Real Skill packageSource verifiedClawHub registry

Skill Evolution

技能进化（知行环，英文 id `skill-evolution`）——Agent 经验沉淀与自改进闭环框架，把 WikiSkill（arXiv:2608.27454）的经验存储机制与 RSI 路线图（arXiv:2609.11873）的能力判据合成为一条可运行闭环：HCI 选域 → 三层记忆沉淀 → 原子化提议 → 四大追问门控 → 可回滚迭代 → 自主权升阶。支持 WorkBuddy / CodeBuddy / Claude Code / Codex 四平台与 Windows / Linux / macOS。当用户报出「技能进化」或别号「知行环」，或要求经验复盘、记录轨迹、能力评估、自改进闭环设计、自主性分级，或引用 RSI / HCI / WikiSkill 相关概念时触发。

Identity and source

Publisher attributionxxoytregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 60% rule confidence
Package forminstruction with code21 recorded files
Canonical sourceClawHub registryclawhub:xxoyt:skill-evolution-2
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/23/2026.claude/skills/skill-evolution

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/23/2026.agents/skills/skill-evolution

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/23/2026skills/skill-evolution

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @xxoyt/skill-evolution-2
clawhub inspect @xxoyt/skill-evolution-2 --version 0.1.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
21 / 21 inspected as text
Checked
9/23/2026, 1:28:05 PM
Scanner
0.1.3
Policy
1.0.3
4 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
4 dependency and API indicators
  • api: arxiv.org
  • api: clawhub.ai
  • api: github.com
  • api: theseus-labs-rsi.github.io
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/23/2026, 1:31:10 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:fb9247ccce757e12c53ed0a74bccd13c90cb9b95bc6aa825b82092cbbd151dc4
Show up to 21 recorded paths
  • assets/hooks/claude-code-settings.json
  • assets/hooks/claude-code-settings.windows.json
  • README.md
  • references/AGENTS.template.md
  • references/anti-patterns.md
  • references/automation.md
  • references/CLAUDE.template.md
  • references/design-playbook.md
  • references/platforms.md
  • references/rsi-framework.md
  • references/templates.md
  • references/workflow.md
  • scripts/install.py
  • scripts/selfcheck.py
  • scripts/wiki_init.ps1
  • scripts/wiki_init.py
  • scripts/wiki_init.sh
  • scripts/wiki_remind.py
  • scripts/wiki_remind.sh
  • skill-card.md
  • SKILL.md

Source changelog

Skill-evolution-2 v0.1.0 changelog - Initial release of 技能进化（知行环）, a closed-loop agent framework integrating WikiSkill's experience storage with RSI roadmap's evaluation criteria. - Triggers on keywords "技能进化" / "知行环", or user requests for experience review, trajectory logging, capability assessment, closed-loop design, and related RSI/HCI/WikiSkill concepts. - Supports WorkBuddy, CodeBuddy, Claude Code, and Codex across Windows, Linux, and macOS. - Implements seven unified closed-loop steps: domain selection, execution logging, pattern extraction, atomic skill proposal, multi-criteria gating, rollback/adoption, and autonomy escalation (L1–L5). - Enforces strict role separation to prevent execution agents from accessing accumulated wiki knowledge during active tasks. - Provides command triggers for each step and maintains a structured project wiki for skills and patterns.