gamealgo-cli 0.3.8 → 0.3.9

package/README.md

@@ -1,6 +1,6 @@
 # GameAlgo CLI
 
-`gamealgo-cli` is the independently released command-line client for GameAlgo. It is intended for AI coding agents and game developers to manage integration plans, event dictionaries, reports, scripts, configuration, keys, and experiments.
+`gamealgo-cli` is the independently released command-line client for GameAlgo. It is intended for AI coding agents and game developers to manage integration plans, event dictionaries, reports, scripts, configuration, keys, experiments, and game diagnosis.
 
 Source repository: <https://github.com/sunyuhao-code/GameAlgoCli>
 
@@ -51,8 +51,11 @@ The skill uses the project-bound CLI and live Server content. It can discover th
 ```bash
 gamealgo optimize list --json
 gamealgo optimize get ad-monetization --json
+gamealgo diagnosis --json
 ```
 
+`gamealgo diagnosis` returns the same structured competition, monetization, and retention diagnosis shown in the dashboard. It requires a Game Admin Key with `reports:read` and an account-verified Maker game binding; save the complete result with `--out diagnosis.json` when an agent needs to use it in a local workflow.
+
 Adjust S2S event forwarding can be configured with an explicit event allowlist:
 
 ```bash

package/dist/client.js

@@ -209,6 +209,9 @@ export class GameAlgoAdminClient {
         const params = new URLSearchParams({ environment, platform });
         return await this.get(`/admin/v1/games/${encodeURIComponent(await this.gameId())}/integration/plan?${params.toString()}`);
     }
+    async getGameDiagnosis() {
+        return await this.get(`/admin/v1/games/${encodeURIComponent(await this.gameId())}/diagnosis`);
+    }
     async listOptimizationTasks() {
         return await this.get(`/admin/v1/games/${encodeURIComponent(await this.gameId())}/optimization/tasks`);
     }

package/dist/commands/diagnosis.js

@@ -0,0 +1,17 @@
+import { parseFlags } from "../args.js";
+import { printResult } from "../output.js";
+import { writeTextFile } from "../resources.js";
+export async function handleDiagnosis(client, args, global) {
+    const flags = parseFlags(args);
+    if (args.length)
+        throw new Error("usage: gamealgo diagnosis [--out diagnosis.json]");
+    if (flags.out === true)
+        throw new Error("--out requires a file path");
+    const diagnosis = await client.getGameDiagnosis();
+    if (typeof flags.out === "string") {
+        await writeTextFile(flags.out, `${JSON.stringify(diagnosis, null, 2)}\n`);
+        await printResult({ ok: true, out: flags.out }, global);
+        return;
+    }
+    await printResult(diagnosis, global);
+}

package/dist/main.js

@@ -13,6 +13,7 @@ import { handleSkill } from "./commands/skill.js";
 import { loadPackageMetadata } from "./config.js";
 import { handleDocs, handleHelp } from "./docs.js";
 import { handleDynamicConfig } from "./commands/dynamic-config.js";
+import { handleDiagnosis } from "./commands/diagnosis.js";
 import { cliErrorPayload } from "./http.js";
 import { printResult } from "./output.js";
 export async function main() {
@@ -98,6 +99,10 @@ export async function main() {
             await handleIntegration(client, args, global);
             return;
         }
+        if (command === "diagnosis" || command === "diagnose") {
+            await handleDiagnosis(client, args, global);
+            return;
+        }
         if (command === "marketing") {
             await handleMarketing(client, args, global);
             return;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gamealgo-cli",
-  "version": "0.3.8",
+  "version": "0.3.9",
   "description": "GameAlgo command-line client for AI agents and game developers",
   "repository": {
     "type": "git",

package/skills/gamealgo/SKILL.md

@@ -20,10 +20,11 @@ Run commands from the game repository that owns the integration. Before any game
 When the user asks what GameAlgo can do, asks for ongoing iteration, or names a broad optimization goal:
 
 1. Run `gamealgo optimize list --json` to load the complete current task catalog from the Server.
-2. Treat the result as an unranked capability catalog. Do not claim that a task is recommended or ready until its prerequisites have been checked against the current game.
-3. Once the user selects a task, or their request clearly identifies one, run `gamealgo optimize get <task-id> --json`.
-4. For each topic named in the task's `docs` field, run `gamealgo docs <topic> --list --json`, then read the sections relevant to the selected task with `gamealgo docs <topic> --section <section-id>` before implementation.
-5. Follow the returned `agentSteps` and use `deliverables` as the completion checklist.
+2. When making a recommendation for the current game, run `gamealgo diagnosis --json` as well. It returns the same structured competition, monetization, and retention diagnosis used by the dashboard. If it is unavailable, treat the diagnosis as an unmet prerequisite rather than fabricating a conclusion; it is available only to account-verified Maker games.
+3. Treat the result as an unranked capability catalog. Do not claim that a task is recommended or ready until its prerequisites have been checked against the current game.
+4. Once the user selects a task, or their request clearly identifies one, run `gamealgo optimize get <task-id> --json`.
+5. For each topic named in the task's `docs` field, run `gamealgo docs <topic> --list --json`, then read the sections relevant to the selected task with `gamealgo docs <topic> --section <section-id>` before implementation.
+6. Follow the returned `agentSteps` and use `deliverables` as the completion checklist.
 
 Do not run every catalog task in sequence. Complete the selected task and report unmet prerequisites instead of manufacturing missing data.