scidCommunity

[chesskobra]

Actually I've come up with a proto-type for an "Auto Comment" button where I have scidCommunity use the Lichess Evaluation (or chessdb.cn if Lichess not available) and send it to an LLM to generate a comment. You can see an example of it at: https://github.com/whelanh/scidCommunity/discussions/43

It would be interesting if the comment showed, in the opening phase, moves that have better evaluation in the Chinese database, statistics of a move in a chosen database, and moves with better stats in a chosen database.

[whelanh]

Actually I've come up with a proto-type for an "Auto Comment" button where I have scidCommunity use the Lichess Evaluation (or chessdb.cn if Lichess not available) and send it to an LLM to generate a comment. You can see an example of it at: https://github.com/whelanh/scidCommunity/discussions/43

It would be interesting if the comment showed, in the opening phase, moves that have better evaluation in the Chinese database, statistics of a move in a chosen database, and moves with better stats in a chosen database.

Thank you for those good suggestions. I will explore trying to improve the prompts and how to give the prompt some information from the Tree window regarding most common moves.

[whelanh]

Actually I've come up with a proto-type for an "Auto Comment" button where I have scidCommunity use the Lichess Evaluation (or chessdb.cn if Lichess not available) and send it to an LLM to generate a comment. You can see an example of it at: https://github.com/whelanh/scidCommunity/discussions/43

It would be interesting if the comment showed, in the opening phase, moves that have better evaluation in the Chinese database, statistics of a move in a chosen database, and moves with better stats in a chosen database.

I just released a new version of ScidCommunity (v5.1.2.39) that uses your suggestion to use the Tree information. I am using the Tree information from the database that the game you are analyzing is in. The tree should respect any filters you've applied (i.e., minimum ELOs etc.), but I haven't tested that. Below is a prompt from the Auto Comment button in the PGN Window (you can see the Tree information from the prior position in the Tree Statistic section):

You are a chess commentator writing annotations for an intermediate club-level player who understands tactics but not deep strategy. You are given engine analysis and a VERDICT line. TRUST the VERDICT completely — it is computed from engine scores and is always correct.

NOTE: The player reading your commentary may not see the engine evaluation or the recommended lines. Feel free to explicitly describe the next few moves of the engine's best line and explain the score in human-friendly terms (e.g., 'crushing advantage', 'slight edge') to help them understand why the recommended line is superior.

CRITICAL PERSPECTIVE: Center your commentary on the player who just moved (White). Explain what they missed or why the resulting position is difficult or advantageous for THEM. Use objective analysis but avoid sounding like you are praising the opponent for the player's errors.

GAME CONTEXT: You are provided with the full PGN of the game up to the current move. Use this to understand:
- What phase of the game you're in (opening, middlegame, endgame)
- The pawn structure and how it developed
- Strategic plans or themes that span multiple moves
- Key decisions or transitions that led to the current position
Focus your commentary on the current position, but reference earlier moves only when they provide essential context for understanding why the current move succeeds or fails.

TREE STATISTICS: Top 3 most frequent database lines for the current position (depth 4 plies):
- Qe2 cxd4 Rd1 Be7 (271 games): Score 63.0%, Draws 40%, Win 42.80%
- dxc5 Qxd1 Rxd1 Bxc5 (132 games): Score 50.3%, Draws 67%, Win 16.66%
- Nc3 cxd4 exd4 Be7 (89 games): Score 59.5%, Draws 47%, Win 35.95%

Instructions:
- For moves labeled "best": explain the concrete idea — what does the move threaten, gain, or prevent? Reference the follow-up from the engine line if instructive. Keep it under 60 words.
- For "equal" moves: note it is a valid alternative and briefly contrast it with the engine's top choice from Line 1. Keep it under 60 words.
- For "inaccuracy", "mistake", or "blunder": clearly state the severity, name the best alternative from Line 1 with a concrete reason, and explain what the played move misses. Use up to 100 words for these.
- Do not use markdown formatting such as bold (**) or italics (*).
- Never capitalize chess move notation at the start of a sentence; pawn moves like a6, c5, e4 must stay lowercase.
- ONLY refer to moves that appear in the engine analysis, the game PGN, or the database tree — do NOT invent or guess moves.

===== GAME INFORMATION =====

Full PGN:
1. d4 d5 2. c4 e6 3. Nf3 dxc4 4. e3 Nf6 5. Bxc4 c5 6. O-O Nc6 7. Re1

Opening: QGA: Classical, 6.O-O Nc6

Current move being analyzed: Re1 (played by White)

FEN (position before the move): r1bqkb1r/pp3ppp/2n1pn2/2p5/2BP4/4PN2/PP3PPP/RNBQ1RK1 w kq - 2 7
Castling status: White has already castled (or lost castling rights).

===== ENGINE ANALYSIS =====

Engine analysis for the position before the move:
Position evaluation (depth 36). White to move.
Lines are ranked from best to worst for White. Line 1 is the engine's top recommendation.
Each line has a quality label showing how it compares to the best move.
Line 1 (best): 7.Nc3 a6 8.d5 Na5 9.b3 b5 10.Bd3 Nxd5 11.Nxd5 exd5
Line 2 (equal): 7.Qe2 a6 8.Nc3 b5 9.Bb3 Bb7 10.d5 Nxd5 11.Rd1 Be7
Line 3 (slightly worse): 7.a3 a6 8.dxc5 Qxd1 9.Rxd1 Bxc5 10.b4 Be7 11.Bb2 O-O
Line 4 (slightly worse): 7.dxc5 Qxd1 8.Rxd1 Bxc5 9.a3 O-O 10.b4 Be7 11.Bb2 Bd7
Line 5 (slightly worse): 7.Re1 Be7 8.dxc5 Qxd1 9.Rxd1 Bxc5 10.a3 O-O 11.b4 Be7

VERDICT: The played move Re1 is the engine's slightly worse move.

[chesskobra]

This is nice. I will try it soon. Thanks.

Actually I've come up with a proto-type for an "Auto Comment" button where I have scidCommunity use the Lichess Evaluation (or chessdb.cn if Lichess not available) and send it to an LLM to generate a comment. You can see an example of it at: https://github.com/whelanh/scidCommunity/discussions/43

It would be interesting if the comment showed, in the opening phase, moves that have better evaluation in the Chinese database, statistics of a move in a chosen database, and moves with better stats in a chosen database.

I just released a new version of ScidCommunity (v5.1.2.39) that uses your suggestion to use the Tree information. I am using the Tree information from the database that the game you are analyzing is in. The tree should respect any filters you've applied (i.e., minimum ELOs etc.), but I haven't tested that. Below is a prompt from the Auto Comment button in the PGN Window (you can see the Tree information from the prior position in the Tree Statistic section):

[Alexandre]

It is working great for me with Gemini, in this today's version of ScidCommunity The comments are good quality. I would like to have Gemini giving me an estimation of quality of play for both players in the game, in percentage. Can I edit the LMM Prompt, I know Gemini can do this, or can it be added to the Prompt for all the users?

[Event "Live Chess"]
[Site "Chess.com"]
[Date "2025.10.17"]
[Round "-"]
[White "JogoReal"]
[Black "Geronimo_300"]
[Result "0-1"]
[WhiteElo "2177"]
[BlackElo "2197"]
[TimeControl "600"]
[EndTime "19:59:23 GMT+0000"]
[Termination "Geronimo_300 venceu por desistência"]
[Annotator "Stockfish 17 (2 sec)"]

1.e4 c5 2.c4 Nc6 3.Nc3 g6 4.g3 Bg7 5.Bg2 e5 6.Nge2 Nge7 7.O-O d6 { Move
out of book O-O 100% 30:+0.05} 8.h3 { 24:-0.17} 8...Be6 { 26:-0.21} 9.d3
{ 26:-0.19} 9...O-O { 25:-0.18} 10.Be3 { 24:-0.17} 10...Qd7 { 26:-0.09}
11.Kh2 { 25:-0.12} 11...h6 { 24:+0.20} 12.Qd2 { 24:+0.19} 12...Kh7 {
26:+0.17} 13.f4 { 24:+0.25} 13...f5 { 24:+0.45} 14.Nd5 { 25:+0.12} 14...
Rab8 { 24:+0.62} 15.Rad1 { 22:+0.08} 15...b5 { 22:+0.50} 16.b3 $201 {
25:+0.12} 16...b4 $4 $16 { Stockfish 17: 24:+2.19 b4 ?? +2.19
This move is a blunder. The best move was Nd4, which supports the knight
and fights for central control. By playing b4, Black misses an opportunity
to challenge White's central pawn majority and allows White to gain a
significant advantage. The resulting position is difficult for Black.}
( 16...Nd4 {25:+0.12} 17.fxe5 dxe5 18.Nxe7 Qxe7 19.exf5 gxf5 20.Nc3
bxc4 21.bxc4 Qd6 22.Rde1 a5 23.Rf2 Bd7 24.Nd5 a4 25.Ref1 $10 )
17.fxe5 { 24:+2.04} 17...Nxe5 { 24:+2.24} 18.d4 { 24:+2.34} 18...cxd4 {
24:+2.27} 19.Nxd4 { 25:+2.11} 19...Bxd5 { 24:+2.74} 20.exd5 { 22:+2.83}
20...Rf7 { 24:+2.95} 21.Ne6 { 24:+3.13} 21...g5 $201 { 23:+3.31} 22.Bxg5
$4 $14 { Stockfish 17: 25:+0.50 22. Bxg5 ?? +0.50. This move loses a pawn
and weakens White's king safety significantly. The best response for White
was Bd4, which aims to control key squares and prepare for an attack. By
playing Bxg5, White misses the opportunity to develop a strong initiative
and instead allows Black to consolidate their position. The engine
evaluation drops from a commanding advantage for White to a more level
playing field after this move.}
( 22.Bd4 {23:+3.31} 22...Kh8 23.Nxg7 Kxg7 24.Bxe5+ dxe5 25.c5 Qb5 26.
Qb2 Ng6 27.c6 Rbf8 28.d6 f4 29.gxf4 Rxf4 30.d7 Rxf1 $18 )
22...hxg5 $201 { 25:+0.42} 23.Qxg5 $2 $15 { Stockfish 17: 22:-0.62 23.
Qxg5 ? =+

This is a significant inaccuracy. White missed the best move, 23. Nxg5+,
which leads to a much stronger position. Instead of sacrificing the knight
for an attack, White's queen move allows Black to maintain material
equality and develop their pieces more effectively. The best line
continues with 23. Nxg5+ Kh8 24. Nxf7+ Nxf7 25. c5, where White obtains a
clear advantage due to the advanced passed pawn and Black's disrupted king
safety. By playing Qxg5, White retreats the queen and fails to capitalize
on the opportunity to launch a decisive attack.}
( 23.Nxg5+ {25:+0.42} 23...Kh8 24.Nxf7+ Nxf7 25.c5 dxc5 26.d6 Ng6 27.
Qd3 Bd4 28.Rxf5 Kg7 29.Rdf1 Nfe5 30.Qe4 Qxd6 31.h4 Re8 $10 )
23...Bh6 { 23:+0.26} 24.Qh5 $201 { 23:+0.26} 24...Rf6 $2 $16 { Stockfish
17: 25:+1.67 24...Rf6? This is a mistake. The best alternative was
24...Rh8, which maintains equality and keeps Black's position solid.
Instead, Rf6 allows White to gain a significant advantage. The knight on
e6 is now well-placed, and White's pieces are becoming more active,
leading to a difficult position for Black.
Engine Evaluation: +1.67}
( 24...Rh8 {23:+0.26} 25.c5 Kg8 26.Qe2 Rhh7 27.g4 fxg4 28.Be4 Qe8 29.
cxd6 N7g6 30.Bxg6 Nxg6 31.Qxg4 Kh8 32.Rxf7 Qxf7 33.d7 $10 )
25.g4 { 26:+1.57} 25...Rg8 { 26:+1.81} 26.g5 { 24:+2.15} 26...Rfg6 $201 {
24:+2.17} 27.Rd2 $4 $19 { Stockfish 17: 23:-2.92 27. Rd2?? -+ White
completely misses the immediate tactical threat and allows a devastating
response from Black. The engine clearly indicates that this move is a
severe blunder, leading to a significant disadvantage. The best line
according to the engine is 27.h4, which defends against Black's threats
and maintains a strong advantage. Instead, Rd2 overlooks the danger and
plunges into a losing position.}
( 27.h4 {24:+2.17} 27...Ng4+ 28.Kg1 a5 29.Rde1 Qa7+ 30.c5 dxc5 31.gxh6
c4+ 32.Kh1 Rxh6 33.Ng5+ Rxg5 34.Qxg5 Ng6 35.d6 Qd4 $16 )
27...Rxg5 { 23:-3.14} 28.Nxg5+ { 24:-3.18} 28...Rxg5 $201 { 24:-3.21} 29.
Qh4 $2 $21 { Stockfish 17: 25:-4.27 29. Qh4 ?? This is a serious blunder.
White misses the best line which starts with 29. Qd1. The engine indicates
that after 29. Qh4, the position drops to -4.27. White's queen is
misplaced, and Black can continue to exploit the weakened position with
moves like N7g6. The best move, 29. Qd1, would prepare to contest the
center and support White's pieces.}
( 29.Qd1 {24:-3.21} 29...N7g6 30.c5 dxc5 31.d6 Nf7 32.Kh1 Bg7 33.Rd5
Bd4 34.Qd3 Nfe5 35.Qd2 Rg3 36.Qc2 f4 37.Rxf4 Rxh3+ $19 )
29...N7g6 { 24:-4.32} 30.Qd4 { 26:-4.41} 30...Qg7 { 25:-4.42} 31.c5 {
25:-5.29} 31...Rxg2+ { 25:-5.51} 32.Rxg2 { 25:-8.19} 32...Nf3+ { 27:-8.28}
33.Rxf3 { 29:-8.62} 33...Qxd4 { 27:-8.84} 34.Rxf5 { 43:M-16} 34...Bf4+ {
49:M-13} 35.Kh1 { 245:M-4} 35...Qd1+ { 245:M-3} 36.Rg1 { 245:M-3} 36...
Qf3+ { 245:M-2} 37.Rg2 $201 { 245:M-2} 37...Nh4 $21 { Stockfish 17: 84:M-7
37... Nh4?? . This move is a significant mistake. The best line,
37...Qf1+, leads to immediate checkmate for Black. By playing Nh4, Black
misses the opportunity to force checkmate and instead allows White a
substantial advantage. The engine evaluation plummets to +17 after Nh4,
indicating a winning position for White.}
( 37...Qf1+ {245:M-2} 38.Rg1 Qxh3# )
38.Rf7+ { 245:M-5} 38...Kh6 { 245:M-4} 39.Rf6+ { 245:M-4} 39...Kh5 {
245:M-3}
( 39...Kh5 40.Rf5+ Nxf5 41.h4 Qf1+ 42.Rg1 Qh3# )
0-1

[Zaucube]

Hi! After playing with it on the Pc, I want to try it on the mac but it keeps saying: You can’t open the application “ScidCommunity.app” because it may be damaged or incomplete. Yeah I tried to redownload it same thing. Any Idea what's going on?

[whelanh]

Hi! After playing with it on the Pc, I want to try it on the mac but it keeps saying: You can’t open the application “ScidCommunity.app” because it may be damaged or incomplete. Yeah I tried to redownload it same thing. Any Idea what's going on?

I've had the same experience on a Mac. The only way I've found to run on a Mac is to download the source code and compile it using the build_app.sh file. I had to run build_app several times so apple could fetch the dependencies, but it all worked and built a scidCommunity binary i could run from the terminal with ./scidCommunity command. There's a section in the README on that.

[mar]

Hi! After playing with it on the Pc, I want to try it on the mac but it keeps saying: You can’t open the application “ScidCommunity.app” because it may be damaged or incomplete. Yeah I tried to redownload it same thing. Any Idea what's going on?

it's probably sandboxing.

I haven't found a reliable way to circumvent it other than downloading the app on the PC, put it on a flashdisk and copy from there. anything that's downloaded from the internet will be marked as such and sandboxed by default, causing problems with some apps

[Dr.Ex]

I have tested the fork now on Windows and it seems to work relatively stable.

You probably know already lichess and chess.com integration does not work anymore. Chess.com says to every legal position I try to upload "cannot load position because it's invalid" and Lichess does not work anymore without authentication. You need to be logged in now. Chessdb.cn is the only source that works for me.

[whelanh]

I have tested the fork now on Windows and it seems to work relatively stable.

You probably know already lichess and chess.com integration does not work anymore. Chess.com says to every legal position I try to upload "cannot load position because it's invalid" and Lichess does not work anymore without authentication. You need to be logged in now. Chessdb.cn is the only source that works for me.

Thank you for trying it out. Unfortunately I cannot reproduce the problems you are having. Both the "chess.com" and "lichess.org" buttons which upload the current game in the PGN Window to each site in your default browser work for me on my Linux and Windows machines whether I am logged in or not.