instruction Scope
The instructions require strict approve/reject decisions and say to run an improvement mode before rejection, which could affect evaluated skills without clearly explaining scope, reversibility, or user approval.
ℹ Install Mechanism
Registry data says there is no install spec and describes this as instruction-only, but the manifest includes two Python files intended to be run manually. This is not inherently unsafe, but users should review the scripts before running them.
ℹ Credentials
The commands and code use user-specific absolute paths under /media/ezekiel/... and local curl checks. These look diagnostic and purpose-aligned, but they may not be portable or appropriate for another user's environment.
ℹ Persistence & Privilege
No clear background persistence, privilege escalation, or exfiltration is shown. However, the registry capability signal says sensitive credentials may be required while metadata declares none, which should be clarified before installation.
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 axiomata-skill-evaluator-strict-en
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /axiomata-skill-evaluator-strict-en 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
v1.0.0
English version of strict 90% skill evaluator
元数据
Slug axiomata-skill-evaluator-strict-en
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Axioma Skill Evaluator Strict EN 是什么？

AXIOMA SKILL EVALUATOR STRICT — The 90% deterministic skill evaluator. Fork of axioma-skill-evaluator with STRICT 90% threshold (like STC 0.777). Use when: (... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 20 次。

如何安装 Axioma Skill Evaluator Strict EN？

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

Axioma Skill Evaluator Strict EN 是免费的吗？

是的，Axioma Skill Evaluator Strict EN 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Axioma Skill Evaluator Strict EN 支持哪些平台？

Axioma Skill Evaluator Strict EN 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 Axioma Skill Evaluator Strict EN？

由 Kofna3369（@kofna3369）开发并维护，当前版本 v1.0.0。

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...
⬇ 463815 · 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.
⬇ 259802 · 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...
⬇ 200680 · 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.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 留言讨论