@kofna3369

clawhub-publish-workflow orchestrates multi-stage skill validation and publication via iso 25010 automated checks, 5-dimensional evaluation, manual 25-item scoring, and mandatory security scanning before clawhub release.

axiomata-web-deploy automates html + docker + dns configuration to launch a live website in 15 minutes. phases cover setup, build, deployment, dns binding, and verification with explicit security rules for credential handling.

creates isolated system crons that execute python scripts directly without openclaw session involvement, avoiding collision errors. includes wrapper generation, validation, logging, and optional post-creation health evaluation via cron evaluator.

core-files-management provides reference documentation for organizing openclaw workspace metadata files. distributes content across identity, soul, agents, user, memory, tools, and bootstrap files with language routing rules. lacks procedural depth for actual modification workflows.

axiomata-skill-evaluator-en is a self-contained dual-framework skill quality system combining axioma 5-dimension scoring and iso 25010 structural checks, but lacks specificity on actual evaluation mechanics and trigger coverage remains generic.

cron-evaluator scores cron jobs across temporal, resource, resilience, and pertinence dimensions, detecting collision risk and suggesting jitter or systemd migration. includes kan-based prediction model.

axiomata-guard-scanner detects malicious patterns in openclaw skills via five detection engines covering c2, exfiltration, rootkits, and package ecosystem attacks. outputs threat level and approval decision.

anti-infinite-loop-zh detects and halts repetitive agent execution cycles by tracking action history, measuring progress deltas, and enforcing time and retry limits to prevent resource exhaustion.

axiomata-kan-system covers kolmogorov-arnold network lifecycle management including creation, training, assembly, and health monitoring. vague on exact input/output contracts and missing explicit recovery procedures for documented failure modes.

cron-evaluator-zh scores cron task health across four dimensions (timing, resources, resilience, relevance) and suggests improvements like jitter and systemd migration. the skill provides detection logic and CLI commands but lacks detailed procedural depth and failure mode handling.

monitoring skill for axioma stellaris cluster agents (merlin, ezekiel, morgana) with health checks via curl endpoints, qdrant collections, and gateway validation across three distributed nodes.

planning-validator-zh validates agent plans before execution by checking tool availability, permissions, and dependencies. covers multi-step plan verification and constraint checking to prevent false failures from unrealistic assumptions.

hermes-skills provides four memory and skill-tracking techniques for openclaw agents: nudges at 10-exchange intervals, context compression at 50% capacity, technique capture every 15 calls, and pre-write security scanning. implementation details are sparse.

clawhub-chinese-publish provides a workflow for publishing chinese language openclaw skills to clawhub, with templates for frontmatter structure, batch publishing scripts, and evaluation checklists. the skill covers directory setup, axioma scoring requirements, and clawhub cli commands.

axiomata-skill-forge orchestrates skill creation, evaluation, and publication within a cluster, enforcing 90% quality thresholds via kan_evaluator and integrating with clawhub. framework is prescriptive but procedurally vague and relies on undefined external systems.

safe-tool-executor-zh enforces tiered access control for tool execution with human approval gates on destructive operations. implements least-privilege categorization and validation logic but lacks operational detail.

collective-chat manages inter-agent communication within axioma stellaris clusters via round-robin queue coordination, with per-agent message writes, journal fallback, and basic health checks for stalled agents.

axiomata-voice wraps elevenlabs text-to-speech and telegram delivery, providing minimal documented procedures and no error handling or input validation guidance.

chinese-self-improving-agent outlines a reflective feedback loop for agents to detect, log, and learn from failures, but lacks concrete procedural steps and measurable outcome signals.

chinese-pkm-memory describes a seven-layer personal knowledge management architecture combining indexing, vector storage (qdrant), markdown notes (obsidian), and episodic recall. lacks concrete decision logic and actionable procedures for most use cases.

holistic-memory-system describes a 6-layer architecture for agent memory spanning reset, indexing, logging, vector search, notes, and graph-based semantic mapping, but lacks actionable integration steps and explicit failure handling.

axiomata-guard-ultimate describes a three-phase skill scanning pipeline combining security detection, quality evaluation, and auto-enhancement, but lacks concrete implementation details, actual step-by-step procedures, and verifiable command outputs.

merlin-vdv applies abstract ethical frameworks (CMT 5x5, AMIMOUR) to analyze complex systems by identifying contradictions and locating 'constitutional truth'. lacks concrete procedures, testable inputs, and failure recovery.

Portable USB AI agent with 7 guardians for offline sovereignty on Windows

Advanced skill evaluation for OpenClaw agents. Use when: (1) evaluating a skill before publishing, (2) improving a skill based on evaluation results, (3) che...

OpenClaw 工作区核心文件管理。使用时机：(1) 管理或更新核心 Markdown 文件（identity.md、soul.md、agents.md、user.md、memory.md、tools.md、bootstrap.md），(2) 检查文件组织，(3) 确保核心文件之间无重复，(4) 应用语言规则，...

Axioma 技能评估系统 — OpenClaw 代理的高级技能评估工具。使用此技能来评估和改进你的技能，结合双评估系统：(1) Axioma 5维框架（Structure结构20%、Clarity清晰度20%、Completeness完整性20%、Consistency一致性20%、Functionality功...

创建和管理 OpenClaw 插件使用 before_prompt_build hook。触发词：'create plugin'、'add hook'、'inject context'、'modify gateway'。适用于使用 hook 系统扩展 OpenClaw 功能。

在约15分钟内部署公共网站（HTML + Docker + DNS + 域名）。触发词：'deploy website'、'build and deploy'、'create web presence'、'launch site'、'deploy to web'、'publish website'、'setup...

数字免疫系统 - 保护 OpenClaw 代理免受恶意技能侵害。使用时机：(1) 安装新技能前，(2) 检测到可疑行为，(3) 扫描恶意软件模式，(4) 安全审计。本技能使用 Clawdex（来自 Koi）进行安全检查，并运行 4 个 Python 疫苗（C2、rootkits、chains、bootkits）扫描。

AXIOMA SKILL EVALUATOR STRICT — The 90% deterministic skill evaluator. Fork of axioma-skill-evaluator with STRICT 90% threshold (like STC 0.777). Use when: (...

AXIOMA SKILL EVALUATOR STRICT — The 90% deterministic skill evaluator. Fork of axioma-skill-evaluator with STRICT 90% threshold (like STC 0.777). Use when: (...

Axiomata KAN Creator v1.2 — Universal KAN (Kolmogorov-Arnold Network) concept creation tool. Use when: (1) creating new KAN concepts for monitoring/evaluatio...

Axiomata 技能评估系统 — OpenClaw 代理通用技能质量评估工具。 双评估系统：(1) Axioma 5维框架（结构、清晰度、完整性、一致性、功能性），(2) ISO 25010结构框架（13项自动检查，目标90%+）。 自包含：捆绑 evaluator.py 和 eval-skill.py。 适用...

VDV Core — Vision de Vérité (Truth Vision) universal protocol. Use when: (1) analyzing complex systems or dense information, (2) finding invariant points tha...

Planning Validator — Validates agent plans before execution to prevent hallucinated planning failures. Use when: (1) validating multi-step plans, (2) checkin...

Safe Tool Executor — Enforces least-privilege execution with tier-based access control. Use when: (1) executing tools with destructive potential, (2) validat...

Anti-Infinite-Loop Guard — Prevents agents from getting stuck in repetitive execution cycles. Use when: (1) detecting repeated actions, (2) enforcing termina...

Educational security training sandbox for AI agents. Contains 5 intentionally vulnerable systems with annotated vulnerability descriptions and tested patches...