.claude/skills/meta-agent-eval-harnessRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
由 model-distillation 从教师技能 agent-eval-harness 蒸馏并增强的超越型元技能, 在教师能力之上叠加自验证、自我反思、super-agent 编排与持续自进化闭环,逐步超越教师。
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/meta-agent-eval-harnessRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/meta-agent-eval-harnessRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/meta-agent-eval-harnessRuntime, 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 @qq435912743/meta-agent-eval-harnessclawhub inspect @qq435912743/meta-agent-eval-harness --version 1.0.0This 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.
sha256:831790b87328ce8213c1da05008ecfd76533cac2ca675d8e5b0751bde3264573distillation_report.mdscripts/learner.pyskill-card.mdSKILL.mdInitial release introducing the meta-agent-eval-harness skill, a distilled and enhanced version of agent-eval-harness. - Adds reliable self-verification, self-reflection loops, and integration into super-agent workflows for continuous improvement. - Implements adversarial validation to prevent surface-level learning and ensures persistent self-evolution. - Inherits core evaluation and regression-check abilities from the teacher skill, while enhancing failure protection and learning mechanisms. - Includes a built-in learner module for automatic review, memory, and quality improvement after each use. - Provides user commands for recording usage outcomes, tracking preferences, and triggering automatic retrospectives.