diff --git a/README.md b/README.md
index aaa0d7ac..39f113d9 100644
--- a/README.md
+++ b/README.md
@@ -203,6 +203,17 @@ python3 scripts/oracle_boundary_audit.py \
 
 审计报告中的 `template_comparisons` 会列出 external-verified template 的 Dasha 起点差异、Shadbala 七曜分量/总分差异、每个分量的 Rupa 容差、单位说明和 `global_scaling_check.recommendation: reject_global_scaling`，并继续保持 `production_tuning_recommended: false`，防止用单个样本或全局倍率调生产常数。
 
+公开 benchmark 看板用于长期展示能力状态、oracle readiness 和“是否可宣称全球第一”的诚实边界：
+
+```bash
+python3 scripts/public_benchmark_dashboard.py \
+  --oracle-file references/oracle/dasha_shadbala_oracle_cases.json \
+  --format markdown \
+  --output docs/benchmark/public_jyotish_benchmark_dashboard.md
+```
+
+当前看板固定输出 `can_claim_global_first: false`，直到外部 oracle 样本、差异审计和长期公开 benchmark 都达到生产调参标准。
+
 `full-reading` 也会输出 `ai_prompt_pack`：这是给网页/app、skill 或后端 AI 代理使用的结构化 Prompt/RAG 上下文包。它不会硬编码断语，而是携带 D1/D9/Dasha/Shadbala/Ashtakavarga 的证据快照、推荐检索文档和边界提示，要求大模型基于计算证据交叉验证，避免单一配置下结论。
 
 ### Prerequisites
diff --git a/docs/benchmark/public_jyotish_benchmark_dashboard.json b/docs/benchmark/public_jyotish_benchmark_dashboard.json
new file mode 100644
index 00000000..268444d1
--- /dev/null
+++ b/docs/benchmark/public_jyotish_benchmark_dashboard.json
@@ -0,0 +1,55 @@
+{
+  "scope": "public_jyotish_benchmark_dashboard",
+  "schema_version": 1,
+  "generated_at": "2026-06-26T09:20:53.904412+00:00",
+  "summary": {
+    "technique_count": 68,
+    "capability_valid": true,
+    "problem_count": 0,
+    "status_counts": {
+      "complete": 9,
+      "covered": 59,
+      "knowledge-only": 0,
+      "missing": 0,
+      "not-integrated": 0,
+      "partial": 0,
+      "workflow-only": 0
+    }
+  },
+  "oracle_readiness": {
+    "total_packets": 5,
+    "valid_packets": 0,
+    "ready_for_calibration": 0,
+    "production_tuning_allowed": false,
+    "all_packets_external_verified": false,
+    "queue_status_counts": {
+      "template_only": 5
+    },
+    "boundary": "Evidence packets can become review-ready only with external artifacts and filled target values. Local engine output remains rejected as an external oracle source."
+  },
+  "boundary_audit": {
+    "template_cases": 5,
+    "external_verified_template_cases": 0,
+    "dasha_cases": 1,
+    "longitude_cases": 1,
+    "shadbala_cases": 1,
+    "production_tuning_recommended": false,
+    "open_items": [
+      "Promote template cases to external_verified only after filling external target rows.",
+      "Add multi-source Vimshottari rows with Moon longitude, ayanamsa and start-boundary settings.",
+      "Add Shadbala component targets before claiming external absolute calibration."
+    ],
+    "template_comparison_count": 0
+  },
+  "public_claim": {
+    "can_claim_global_first": false,
+    "reason": "Do not claim global first until Dasha/Shadbala external oracle packets are valid, production tuning is allowed, and public benchmark history is stable."
+  },
+  "global_first_gap": "Dasha/Shadbala external oracle readiness remains 0, Shadbala absolute values still need component-level external evidence, and public long-term benchmark history is not yet comparable to the strongest global open-source projects.",
+  "next_actions": [
+    "Fill the first external JHora/PyJHora packet under references/oracle/artifacts/pending_packets.",
+    "Run oracle_evidence_validator.py until at least one packet is valid.",
+    "Run oracle_boundary_audit.py to inspect Dasha/Shadbala deltas without tuning constants.",
+    "Publish this dashboard after each validated sample batch."
+  ]
+}
\ No newline at end of file
diff --git a/docs/benchmark/public_jyotish_benchmark_dashboard.md b/docs/benchmark/public_jyotish_benchmark_dashboard.md
new file mode 100644
index 00000000..c5584703
--- /dev/null
+++ b/docs/benchmark/public_jyotish_benchmark_dashboard.md
@@ -0,0 +1,38 @@
+# Public Jyotish Benchmark Dashboard
+
+Generated: `2026-06-26T09:20:54.438994+00:00`
+
+## Capability Registry
+
+- technique_count: `68`
+- capability_valid: `true`
+- problem_count: `0`
+
+## Dasha/Shadbala Oracle Readiness
+
+- total_packets: `5`
+- valid_packets: `0`
+- ready_for_calibration: `0`
+- production_tuning_allowed: `false`
+
+## Boundary Audit
+
+- external_verified_template_cases: `0`
+- template_comparison_count: `0`
+- production_tuning_recommended: `false`
+
+## Global First Claim
+
+- can_claim_global_first: `false`
+- reason: Do not claim global first until Dasha/Shadbala external oracle packets are valid, production tuning is allowed, and public benchmark history is stable.
+
+## Remaining Gap
+
+Dasha/Shadbala external oracle readiness remains 0, Shadbala absolute values still need component-level external evidence, and public long-term benchmark history is not yet comparable to the strongest global open-source projects.
+
+## Next Actions
+
+- Fill the first external JHora/PyJHora packet under references/oracle/artifacts/pending_packets.
+- Run oracle_evidence_validator.py until at least one packet is valid.
+- Run oracle_boundary_audit.py to inspect Dasha/Shadbala deltas without tuning constants.
+- Publish this dashboard after each validated sample batch.
diff --git a/scripts/public_benchmark_dashboard.py b/scripts/public_benchmark_dashboard.py
new file mode 100644
index 00000000..7cc207c8
--- /dev/null
+++ b/scripts/public_benchmark_dashboard.py
@@ -0,0 +1,176 @@
+#!/usr/bin/env python3
+"""Generate a public benchmark dashboard for Jyotish skill readiness."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import subprocess
+import sys
+import tempfile
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+
+
+ROOT = Path(__file__).resolve().parents[1]
+PYTHON = sys.executable
+
+
+def _run_json(command: list[str]) -> dict[str, Any]:
+    completed = subprocess.run(
+        command,
+        cwd=ROOT,
+        text=True,
+        capture_output=True,
+        timeout=90,
+        check=False,
+    )
+    if completed.returncode != 0:
+        raise RuntimeError(completed.stderr.strip() or completed.stdout.strip())
+    return json.loads(completed.stdout)
+
+
+def _oracle_readiness(oracle_file: str) -> dict[str, Any]:
+    queue = _run_json([PYTHON, "scripts/oracle_collection_queue.py", "--oracle-file", oracle_file, "--format", "json"])
+    with tempfile.NamedTemporaryFile("w+", suffix=".json", encoding="utf-8", delete=True) as fh:
+        json.dump(queue, fh, ensure_ascii=False)
+        fh.flush()
+        validation = _run_json([PYTHON, "scripts/oracle_evidence_validator.py", "--queue-file", fh.name])
+    summary = validation["summary"]
+    return {
+        "total_packets": summary["total_packets"],
+        "valid_packets": summary["valid_packets"],
+        "ready_for_calibration": summary["ready_for_calibration"],
+        "production_tuning_allowed": summary["production_tuning_allowed"],
+        "all_packets_external_verified": summary["all_packets_external_verified"],
+        "queue_status_counts": queue["summary"].get("by_status", {}),
+        "boundary": validation["boundary"],
+    }
+
+
+def _boundary_audit(oracle_file: str) -> dict[str, Any]:
+    report = _run_json([PYTHON, "scripts/oracle_boundary_audit.py", "--oracle-file", oracle_file])
+    summary = report["summary"]
+    return {
+        "template_cases": summary["template_cases"],
+        "external_verified_template_cases": summary.get("external_verified_template_cases", 0),
+        "dasha_cases": summary["dasha_cases"],
+        "longitude_cases": summary["longitude_cases"],
+        "shadbala_cases": summary["shadbala_cases"],
+        "production_tuning_recommended": summary["production_tuning_recommended"],
+        "open_items": summary["open_items"],
+        "template_comparison_count": len(report.get("template_comparisons", [])),
+    }
+
+
+def build_dashboard(oracle_file: str) -> dict[str, Any]:
+    capability = _run_json([PYTHON, "scripts/audit_capabilities.py", "--mode", "validate"])
+    oracle = _oracle_readiness(oracle_file)
+    boundary = _boundary_audit(oracle_file)
+    global_first_gap = (
+        "Dasha/Shadbala external oracle readiness remains 0, Shadbala absolute values still need "
+        "component-level external evidence, and public long-term benchmark history is not yet comparable "
+        "to the strongest global open-source projects."
+    )
+    can_claim_global_first = bool(
+        capability.get("valid")
+        and oracle["production_tuning_allowed"]
+        and boundary["production_tuning_recommended"]
+    )
+    return {
+        "scope": "public_jyotish_benchmark_dashboard",
+        "schema_version": 1,
+        "generated_at": datetime.now(timezone.utc).isoformat(),
+        "summary": {
+            "technique_count": capability["technique_count"],
+            "capability_valid": capability["valid"],
+            "problem_count": capability["problem_count"],
+            "status_counts": capability["status_counts"],
+        },
+        "oracle_readiness": oracle,
+        "boundary_audit": boundary,
+        "public_claim": {
+            "can_claim_global_first": can_claim_global_first,
+            "reason": (
+                "Do not claim global first until Dasha/Shadbala external oracle packets are valid, "
+                "production tuning is allowed, and public benchmark history is stable."
+            ),
+        },
+        "global_first_gap": global_first_gap,
+        "next_actions": [
+            "Fill the first external JHora/PyJHora packet under references/oracle/artifacts/pending_packets.",
+            "Run oracle_evidence_validator.py until at least one packet is valid.",
+            "Run oracle_boundary_audit.py to inspect Dasha/Shadbala deltas without tuning constants.",
+            "Publish this dashboard after each validated sample batch.",
+        ],
+    }
+
+
+def render_markdown(report: dict[str, Any]) -> str:
+    oracle = report["oracle_readiness"]
+    boundary = report["boundary_audit"]
+    claim = report["public_claim"]
+    lines = [
+        "# Public Jyotish Benchmark Dashboard",
+        "",
+        f"Generated: `{report['generated_at']}`",
+        "",
+        "## Capability Registry",
+        "",
+        f"- technique_count: `{report['summary']['technique_count']}`",
+        f"- capability_valid: `{str(report['summary']['capability_valid']).lower()}`",
+        f"- problem_count: `{report['summary']['problem_count']}`",
+        "",
+        "## Dasha/Shadbala Oracle Readiness",
+        "",
+        f"- total_packets: `{oracle['total_packets']}`",
+        f"- valid_packets: `{oracle['valid_packets']}`",
+        f"- ready_for_calibration: `{oracle['ready_for_calibration']}`",
+        f"- production_tuning_allowed: `{str(oracle['production_tuning_allowed']).lower()}`",
+        "",
+        "## Boundary Audit",
+        "",
+        f"- external_verified_template_cases: `{boundary['external_verified_template_cases']}`",
+        f"- template_comparison_count: `{boundary['template_comparison_count']}`",
+        f"- production_tuning_recommended: `{str(boundary['production_tuning_recommended']).lower()}`",
+        "",
+        "## Global First Claim",
+        "",
+        f"- can_claim_global_first: `{str(claim['can_claim_global_first']).lower()}`",
+        f"- reason: {claim['reason']}",
+        "",
+        "## Remaining Gap",
+        "",
+        report["global_first_gap"],
+        "",
+        "## Next Actions",
+        "",
+    ]
+    lines.extend(f"- {item}" for item in report["next_actions"])
+    lines.append("")
+    return "\n".join(lines)
+
+
+def parse_args(argv: list[str] | None = None) -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Generate public Jyotish benchmark dashboard")
+    parser.add_argument("--oracle-file", default="references/oracle/dasha_shadbala_oracle_cases.json")
+    parser.add_argument("--format", choices=["json", "markdown"], default="json")
+    parser.add_argument("--output", help="Optional output path")
+    return parser.parse_args(argv)
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = parse_args(argv)
+    report = build_dashboard(args.oracle_file)
+    text = json.dumps(report, ensure_ascii=False, indent=2) if args.format == "json" else render_markdown(report)
+    if args.output:
+        output = Path(args.output)
+        output.parent.mkdir(parents=True, exist_ok=True)
+        output.write_text(text, encoding="utf-8")
+    print(text)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())
diff --git a/tests/test_public_benchmark_dashboard.py b/tests/test_public_benchmark_dashboard.py
new file mode 100644
index 00000000..761d7b6a
--- /dev/null
+++ b/tests/test_public_benchmark_dashboard.py
@@ -0,0 +1,62 @@
+#!/usr/bin/env python3
+"""Tests for the public Jyotish benchmark dashboard."""
+
+from __future__ import annotations
+
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+
+
+def run_dashboard(*args: str) -> subprocess.CompletedProcess[str]:
+    return subprocess.run(
+        [
+            sys.executable,
+            "scripts/public_benchmark_dashboard.py",
+            "--oracle-file",
+            "references/oracle/dasha_shadbala_oracle_cases.json",
+            *args,
+        ],
+        cwd=ROOT,
+        text=True,
+        capture_output=True,
+        timeout=60,
+        check=False,
+    )
+
+
+def test_public_benchmark_dashboard_outputs_stable_json_summary() -> None:
+    completed = run_dashboard("--format", "json")
+
+    assert completed.returncode == 0, completed.stderr or completed.stdout
+    report = json.loads(completed.stdout)
+    assert report["scope"] == "public_jyotish_benchmark_dashboard"
+    assert report["schema_version"] == 1
+    assert report["summary"]["technique_count"] >= 60
+    assert report["summary"]["capability_valid"] is True
+    assert report["oracle_readiness"]["total_packets"] == 5
+    assert report["oracle_readiness"]["valid_packets"] == 0
+    assert report["oracle_readiness"]["ready_for_calibration"] == 0
+    assert report["oracle_readiness"]["production_tuning_allowed"] is False
+    assert report["boundary_audit"]["production_tuning_recommended"] is False
+    assert "Dasha/Shadbala" in report["global_first_gap"]
+    assert report["public_claim"]["can_claim_global_first"] is False
+    assert report["public_claim"]["reason"]
+
+
+def test_public_benchmark_dashboard_outputs_markdown_and_can_write_file(tmp_path: Path) -> None:
+    output = tmp_path / "benchmark.md"
+    completed = run_dashboard("--format", "markdown", "--output", str(output))
+
+    assert completed.returncode == 0, completed.stderr or completed.stdout
+    assert output.exists()
+    markdown = output.read_text(encoding="utf-8")
+    assert "# Public Jyotish Benchmark Dashboard" in markdown
+    assert "Dasha/Shadbala Oracle Readiness" in markdown
+    assert "Global First Claim" in markdown
+    assert "can_claim_global_first: `false`" in markdown
+    assert "production_tuning_allowed: `false`" in markdown