.claude/skills/self-improving-agentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
记录错误、纠正、能力缺口与最佳实践,形成可复用的持续改进闭环。V2 = 八步学习法 + LLM 语义分析 + OpenSpace 自动维护。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/self-improving-agentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/self-improving-agentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/self-improving-agentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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 @147258xuan/self-improving-agent-nextclawhub inspect @147258xuan/self-improving-agent-next --version 0.1.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
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.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:e8ac6b96f3894606d2f29cf0c3ef034c4f178c208fbb44f81e0c9114cf0e9938_meta.jsonassets/LEARNINGS.mdassets/SKILL-TEMPLATE.mdhooks/openclaw/handler.jshooks/openclaw/handler.tshooks/openclaw/HOOK.mdreferences/examples.mdreferences/hooks-setup.mdreferences/openclaw-integration.mdscripts/activator.shscripts/error-detector.shscripts/extract-skill.shskill-card.mdSKILL-V2.mdSKILL.mdSelf-Improving Agent 0.1.0 introduces a V2 learning and maintenance workflow. - Replaces the basic logging guide with an eight-step loop: precheck, record, report, measure, feedback, version, archive, and expire. - Adds safeguards for promoting lessons, preventing recurring errors, and interpreting V1 precheck and metrics results. - Defines V2 workflows for semantic prechecks, recording, feedback, metrics, deduplication, and archive review. - Adds inventory limits, OpenSpace maintenance guidance, and a V1-to-V2 comparison. - Adds SKILL-V2.md and removes skill-card.md.