dsh-socrates
Socratic clarify-first deep research plugin for DeepSeek Harness: adaptive multi-round research with evidence-closed cited reports, cross-verification, and citation auditing.
65 results
Socratic clarify-first deep research plugin for DeepSeek Harness: adaptive multi-round research with evidence-closed cited reports, cross-verification, and citation auditing.
DeepSeek Harness bundle: plan-travel-guide skill with map/OTA/ticketing catalog sweep, Xiaohongshu/Douyin/Weibo/Bilibili discovery, POI verification, and day-by-day route clustering.
DSH Cordis plugin: turn arbitrary source text or images with text, diagrams, and tables into an AI-generated knowledge graph (facts / inferences / concepts / definitions / examples / counter-examples / rules) with two-way linking between the graph and the original text, plus evidence-grounded verification, questioning, one-click fixes and an audit log.
Cordis-native, evidence-driven full-stack engineering discipline for DeepSeek Harness agents
DeepSeek Harness frontend runtime verification: detect, run, preview, interact, diff, and prove local web apps.
A blind, fair, local Agent arena inside DSH Web: same task, same commit, isolated worktrees, shared verification, judge before you reveal.
Popper: a falsification-driven correction loop for agent sessions — claim commitment, gate falsification, and mutually exclusive hypothesis revision, with an append-only evidence ledger
MCP-first Agent runtime debugging, verification, and controlled profiling for DeepSeek Harness / Cordis.
DeepSeek Harness bundle: Chinese accounting standards (CAS / ASSE) and tax law lookup with article-level citations, plus a verification-discipline skill.
Persistent long-horizon autonomous mission runtime for DeepSeek Harness: dependency DAG, independent verification, replan-on-failure, lease ownership.
Two-stage intent and evidence review, deterministic completion gates, and bounded repair for DeepSeek Harness agents
DSH bundle: Xiaohongshu (RED) viral-note agent skill — hot-note research, note generation/rewrite, verification, authorized account analysis, QR login and controlled publishing, shipped as a bundled skill provider. Zero-dependency.
DeepSeek Harness long-run mission suite: mission control, Long-Run Captain preset, patched LLM-as-a-Verifier, self-wake timer.
dsh-experience-flywheel · DSH 经验飞轮插件 — agent cross-session experience memory + dual-acceptance gates (auto query/inject via agent/pre-step middleware; exit-1 gate scripts)
Raw-file SHA-256 and SHA-512 verification tool for DeepSeek Harness
Evidence-first handoff auditing and documentation-sync skills for Codex and DeepSeek Harness.
Verification toolkit for DeepSeek Harness agents: evidence-based claim checking against workspace files with line citations, config file validation (JSON/YAML), HTTP URL status checks, npm package checks and GitHub repo submission-readiness checks — complementary to dsh-plugin-gate
Eyes for your DeepSeek Harness agent — it opens, sees, and fixes what it builds. Headless-browser preview & self-verification tools (screenshot, console, DOM read, interact) as a dsh plugin.
DSH plugin: decode and inspect JWT tokens (debug only, no signature verification).
Runtime security guard for DeepSeek Harness (DSH) — blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.
Human-gated DeepSeek Harness plugin creation, verification, and release studio
Task contracts, approval gates, checkpoints, verification evidence, and best-effort rollback for DeepSeek Harness
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.
Talk to Excel in DeepSeek Harness: create/edit spreadsheets, formulas, styles, filters, and tables by conversation; auto-verifies formulas after every edit, repairs silent errors, and validates charts.