dsh-agent-arena
Isolated multi-model coding matches with deterministic verification, scoring, and reports
15 results
Isolated multi-model coding matches with deterministic verification, scoring, and reports
Plugin-combination analysis for the DeepSeek Harness: dependency trees, conflict detection, risk scoring with prediction, visualization, and combination simulation.
A DeepSeek Harness (DSH) community agent preset for rigorous A-share five-dimension (technical/valuation/fundamental/capital-flow/news) standardized analysis: persona, skill knowledge base, hard risk gate, deterministic Python scoring core, Tencent-first collectors. Not an investment recommendation.
/code-review slash command for DeepSeek Harness — multi-agent review of pull requests and local code, with configurable confidence scoring
Clinical documentation toolkit for DeepSeek Harness: SBAR and I-PASS handovers, SOAP and APSO notes, admission H&P, discharge summaries with pending-results enforcement, patient-instruction readability scoring, HIPAA Safe Harbor de-identification, and cited FDA label/FAERS/recalls/Drugs@FDA, MedlinePlus, PubMed/PMC/Europe PMC, and ClinicalTrials.gov (search/details/eligibility/investigators/endpoints) lookups. Drafts only; not a medical device.
Plugin insight center — one answer to '哪些值得装': requirement matching (plugin_guide), environment recipes (recipe), health scoring (plugin_rank), static security scanning (plugin_audit), and a single install verdict (plugin_verdict)
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.
A-share full-chain investment research: real-time quote, Buffett-style value scoring, risk radar and institutional consensus in one tool
Host-agnostic controller for staging, validating, scoring, and solidifying evolved tool plugins.
AutoResearch suite for DeepSeek Harness: arxiv recall, LQS scoring, research state panel, stall guardian, five-persona peer review, plus the research-ui visualization feature-switch control plane.
DeepSeek Harness plugin for ecommerce operators: CSV batch tools, reproducible scoring, Chinese skills and store policy KB.
Kestrel — adversarial deep-research engine for DeepSeek Harness. Mechanically-verified citations, independent-corroboration scoring that exposes syndication laundering, prosecutor/defender claim tribunal, and a compounding evidence graph.
DSH web plugin: Skill Cockpit panel in Settings. See all skills (system/project/pool) with Chinese notes, search, enable/disable/delete/import, local test-fire scoring, and per-skill usage stats to spot zombie skills.
Agent benchmark evaluation plugin for DeepSeek Harness: web panel, slash commands, headless CLI, test-set import, model/judge switching, orchestration, scoring, and reports.
Fuzzy file finding and indexed content search for DSH: find_files / resolve_file / related_files / fff_grep. Pure-JS path index + subsequence scoring (no native dependencies). Port of pi-fff for the Pi coding agent.