Add Copilot skill architecture with 10 skills, 2 agents, and shared infra

Introduce .github/skills/ with solve, prove, optimize, simplify,
encode, explain, benchmark, memory-safety, static-analysis, and
deeptest skills. Each skill follows a SKILL.md + scripts/ pattern
with Python scripts backed by a shared SQLite logging library
(z3db.py). Two orchestrator agents (z3-solver, z3-verifier) route
requests to the appropriate skills.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

.github/skills/benchmark/SKILL.md

@@ -0,0 +1,48 @@
+---
+name: benchmark
+description: Measure Z3 performance on a formula or file. Collects wall-clock time, theory solver statistics, memory usage, and conflict counts. Results are logged to z3agent.db for longitudinal tracking.
+---
+
+Given an SMT-LIB2 formula or file, run Z3 with statistics enabled and report performance characteristics. This is useful for identifying performance regressions, comparing tactic strategies, and profiling theory solver workload distribution.
+
+# Step 1: Run Z3 with statistics
+
+```bash
+python3 scripts/benchmark.py --file problem.smt2
+python3 scripts/benchmark.py --file problem.smt2 --runs 5
+python3 scripts/benchmark.py --formula "(declare-const x Int)..." --debug
+```
+
+The script invokes `z3 -st` and parses the `:key value` statistics block.
+
+# Step 2: Interpret the output
+
+The output includes:
+
+- wall-clock time (ms)
+- result (sat/unsat/unknown/timeout)
+- memory usage (MB)
+- conflicts, decisions, propagations
+- per-theory breakdown (arithmetic, bv, array, etc.)
+
+With `--runs N`, the script runs Z3 N times and reports min/median/max timing.
+
+# Step 3: Compare over time
+
+Past benchmark runs are logged to `z3agent.db`. Query them:
+```bash
+python3 ../../shared/z3db.py runs --skill benchmark --last 20
+python3 ../../shared/z3db.py query "SELECT smtlib2, result, stats FROM formulas WHERE run_id IN (SELECT run_id FROM runs WHERE skill='benchmark') ORDER BY run_id DESC LIMIT 5"
+```
+
+# Parameters
+
+| Parameter | Type | Required | Default | Description |
+|-----------|------|----------|---------|-------------|
+| formula | string | no | | SMT-LIB2 formula |
+| file | path | no | | path to .smt2 file |
+| runs | int | no | 1 | number of repeated runs for timing |
+| timeout | int | no | 60 | seconds per run |
+| z3 | path | no | auto | path to z3 binary |
+| debug | flag | no | off | verbose tracing |
+| db | path | no | .z3-agent/z3agent.db | logging database |

.github/skills/benchmark/scripts/benchmark.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+"""
+benchmark.py: measure Z3 performance with statistics.
+
+Usage:
+    python benchmark.py --file problem.smt2
+    python benchmark.py --file problem.smt2 --runs 5
+"""
+
+import argparse
+import statistics
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent.parent / "shared"))
+from z3db import Z3DB, run_z3, parse_stats, setup_logging
+
+
+def main():
+    parser = argparse.ArgumentParser(prog="benchmark")
+    parser.add_argument("--formula")
+    parser.add_argument("--file")
+    parser.add_argument("--runs", type=int, default=1)
+    parser.add_argument("--timeout", type=int, default=60)
+    parser.add_argument("--z3", default=None)
+    parser.add_argument("--db", default=None)
+    parser.add_argument("--debug", action="store_true")
+    args = parser.parse_args()
+
+    setup_logging(args.debug)
+
+    if args.file:
+        formula = Path(args.file).read_text()
+    elif args.formula:
+        formula = args.formula
+    else:
+        parser.error("provide --formula or --file")
+        return
+
+    db = Z3DB(args.db)
+    timings = []
+
+    for i in range(args.runs):
+        run_id = db.start_run("benchmark", formula)
+        result = run_z3(formula, z3_bin=args.z3, timeout=args.timeout,
+                        args=["-st"], debug=args.debug)
+
+        stats = parse_stats(result["stdout"])
+        db.log_formula(run_id, formula, result["result"], stats=stats)
+        db.finish_run(run_id, result["result"], result["duration_ms"],
+                      result["exit_code"])
+        timings.append(result["duration_ms"])
+
+        if args.runs == 1:
+            print(f"result: {result['result']}")
+            print(f"time: {result['duration_ms']}ms")
+            if stats:
+                print("statistics:")
+                for k, v in sorted(stats.items()):
+                    print(f"  :{k} {v}")
+
+    if args.runs > 1:
+        print(f"runs: {args.runs}")
+        print(f"min: {min(timings)}ms")
+        print(f"median: {statistics.median(timings):.0f}ms")
+        print(f"max: {max(timings)}ms")
+        print(f"result: {result['result']}")
+
+    db.close()
+    sys.exit(0 if result["exit_code"] == 0 else 1)
+
+
+if __name__ == "__main__":
+    main()