Plugins

Adaptive model discovery, evaluation, tiering, and subagent routing for DeepSeek Harness.

Langfuse observability for DeepSeek Harness (DSH): per-turn trace trees aggregated by session id, with prompt versioning and evaluation.

Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence

Check which DeepSeek Harness plugins actually loaded, and look up public evaluation boards on trapstreet.run

Design I/O for coding agents: controllable UI generation via declarations (spec/domain/craft/design/components/template) and contracts (skill/evaluator). Use for product UI—console, dashboard, agent-ops, CJK-first apps.

Skill for building a game design brief into a playable, publishable TapTap Maker project: it picks the browser workspace or local MCP route, extracts the five elements of the brief, writes a first-round prompt for a minimal core loop, iterates in the official order, checks preview and release materials, and keeps credit, credential and irreversible-action limits in view. Includes eight reference notes on the product, credits, themes and asset limits, the leaderboard, brief parsing, iteration, publishing and safety, four templates, and three read-only Python checks for brief completeness, project layout and release materials.

QMS NCR ingest, batch alias resolution, impact evaluation, CAPA and 8D state.

Unity 2022.3 editor control for the agent: 20 tools that read the scene hierarchy, create and edit GameObjects, components and serialized properties, drive Play mode, capture screenshots, evaluate C# inside the editor and start player builds.

Weather care for DeepSeek Harness: turns a forecast into one sentence you can send — clothing and umbrella advice from feels-like temperature, humidity and air quality, adjusted for how cold-sensitive the user is and how they commute. Also a switchable daily care push, extreme-weather alerts and reminders, evaluated when the agent wakes (a host such as qq-bridge can wake it on schedule). Preferences stay on the local machine.

Diagnostic evaluation plugin for DeepSeek Harness: freezes the confirmed Harness configuration, runs a benchmark, keeps the full session trace, and attributes failures to model, Harness, benchmark or environment.

Connects a local Synthesizer V Studio 2 Pro to the agent through its own Lua script API, with five tools for discovery, a persistent bridge, voice composition, note editing and DAW (VST3/ARA + MIDI) integration. Windows 10/11 only; requires Synthesizer V Studio 2 Pro 2.1.2+ with a project open.

Registers one agent tool, plugin_guard, that statically scans a DSH plugin package before it is installed and reports a verdict with the reasons: a missing or broken dsh.bundle.patch, a missing dsh.permissions block, install scripts, dangerous APIs and obfuscation, dependency risk, and source that is not indexed and therefore cannot be verified. Read-only: the scanned code is never imported, installed, evaluated or run.

Registers one `valuation_service` tool that reads a workpaper tree of 01/02/04 JSON and returns one unified schema: six ratio groups, forecast ratios, DCF input slots with explicit missing markers, comparable PS/PE and IRR. Deterministic and local: missing WACC, growth, capex, D&A or working-capital inputs stay blank instead of being guessed, and assumption differences are flagged for review.

Release gate for AI answer quality. Two channels: replay an existing VeriScope archive through the original Python quality gate, or run a threshold gate over a Ragas per-row export with Node only — no VeriScope, Python or pandas. Returns PASS, FAIL or REVIEW with source evidence and a re-checkable receipt; supports per-row thresholds and exact decimal comparison. It never re-evaluates and never calls a model, and REVIEW never becomes PASS.

Checks a bid evaluation scoring matrix for internal arithmetic consistency: that each factor's maximum, the scores recorded and the total agree with each other. Reports the differences it finds; it does not judge whether the evaluation itself was correct or fair.

Cross-session memory for your dsh agent: remembered, recalled, and re-verified instead of assumed.

DSH 试金石：给「自改造」补上评测这一环——用一套金标准用例，把改动前 vs 改动后跑一遍、打分、对比，好就留、不好就撤。

Retrospective agent-session evaluation: deterministic grade cards and cross-session regression diffs from persisted logs — no benchmark runs, no LLM judges.

Measure whether a dsh setup change actually helped: register repeatable cases, run them, and diff the results before and after you change rules, skills, or models.

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters via TPE Bayesian search; only strictly-better recipes are kept. Offline one-command run, data bundle shipped with sha1 reconciliation, GPU auto-detect. Ships one skill.

DSH plugin for bounded agent evaluation: compare an original with candidate prompt or supported configuration changes against user-supplied checks, record evidence and costs, and leave adoption to the user.

Deterministic engineering orchestration runtime for DeepSeek Harness: the orbit_controller tool and OrbitService run Commander, Executor and Smart Watchdog children through PLAN, EXECUTE, EVALUATE, bounded correction and runtime recovery, with durable state in <project>/.cx/state.json.

DSH web plugin: a LiveBench tab in the Trajectory view (right of 对话/轨迹). Run LiveBench evaluations against every model configured in the DeepSeek Harness — pick provider/model, category, task, release and question range from dropdowns, watch progress, and

DSH session workflows for packaging verifiable capsules, evaluating reusable Skills, and comparing controlled session trajectories.