SEMANTIC DIRECTORY · plugin-directory-semantic-v3-19
Model & Agent Quality Evaluation
以受控实验和统计证据评估模型、提示词、RAG 或智能体配置，包括基准测试、A/B、回归、盲测、漂移检测、连通性诊断和发布治理；不承担日常运行遥测。
Leaf membership
25 plugins
dsh-self-evolutionLhy723/dsh-self-evolutionCatalog AnalyzedBenchmark-driven self-evolution for DeepSeek Harness · 冻结基准上的 Agent Profile 自我进化：评测 → Candidate → 严格接受/回滚CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals3 starsdsh-self-harness-toolsSuTang-vain/dsh-self-harness-toolsCatalog AnalyzedTwo self-contained DeepSeek Harness plugins: dsh-prior-probe (frozen probe-battery tools, official bundle) and dsh-evidence-dashboard (archive dashboard).CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals1 starsdsh-skill-evalrenjianguojinqianfan/dsh-skill-evalCatalog AnalyzedDSH Plugin：用 LLM judge 评测技能 description 的触发准确率（欠触发/过触发）CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals2 starsdsh-wmWayneJin0918/dsh-wmCatalog AnalyzedPlayable world-model toolkit for DeepSeek Harness: look at frames, name the 3D / pixel / latent route, measure a run, and RSI the research loop.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals4 starsoh-my-knowledgeoh-my-knowledgeCatalog AnalyzedOMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.54.0Evidence updated2026-09-23Public signals2539 downloadsollama-monitorollama-monitorCatalog AnalyzedOllama 监控与测评平台：node 半侧提供 DSH 工具，web 半侧提供设置页内的交互面板CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.3Evidence updated2026-09-24Public signals0 downloadsxby-cookie-rewardxby-skill/xby-cookie-rewardCatalog Analyzed一个通过游戏化自我反思为LLM提供Cookie奖励的模型上下文协议服务器。CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars
Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.