oh-my-knowledge
OMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.
22 results
OMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.
L1-L2-L3 three-tier memory agent harness: gate approval, zero-judgement event log, weekly distillation, TDD execution loop. Claude Code plugin and DeepSeek Harness (dsh) bundle.
Self-learning habit engine for the DeepSeek Harness — detects user-correction signals, judges habits with a low-cost model on threshold, settles candidates behind a two-level human gate
Two-tier model router for DeepSeek Harness — automatic execution/judgment routing with LLM Judge, multi-model fallback chains, and exponential-backoff runtime failover. A DSH adaptation of pi-shift-router.
Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and a per-session audit trail in the conversation window's 审批 tab.
Codex-style approval autopilot for DeepSeek Harness: ordered glob rules (allow/ask/deny) plus an AI risk judge (low/medium/high) mapped through a risk tolerance, as an approval answerer.
Skill-trigger evaluation: an LLM judge recreates the DSH skill catalog and measures how reliably a skill description routes matching queries.
LLM-as-a-Verifier plugin for DeepSeek Harness: fine-grained logprob-based scoring, pairwise pivot tournaments (best-of-N) and an automatic end-of-turn quality gate.
Cross-border counterparty due diligence for DeepSeek Harness — resolve the entity you are actually contracting with, then judge whether the record is fit to rely on.
Adversarial pro/con debate with a neutral judge for DeepSeek Harness: /debate human command, subagent-driven rounds, verdict record, and a web debate card.
Run one command N rounds and judge by median/distribution instead of a single run
Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance, and a web control page in Settings → Plugins.
Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.
OI 出题工作台:知识点锁定、数据构造、本地评测,打包 Hydro/HOJ 原生题目包,发布/管理 Hydro 与 HOJ OJ,提供 Python 外部管理 UI 与系统斜杠命令。Opt-in skill-first plugin for DeepSeek Harness.
A DeepSeek Harness plugin + skill that scouts the DSH ecosystem: the core deepseek-harness repo and every dsh-plugin-tagged repository, discovers harnesses related to your goal, and judges whether each is worth trying.
Agent benchmark evaluation plugin for DeepSeek Harness: web panel, slash commands, headless CLI, test-set import, model/judge switching, orchestration, scoring, and reports.
Plugin value auditor for DeepSeek Harness: judge a plugin before install and audit installed ones — heuristic scan + LLM judge, with model-switch re-audit reminders. · DSH 插件价值裁判:装前判断值不值得装,装后审计是否还该留,模型切换时提醒复核。
DSH agent preset: minimal Windows preset with persistent Git Bash + str_replace_editor
Completion verification for DeepSeek Harness: gates goal stamps (update_goal complete) and turn boundaries — a goal stays open until workspace verification commands exit 0
A blind, fair, local Agent arena inside DSH Web: same task, same commit, isolated worktrees, shared verification, judge before you reveal.
误食催吐判断
Shared zero-runtime-dependency toolkit for PerryLink DSH plugins: a pluggable Provider registry seam, fail-closed approval and adaptive session-event gates, mechanical verify scripts, shared sanitize/pricing/judge modules, and a new-plugin skeleton.