docs(registry): refresh deep-research description for v0.2.0

manifests.json

@@ -84,7 +84,7 @@
     {
       "id": "deep-research",
       "name": "deep_research",
-      "description": "Protocol-first, gated, multi-agent literature investigation. Two human-in-the-loop gates bracket a four-role subagent crew (Scout / Skeptic / Methodologist / Synthesizer); every claim a synthesis ships must be backed by a row in research_evidence with a verbatim quote_span — if a claim can't produce its quote, the claim gets cut. v0.1.0 ships the protocol (SKILL.md), DB schema (PostgreSQL + SQLite), five agent role prompts, install-manifest, and a worked example (cholesterol primary prevention). Agent-runtime-agnostic — the reference implementation uses the Claude Agent SDK, but the workflow only requires subagent fan-out, persistent KV, scholarly HTTP, and a human-in-loop checkpoint surface. Python reference impl (scholar adapter + synthesis_doc_builder) lands in v0.2.0.",
+      "description": "Protocol-first, gated, multi-agent literature investigation. Two human-in-the-loop gates bracket a four-role subagent crew (Scout / Skeptic / Methodologist / Synthesizer); every claim a synthesis ships must be backed by a row in research_evidence with a verbatim quote_span — if a claim can't produce its quote, the claim gets cut. v0.1.0 shipped the protocol (SKILL.md), DB schema (PostgreSQL + SQLite), five agent role prompts, install-manifest, and a worked example (cholesterol primary prevention). v0.2.0 adds the Python reference implementation: a stdlib-urllib scholar adapter (OpenAlex / Semantic Scholar / PubMed / arXiv / Europe PMC / Crossref / Unpaywall) and a python-docx + matplotlib synthesis builder with pluggable upload. Agent-runtime-agnostic; core stays stdlib-only, the docx builder is gated behind the optional [viz] extra.",
       "capabilities": [
         "research",
         "literature-review",

registry/deep-research/index.html

@@ -623,7 +623,7 @@ <h2>
         Runtime
       </h2>
       <p class="small muted">runtime: <code>python-module</code> &middot; install method: <code>git</code> &middot; entrypoint: <code>python -m deep_research</code></p>
-      <p>deep_research is an agent-runtime-agnostic workflow that turns an empirical research question into a citation-grade synthesis. Two human-in-the-loop gates (protocol pre-registration, Pass-2 spend) bracket a four-role subagent crew (Scout / Skeptic / Methodologist / Synthesizer). Every claim a synthesis ships must be backed by a row in the research_evidence table with a verbatim quote_span; claims without their quote get cut. The v0.1.0 distribution ships the protocol (SKILL.md), DB schema (PostgreSQL + SQLite), five agent role prompts, and a worked example. The Python reference implementation (scholar adapter + synthesis_doc_builder) lands in v0.2.0.</p>
+      <p>deep_research is an agent-runtime-agnostic workflow that turns an empirical research question into a citation-grade synthesis. Two human-in-the-loop gates (protocol pre-registration, Pass-2 spend) bracket a four-role subagent crew (Scout / Skeptic / Methodologist / Synthesizer). Every claim a synthesis ships must be backed by a row in the research_evidence table with a verbatim quote_span; claims without their quote get cut. v0.2.0 adds the Python reference implementation: a stdlib-urllib scholar adapter (OpenAlex / Semantic Scholar / PubMed / arXiv / Europe PMC / Crossref / Unpaywall) and a python-docx + matplotlib synthesis builder with pluggable upload. Core stays stdlib-only; the docx builder is gated behind the optional `[viz]` extra.</p>
       <p class="small muted">Tags: <span class="badge cap">research</span><span class="badge cap">literature-review</span><span class="badge cap">meta-analysis</span><span class="badge cap">agents</span><span class="badge cap">subagent-fan-out</span><span class="badge cap">no-fabrication</span><span class="badge cap">skill-bundle</span></p>
       <p class="small muted">License: Apache-2.0</p>
       <p><span class="freshness">Last fetched 2026-06-01T20:33:24Z (live)</span></p>