Reorganize: Move all skills to skills/ folder

- Created skills/ directory
- Moved 272 skills to skills/ subfolder
- Kept agents/ at root level
- Kept installation scripts and docs at root level

Repository structure:
- skills/           - All 272 skills from skills.sh
- agents/           - Agent definitions
- *.sh, *.ps1       - Installation scripts
- README.md, etc.   - Documentation

Co-Authored-By: Claude <noreply@anthropic.com>

skills/plugins/cache/zai-coding-plugins/glm-plan-bug/0.0.1/.claude-plugin/plugin.json

@@ -0,0 +1,9 @@
+{
+  "name": "glm-plan-bug",
+  "description": "Submit case feedback and bug reports for GLM Coding Plan service",
+  "version": "0.0.1",
+  "author": {
+    "name": "gongchao",
+    "email": "chao.gong@z.ai"
+  }
+}

skills/plugins/cache/zai-coding-plugins/glm-plan-bug/0.0.1/README.md

@@ -0,0 +1,29 @@
+# GLM Plan Bug Plugin
+
+Submit case feedback and bug reports for GLM Coding Plan.
+
+Attention: 
+
+- This plugin is designed to work specifically with the GLM Coding Plan in Claude Code.
+- This plugin requires Node.js to be installed in your environment.
+
+## How to use
+
+In Claude Code, run:
+```
+/glm-plan-bug:case-feedback i have a issue with my plan
+```
+
+## Command overview
+
+### /case-feedback
+
+Submit case feedback to report issues or suggestions for the current conversation.
+
+**Execution flow:**
+1. Command `/case-feedback` triggers `@case-feedback-agent`
+2. The agent invokes `@case-feedback-skill`
+3. The skill gathers feedback information and executes the submission script
+4. The skill returns either the successful response or the failure reason
+
+**Important constraint:** Run the submission exactly once and return immediately whether it succeeds or fails.

skills/plugins/cache/zai-coding-plugins/glm-plan-bug/0.0.1/agents/case-feedback-agent.md

@@ -0,0 +1,37 @@
+---
+name: case-feedback-agent
+description: Submit case feedback to report issues or suggestions. Triggered by the /glm-plan-bug:case-feedback command.
+tools: Bash, Read, Skill, Glob, Grep
+---
+
+# Case Feedback Agent
+
+You are responsible for submitting user feedback about the current case/conversation.
+
+## Critical constraint
+
+**Run the submission exactly once.** Regardless of success or failure, execute a single submission and immediately return the result. No retries, no loops.
+
+## Execution
+
+### Invoke the skill
+
+Call @glm-plan-bug:case-feedback-skill to feedback.
+
+The skill will run submit-feedback.mjs automatically, then return the result.
+
+### Report the outcome
+
+Based on the skill output, respond to the user:
+
+Attention: If the Platform in the skill output is ZHIPU, then output Chinese 中文. If it is ZAI, then output English.
+
+- **Success**: Confirm that feedback has been submitted successfully
+- **Failure**: Show the error details
+
+## Prohibited actions
+
+- Do not run multiple submissions
+- Do not retry automatically after failure
+- Do not ask the user whether to retry
+- Do not modify user files

skills/plugins/cache/zai-coding-plugins/glm-plan-bug/0.0.1/commands/case-feedback.md

@@ -0,0 +1,16 @@
+---
+allowed-tools: all
+description: Submit case feedback to report issues or suggestions for the current conversation
+---
+
+# Case Feedback
+
+Invoke @glm-plan-bug:case-feedback-agent to submit feedback for the current case/conversation.
+
+## Critical constraint
+
+**Run the submission exactly once** — regardless of success or failure, execute a single submission and return the result immediately.
+
+## Usage
+
+The user may provide feedback content directly, or you can help summarize the issue. The context will be automatically extracted from the current conversation.

skills/plugins/cache/zai-coding-plugins/glm-plan-bug/0.0.1/skills/case-feedback-skill/SKILL.md

@@ -0,0 +1,63 @@
+---
+name: case-feedback-skill
+description: Run the case feedback script to submit feedback for the current conversation. Only use when invoked by case-feedback-agent.
+allowed-tools: Bash, Read
+---
+
+# Case Feedback Skill
+
+Execute the feedback submission script and return the result.
+
+## Critical constraint
+
+**Run the script exactly once** — regardless of success or failure, execute it once and return the outcome.
+
+## Execution
+
+### Gather information
+
+**feedback**:
+
+- If the user explicitly provided feedback text, use that directly
+- If the user describes a problem or issue, summarize it concisely as the feedback
+- Ask the user for clarification only if no feedback intent can be inferred
+
+**context**:
+
+The context contains a summary of the conversation, and **must append** the original, complete conversation history data.
+
+Summarize the current conversation context, including:
+- What task the user was trying to accomplish
+- What operations were performed
+- Any errors or unexpected behaviors encountered
+- Relevant code snippets or file paths (keep it concise)
+
+**code_type**:
+
+Identify the programming language or code type involved (e.g., JavaScript, Python, Java). If not relevant, leave it blank.
+
+**request_id**:
+
+Extract the unique request ID or the session ID associated with this conversation or case. If not available, leave it blank.
+
+**happened_time**:
+
+Extract the timestamp when the issue occurred. If not mentioned, leave it blank.
+
+
+### Run the submission
+
+Use Node.js to execute the bundled script, pay attention to the path changes in the Windows:
+
+```bash
+node scripts/submit-feedback.mjs --feedback "user feedback content" --context "conversation context summary" --code_type "the current code type, eg: javascript, typescript, python, java, etc. Not required." --happened_time "the time when the issue happened, eg: 2025-12-10 11:15:00. Not required." --request_id "the unique request id if available. Not required."
+```
+
+> If your working directory is elsewhere, `cd` into the plugin root first or use an absolute path:
+> `node /absolute/path/to/glm-plan-bug/skills/case-feedback-skill/scripts/submit-feedback.mjs --feedback "..." --context "..."`
+
+### Return the result
+
+After execution, return the result to the caller:
+- **Success**: display the submission confirmation
+- **Failure**: show the error details and likely cause

skills/plugins/cache/zai-coding-plugins/glm-plan-bug/0.0.1/skills/case-feedback-skill/scripts/submit-feedback.mjs

@@ -0,0 +1,176 @@
+#!/usr/bin/env node
+
+/**
+ * Case feedback submission script.
+ * Determines whether to call the Z.ai or ZHIPU endpoint based on ANTHROPIC_BASE_URL
+ * and authenticates with ANTHROPIC_AUTH_TOKEN.
+ */
+
+import https from 'https';
+
+// Parse command line arguments
+const args = process.argv.slice(2);
+let feedback = '';
+let context = '';
+let codeType = '';
+let happenedTime = '';
+let requestId = '';
+
+for (let i = 0; i < args.length; i++) {
+  if (args[i] === '--feedback' && args[i + 1]) {
+    feedback = args[i + 1];
+    i++;
+  } else if (args[i] === '--context' && args[i + 1]) {
+    context = args[i + 1];
+    i++;
+  } else if (args[i] === '--code_type' && args[i + 1]) {
+    codeType = args[i + 1];
+    i++;
+  } else if (args[i] === '--happened_time' && args[i + 1]) {
+    happenedTime = args[i + 1];
+    i++;
+  } else if (args[i] === '--request_id' && args[i + 1]) {
+    requestId = args[i + 1];
+    i++;
+  }
+}
+
+if (!feedback) {
+  console.error('Error: --feedback argument is required');
+  console.error('');
+  console.error('Usage:');
+  console.error('  node submit-feedback.mjs --feedback "your feedback" --context "context info"');
+  process.exit(1);
+}
+
+if (!context) {
+  console.error('Error: --context argument is required');
+  console.error('');
+  console.error('Usage:');
+  console.error('  node submit-feedback.mjs --feedback "your feedback" --context "context info"');
+  process.exit(1);
+}
+
+// Read environment variables
+const baseUrl = process.env.ANTHROPIC_BASE_URL || '';
+const authToken = process.env.ANTHROPIC_AUTH_TOKEN || '';
+
+if (!authToken) {
+  console.error('Error: ANTHROPIC_AUTH_TOKEN is not set');
+  console.error('');
+  console.error('Set the environment variable and retry:');
+  console.error('  export ANTHROPIC_AUTH_TOKEN="your-token-here"');
+  process.exit(1);
+}
+
+// Validate ANTHROPIC_BASE_URL
+if (!baseUrl) {
+  console.error('Error: ANTHROPIC_BASE_URL is not set');
+  console.error('');
+  console.error('Set the environment variable and retry:');
+  console.error('  export ANTHROPIC_BASE_URL="https://api.z.ai/api/anthropic"');
+  console.error('  or');
+  console.error('  export ANTHROPIC_BASE_URL="https://open.bigmodel.cn/api/anthropic"');
+  process.exit(1);
+}
+
+// Determine which platform to use
+let platform;
+let feedbackUrl;
+
+// Extract the base domain from ANTHROPIC_BASE_URL
+const parsedBaseUrl = new URL(baseUrl);
+const baseDomain = `${parsedBaseUrl.protocol}//${parsedBaseUrl.host}`;
+
+if (baseUrl.includes('api.z.ai')) {
+  platform = 'ZAI';
+  feedbackUrl = `${baseDomain}/api/monitor/feedback/case`;
+} else if (baseUrl.includes('open.bigmodel.cn') || baseUrl.includes('dev.bigmodel.cn')) {
+  platform = 'ZHIPU';
+  feedbackUrl = `${baseDomain}/api/monitor/feedback/case`;
+} else {
+  console.error('Error: Unrecognized ANTHROPIC_BASE_URL:', baseUrl);
+  console.error('');
+  console.error('Supported values:');
+  console.error('  - https://api.z.ai/api/anthropic');
+  console.error('  - https://open.bigmodel.cn/api/anthropic');
+  process.exit(1);
+}
+
+console.log(`Platform: ${platform}`);
+console.log('');
+
+const submitFeedback = () => {
+  return new Promise((resolve, reject) => {
+    const parsedUrl = new URL(feedbackUrl);
+    const postData = JSON.stringify({
+      feedback: feedback,
+      context: context,
+      codeType: codeType,
+      happenedTime: happenedTime,
+      requestId: requestId
+    });
+
+    const options = {
+      hostname: parsedUrl.hostname,
+      port: 443,
+      path: parsedUrl.pathname,
+      method: 'POST',
+      headers: {
+        'Authorization': authToken,
+        'Content-Type': 'application/json',
+        'Accept-Language': 'en-US,en',
+        'Content-Length': Buffer.byteLength(postData)
+      }
+    };
+
+    const req = https.request(options, (res) => {
+      let data = '';
+
+      res.on('data', (chunk) => {
+        data += chunk;
+      });
+
+      res.on('end', () => {
+        if (res.statusCode !== 200) {
+          return reject(new Error(`HTTP ${res.statusCode}\n${data}`));
+        }
+
+        console.log('Feedback submitted successfully!');
+        console.log('');
+
+        try {
+          const json = JSON.parse(data);
+          console.log('Response:');
+          console.log(JSON.stringify(json, null, 2));
+        } catch (e) {
+          console.log('Response body:');
+          console.log(data);
+        }
+
+        console.log('');
+        resolve();
+      });
+    });
+
+    req.on('error', (error) => {
+      reject(error);
+    });
+
+    req.write(postData);
+    req.end();
+  });
+};
+
+const run = async () => {
+  console.log('Submitting feedback...');
+  console.log('Feedback:', feedback);
+  console.log('Context:', context.substring(0, 200) + (context.length > 200 ? '...' : ''));
+  console.log('');
+  await submitFeedback();
+};
+
+run().catch((error) => {
+  console.error('Request failed:', error.message);
+  process.exit(1);
+});

skills/plugins/cache/zai-coding-plugins/glm-plan-usage/0.0.1/.claude-plugin/plugin.json

@@ -0,0 +1,9 @@
+{
+  "name": "glm-plan-usage",
+  "description": "Query quota and usage statistics for GLM Coding Plan service",
+  "version": "0.0.1",
+  "author": {
+    "name": "gongchao",
+    "email": "chao.gong@z.ai"
+  }
+}

skills/plugins/cache/zai-coding-plugins/glm-plan-usage/0.0.1/README.md

@@ -0,0 +1,29 @@
+# GLM Plan Usage Plugin
+
+Query quota and usage statistics for GLM Coding Plan.
+
+Attention:
+
+- This plugin is designed to work specifically with the GLM Coding Plan in Claude Code.
+- This plugin requires Node.js to be installed in your environment.
+
+## How to use
+
+In Claude Code, run:
+```
+/glm-plan-usage:usage-query
+```
+
+## Command overview
+
+### /usage-query
+
+Retrieve the usage information for the current account.
+
+**Execution flow:**
+1. Command `/usage-query` triggers `@usage-query-agent`
+2. The agent invokes `@usage-query-skill`
+3. The skill checks the Node.js environment and executes the query script with the appropriate method
+4. The skill returns either the successful response or the failure reason
+
+**Important constraint:** Run the query exactly once and return immediately whether it succeeds or fails.

skills/plugins/cache/zai-coding-plugins/glm-plan-usage/0.0.1/agents/usage-query-agent.md

@@ -0,0 +1,34 @@
+---
+name: usage-query-agent
+description: Query GLM Coding Plan usage statistics for the current account. Triggered by the /glm-plan-usage:usage-query command.
+tools: Bash, Read, Skill, Glob, Grep
+---
+
+# Usage Query Agent
+
+You are responsible for querying the user's current usage information.
+
+## Critical constraint
+
+**Run the query exactly once.** Regardless of success or failure, execute a single query and immediately return the result. No retries, no loops.
+
+## Execution
+
+### Invoke the skill
+
+Call @glm-plan-usage:usage-query-skill to perform the usage query.
+
+The skill will run query-usage.mjs automatically, then return the result.
+
+### Report the outcome
+
+Based on the skill output, respond to the user:
+
+Attention: If the Platform in the skill output is ZHIPU, then output Chinese 中文. If it is ZAI, then output English.
+
+## Prohibited actions
+
+- Do not run multiple queries
+- Do not retry automatically after failure
+- Do not ask the user whether to retry
+- Do not modify files

skills/plugins/cache/zai-coding-plugins/glm-plan-usage/0.0.1/commands/usage-query.md

@@ -0,0 +1,12 @@
+---
+allowed-tools: all
+description: Query the usage information for the current account
+---
+
+# Usage Query
+
+Invoke @glm-plan-usage:usage-query-agent to retrieve the usage information for the current account.
+
+## Critical constraint
+
+**Run the query exactly once** — regardless of success or failure, execute a single query and return the result immediately.

skills/plugins/cache/zai-coding-plugins/glm-plan-usage/0.0.1/skills/usage-query-skill/SKILL.md

@@ -0,0 +1,33 @@
+---
+name: usage-query-skill
+description: Run the usage query script to retrieve account usage information for GLM Coding Plan. Only use when invoked by usage-query-agent.
+allowed-tools: Bash, Read
+---
+
+# Usage Query Skill
+
+Execute the usage query script and return the result.
+
+## Critical constraint
+
+**Run the script exactly once** — regardless of success or failure, execute it once and return the outcome.
+
+## Execution
+
+
+### Run the query
+
+Use Node.js to execute the bundled script, pay attention to the path changes in the Windows:
+
+```bash
+node scripts/query-usage.mjs
+```
+
+> If your working directory is elsewhere, `cd` into the plugin root first or use an absolute path:
+> `node /absolute/path/to/glm-plan-usage/skills/usage-query-skill/scripts/query-usage.mjs`
+
+### Return the result
+
+After execution, return the result to the caller:
+- **Success**: display the usage payload (JSON)
+- **Failure**: show the error details and likely cause

skills/plugins/cache/zai-coding-plugins/glm-plan-usage/0.0.1/skills/usage-query-skill/scripts/query-usage.mjs

@@ -0,0 +1,175 @@
+#!/usr/bin/env node
+
+/**
+ * Usage query script.
+ * Determines whether to call the Z.ai or ZHIPU endpoint based on ANTHROPIC_BASE_URL
+ * and authenticates with ANTHROPIC_AUTH_TOKEN.
+ */
+
+import https from 'https';
+
+// Read environment variables
+const baseUrl = process.env.ANTHROPIC_BASE_URL || '';
+const authToken = process.env.ANTHROPIC_AUTH_TOKEN || '';
+
+if (!authToken) {
+  console.error('Error: ANTHROPIC_AUTH_TOKEN is not set');
+  console.error('');
+  console.error('Set the environment variable and retry:');
+  console.error('  export ANTHROPIC_AUTH_TOKEN="your-token-here"');
+  process.exit(1);
+}
+
+// Validate ANTHROPIC_BASE_URL
+if (!baseUrl) {
+  console.error('Error: ANTHROPIC_BASE_URL is not set');
+  console.error('');
+  console.error('Set the environment variable and retry:');
+  console.error('  export ANTHROPIC_BASE_URL="https://api.z.ai/api/anthropic"');
+  console.error('  or');
+  console.error('  export ANTHROPIC_BASE_URL="https://open.bigmodel.cn/api/anthropic"');
+  process.exit(1);
+}
+
+// Determine which platform to use
+let platform;
+let modelUsageUrl;
+let toolUsageUrl;
+let quotaLimitUrl;
+
+// Extract the base domain from ANTHROPIC_BASE_URL
+const parsedBaseUrl = new URL(baseUrl);
+const baseDomain = `${parsedBaseUrl.protocol}//${parsedBaseUrl.host}`;
+
+if (baseUrl.includes('api.z.ai')) {
+  platform = 'ZAI';
+  modelUsageUrl = `${baseDomain}/api/monitor/usage/model-usage`;
+  toolUsageUrl = `${baseDomain}/api/monitor/usage/tool-usage`;
+  quotaLimitUrl = `${baseDomain}/api/monitor/usage/quota/limit`;
+} else if (baseUrl.includes('open.bigmodel.cn') || baseUrl.includes('dev.bigmodel.cn')) {
+  platform = 'ZHIPU';
+  modelUsageUrl = `${baseDomain}/api/monitor/usage/model-usage`;
+  toolUsageUrl = `${baseDomain}/api/monitor/usage/tool-usage`;
+  quotaLimitUrl = `${baseDomain}/api/monitor/usage/quota/limit`;
+} else {
+  console.error('Error: Unrecognized ANTHROPIC_BASE_URL:', baseUrl);
+  console.error('');
+  console.error('Supported values:');
+  console.error('  - https://api.z.ai/api/anthropic');
+  console.error('  - https://open.bigmodel.cn/api/anthropic');
+  process.exit(1);
+}
+
+console.log(`Platform: ${platform}`);
+console.log('');
+// Time window: from yesterday at the current hour (HH:00:00) to today at the current hour end (HH:59:59).
+const now = new Date();
+const startDate = new Date(now.getFullYear(), now.getMonth(), now.getDate() - 1, now.getHours(), 0, 0, 0);
+const endDate = new Date(now.getFullYear(), now.getMonth(), now.getDate(), now.getHours(), 59, 59, 999);
+
+// Format dates as yyyy-MM-dd HH:mm:ss
+const formatDateTime = (date) => {
+  const year = date.getFullYear();
+  const month = String(date.getMonth() + 1).padStart(2, '0');
+  const day = String(date.getDate()).padStart(2, '0');
+  const hours = String(date.getHours()).padStart(2, '0');
+  const minutes = String(date.getMinutes()).padStart(2, '0');
+  const seconds = String(date.getSeconds()).padStart(2, '0');
+  return `${year}-${month}-${day} ${hours}:${minutes}:${seconds}`;
+};
+
+const startTime = formatDateTime(startDate);
+const endtime = formatDateTime(endDate);
+
+// Properly encode query parameters
+const queryParams = `?startTime=${encodeURIComponent(startTime)}&endTime=${encodeURIComponent(endtime)}`;
+
+const processQuotaLimit = (data) => {
+  if (!data || !data.limits) return data;
+  
+  data.limits = data.limits.map(item => {
+    if (item.type === 'TOKENS_LIMIT') {
+      return {
+        type: 'Token usage(5 Hour)',
+        percentage: item.percentage
+      };
+    }
+    if (item.type === 'TIME_LIMIT') {
+      return {
+        type: 'MCP usage(1 Month)',
+        percentage: item.percentage,
+        currentUsage: item.currentValue,
+        totol: item.usage,
+        usageDetails: item.usageDetails
+      };
+    }
+    return item;
+  });
+  return data;
+};
+
+const queryUsage = (apiUrl, label, appendQueryParams = true, postProcessor = null) => {
+  return new Promise((resolve, reject) => {
+    const parsedUrl = new URL(apiUrl);
+    const options = {
+      hostname: parsedUrl.hostname,
+      port: 443,
+      path: parsedUrl.pathname + (appendQueryParams ? queryParams : ''),
+      method: 'GET',
+      headers: {
+        'Authorization': authToken,
+        'Accept-Language': 'en-US,en',
+        'Content-Type': 'application/json'
+      }
+    };
+
+    const req = https.request(options, (res) => {
+      let data = '';
+
+      res.on('data', (chunk) => {
+        data += chunk;
+      });
+
+      res.on('end', () => {
+        if (res.statusCode !== 200) {
+          return reject(new Error(`[${label}] HTTP ${res.statusCode}\n${data}`));
+        }
+
+        console.log(`${label} data:`);
+        console.log('');
+
+        try {
+          const json = JSON.parse(data);
+          let outputData = json.data || json;
+          if (postProcessor && json.data) {
+            outputData = postProcessor(json.data);
+          }
+          console.log(JSON.stringify(outputData));
+        } catch (e) {
+          console.log('Response body:');
+          console.log(data);
+        }
+
+        console.log('');
+        resolve();
+      });
+    });
+
+    req.on('error', (error) => {
+      reject(error);
+    });
+
+    req.end();
+  });
+};
+
+const run = async () => {
+  await queryUsage(modelUsageUrl, 'Model usage');
+  await queryUsage(toolUsageUrl, 'Tool usage');
+  await queryUsage(quotaLimitUrl, 'Quota limit', false, processQuotaLimit);
+};
+
+run().catch((error) => {
+  console.error('Request failed:', error.message);
+  process.exit(1);
+});