#include <bits/stdc++.h>
#include <ext/pb_ds/tree_policy.hpp>
#include <ext/pb_ds/assoc_container.hpp>
using namespace std;
using namespace __gnu_pbds;
typedef long long ll;
typedef long double ld;
typedef complex<ld> cd;
typedef pair<int, int> pi;
typedef pair<ll,ll> pl;
typedef pair<ld,ld> pd;
typedef vector<int> vi;
typedef vector<ld> vd;
typedef vector<ll> vl;
typedef vector<pi> vpi;
typedef vector<pl> vpl;
typedef vector<cd> vcd;
template <class T> using Tree = tree<T, null_type, less<T>, rb_tree_tag,tree_order_statistics_node_update>;
#define FOR(i, a, b) for (int i=a; i<(b); i++)
#define F0R(i, a) for (int i=0; i<(a); i++)
#define FORd(i,a,b) for (int i = (b)-1; i >= a; i--)
#define F0Rd(i,a) for (int i = (a)-1; i >= 0; i--)
#define sz(x) (int)(x).size()
#define mp make_pair
#define pb push_back
#define f first
#define s second
#define lb lower_bound
#define ub upper_bound
#define all(x) x.begin(), x.end()
const int MOD = 1000000007;
const ll INF = 1e18;
const int MX = 1000005;
int N,K;
ll sum, mx;
vpl v;
vpl tmp;
void ins(ll l, ll r, int x) {
tmp.pb({l,x});
tmp.pb({r+1,-x});
}
int main() {
ios_base::sync_with_stdio(0); cin.tie(0);
cin >> N >> K;
F0R(i,N) {
ll A; cin >> A;
sum += A;
mx = max(mx,A);
v.pb({A,i+1});
}
if (sum % K != 0 || mx > sum/K) {
cout << -1;
exit(0);
}
ll lst = 0;
for (auto x: v) {
if (lst+x.f-1 >= sum/K) {
ins(lst,sum/K-1,x.s);
ins(0,lst+x.f-1-sum/K,x.s);
} else ins(lst,lst+x.f-1,x.s);
lst = (lst+x.f)%(sum/K);
}
sort(all(tmp));
set<int> cur;
vector<pair<ll,vi>> ans;
for (int i = 0; i < sz(tmp); ) {
int I = i;
while (i < sz(tmp) && tmp[i].f == tmp[I].f) {
if (tmp[i].s < 0) cur.erase(abs(tmp[i].s));
else cur.insert(tmp[i].s);
i ++;
}
if (i < sz(tmp)) {
vi v; for (int i: cur) v.pb(i);
ans.pb({tmp[i].f-tmp[I].f,v});
}
}
cout << sz(ans) << "\n";
for (auto a: ans) {
cout << a.f << " ";
for (int x: a.s) cout << x << " ";
cout << "\n";
}
}
/* Look for:
* the exact constraints (multiple sets are too slow for n=10^6 :( )
* special cases (n=1?)
* overflow (ll vs int?)
* array bounds
*/
