fix: improve skill system prompts and simplify tool descriptions

- Simplify skill-creator installation flow
- Refine skill selection prompt for better matching
- Add parameter alias and env variable hints for tools
- Skip linkai-agent when unconfigured
- Create skills/ dir in workspace on init

README.md

@@ -90,7 +90,7 @@ bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
 
 项目支持国内外主流厂商的模型接口，可选模型及配置说明参考：[模型说明](#模型说明)。
 
-> 注：Agent模式下推荐使用以下模型，可根据效果及成本综合选择：MiniMAx(MiniMax-M2.1)、GLM(glm-4.7)、Qwen(qwen3-max)、Claude(claude-opus-4-6、claude-sonnet-4-5、claude-sonnet-4-0)、Gemini(gemini-3-flash-preview、gemini-3-pro-preview)
+> 注：Agent模式下推荐使用以下模型，可根据效果及成本综合选择：GLM(glm-4.7)、MiniMAx(MiniMax-M2.1)、Qwen(qwen3-max)、Claude(claude-opus-4-6、claude-sonnet-4-5、claude-sonnet-4-0)、Gemini(gemini-3-flash-preview、gemini-3-pro-preview)
 
 同时支持使用 **LinkAI平台** 接口，可灵活切换 OpenAI、Claude、Gemini、DeepSeek、Qwen、Kimi 等多种常用模型，并支持知识库、工作流、插件等Agent能力，参考 [接口文档](https://docs.link-ai.tech/platform/api)。
 
@@ -173,7 +173,7 @@ pip3 install -r requirements-optional.txt
 <details>
 <summary>2. 其他配置</summary>
 
-+ `model`: 模型名称，Agent模式下推荐使用 `MiniMax-M2.1`、`glm-4.7`、`qwen3-max`、`claude-opus-4-6`、`claude-sonnet-4-5`、`claude-sonnet-4-0`、`gemini-3-flash-preview`、`gemini-3-pro-preview`，全部模型名称参考[common/const.py](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py)文件
++ `model`: 模型名称，Agent模式下推荐使用 `glm-4.7`、`MiniMax-M2.1`、`qwen3-max`、`claude-opus-4-6`、`claude-sonnet-4-5`、`claude-sonnet-4-0`、`gemini-3-flash-preview`、`gemini-3-pro-preview`，全部模型名称参考[common/const.py](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py)文件
 + `character_desc`：普通对话模式下的机器人系统提示词。在Agent模式下该配置不生效，由工作空间中的文件内容构成。
 + `subscribe_msg`：订阅消息，公众号和企业微信channel中请填写，当被订阅时会自动回复， 可使用特殊占位符。目前支持的占位符有{trigger_prefix}，在程序中它会自动替换成bot的触发词。
 </details>

agent/prompt/builder.py

@@ -157,96 +157,66 @@ def _build_identity_section(base_persona: Optional[str], language: str) -> List[
 
 
 def _build_tooling_section(tools: List[Any], language: str) -> List[str]:
-    """构建工具说明section"""
+    """Build tooling section with concise tool list and call style guide."""
+    # One-line summaries for known tools (details are in the tool schema)
+    core_summaries = {
+        "read": "读取文件内容",
+        "write": "创建或覆盖文件",
+        "edit": "精确编辑文件",
+        "ls": "列出目录内容",
+        "grep": "搜索文件内容",
+        "find": "按模式查找文件",
+        "bash": "执行shell命令",
+        "terminal": "管理后台进程",
+        "web_search": "网络搜索",
+        "web_fetch": "获取URL内容",
+        "browser": "控制浏览器",
+        "memory_search": "搜索记忆",
+        "memory_get": "读取记忆内容",
+        "env_config": "管理API密钥和技能配置",
+        "scheduler": "管理定时任务和提醒",
+        "send": "发送文件给用户",
+    }
+
+    # Preferred display order
+    tool_order = [
+        "read", "write", "edit", "ls", "grep", "find",
+        "bash", "terminal",
+        "web_search", "web_fetch", "browser",
+        "memory_search", "memory_get",
+        "env_config", "scheduler", "send",
+    ]
+
+    # Build name -> summary mapping for available tools
+    available = {}
+    for tool in tools:
+        name = tool.name if hasattr(tool, 'name') else str(tool)
+        available[name] = core_summaries.get(name, "")
+
+    # Generate tool lines: ordered tools first, then extras
+    tool_lines = []
+    for name in tool_order:
+        if name in available:
+            summary = available.pop(name)
+            tool_lines.append(f"- {name}: {summary}" if summary else f"- {name}")
+    for name in sorted(available):
+        summary = available[name]
+        tool_lines.append(f"- {name}: {summary}" if summary else f"- {name}")
+
     lines = [
         "## 工具系统",
         "",
-        "你可以使用以下工具来完成任务。工具名称是大小写敏感的，请严格按照列表中的名称调用。",
+        "可用工具（名称大小写敏感，严格按列表调用）:",
+        "\n".join(tool_lines),
         "",
-        "### 可用工具",
+        "工具调用风格：",
+        "",
+        "- 在多步骤任务、敏感操作或用户要求时简要解释决策过程",
+        "- 持续推进直到任务完成，完成后向用户报告结果。",
+        "- 回复中涉及密钥、令牌等敏感信息必须脱敏。",
         "",
     ]
-    
+
-    # 工具分类和排序
-    tool_categories = {
-        "文件操作": ["read", "write", "edit", "ls", "grep", "find"],
-        "命令执行": ["bash", "terminal"],
-        "网络搜索": ["web_search", "web_fetch", "browser"],
-        "记忆系统": ["memory_search", "memory_get"],
-        "其他": []
-    }
-    
-    # 构建工具映射
-    tool_map = {}
-    tool_descriptions = {
-        "read": "读取文件内容",
-        "write": "创建新文件或完全覆盖现有文件（会删除原内容！追加内容请用 edit）。注意：单次 write 内容不要超过 10KB，超大文件请分步创建",
-        "edit": "精确编辑文件（追加、修改、删除部分内容）",
-        "ls": "列出目录内容",
-        "grep": "在文件中搜索内容",
-        "find": "按照模式查找文件",
-        "bash": "执行shell命令",
-        "terminal": "管理后台进程",
-        "web_search": "网络搜索（使用搜索引擎）",
-        "web_fetch": "获取URL内容",
-        "browser": "控制浏览器",
-        "memory_search": "搜索记忆文件",
-        "memory_get": "获取记忆文件内容",
-        "calculator": "计算器",
-        "current_time": "获取当前时间",
-    }
-    
-    for tool in tools:
-        tool_name = tool.name if hasattr(tool, 'name') else str(tool)
-        tool_desc = tool.description if hasattr(tool, 'description') else tool_descriptions.get(tool_name, "")
-        tool_map[tool_name] = tool_desc
-    
-    # 按分类添加工具
-    for category, tool_names in tool_categories.items():
-        category_tools = [(name, tool_map.get(name, "")) for name in tool_names if name in tool_map]
-        if category_tools:
-            lines.append(f"**{category}**:")
-            for name, desc in category_tools:
-                if desc:
-                    lines.append(f"- `{name}`: {desc}")
-                else:
-                    lines.append(f"- `{name}`")
-                del tool_map[name]  # 移除已添加的工具
-            lines.append("")
-    
-    # 添加其他未分类的工具
-    if tool_map:
-        lines.append("**其他工具**:")
-        for name, desc in sorted(tool_map.items()):
-            if desc:
-                lines.append(f"- `{name}`: {desc}")
-            else:
-                lines.append(f"- `{name}`")
-        lines.append("")
-    
-    # 工具使用指南
-    lines.extend([
-        "### 工具调用风格",
-        "",
-        "默认规则: 对于常规、低风险的工具调用，直接调用即可，无需叙述。",
-        "",
-        "需要叙述的情况:",
-        "- 多步骤、复杂的任务",
-        "- 敏感操作（如删除文件）",
-        "- 用户明确要求解释过程",
-        "",
-        "叙述要求: 保持简洁、信息密度高，避免重复显而易见的步骤。",
-        "",
-        "完成标准:",
-        "- 确保用户的需求得到实际解决，而不仅仅是制定计划。",
-        "- 当任务需要多次工具调用时，持续推进直到完成, 解决完后向用户报告结果或回复用户的问题",
-        "- 每次工具调用后，评估是否已获得足够信息来推进或完成任务",
-        "- 避免重复调用相同的工具和相同参数获取相同的信息，除非用户明确要求",
-        "",
-        "**安全提醒**: 回复中涉及密钥、令牌、密码等敏感信息时，必须脱敏处理，禁止直接显示完整内容。",
-        "",
-    ])
-    
     return lines
 
 
@@ -265,16 +235,17 @@ def _build_skills_section(skill_manager: Any, tools: Optional[List[Any]], langua
                 break
     
     lines = [
-        "## 技能系统",
+        "## 技能系统（mandatory）",
         "",
         "在回复之前：扫描下方 <available_skills> 中的 <description> 条目。",
         "",
-        f"- 如果恰好有一个技能明确适用：使用 `{read_tool_name}` 工具读取其 <location> 路径下的 SKILL.md 文件，然后遵循它",
+        f"- 如果恰好有一个技能(Skill)明确适用：使用 `{read_tool_name}` 读取其 <location> 处的 SKILL.md，然后严格遵循它",
-        "- 如果多个技能都适用：选择最具体的一个，然后读取并遵循",
+        "- 如果多个技能都适用则选择最匹配的一个，如果没有明确适用的则不要读取任何 SKILL.md",
-        "- 如果没有明确适用的：不要读取任何 SKILL.md",
+        "- 读取 SKILL.md 后直接按其指令执行，无需多余的预检查",
         "",
-        "**约束**: 永远不要一次性读取多个技能；只在选择后再读取。",
+        "**注意**: 永远不要一次性读取多个技能，只在选择后再读取。技能和工具不同，必须先读取其SKILL.md并按照文件内容运行。",
         "",
+        "以下是可用技能："
     ]
     
     # 添加技能列表（通过skill_manager获取）

agent/prompt/workspace.py

@@ -57,6 +57,10 @@ def ensure_workspace(workspace_dir: str, create_templates: bool = True) -> Works
     
     # 创建memory子目录
     os.makedirs(memory_dir, exist_ok=True)
+
+    # 创建skills子目录 (for workspace-level skills installed by agent)
+    skills_dir = os.path.join(workspace_dir, "skills")
+    os.makedirs(skills_dir, exist_ok=True)
     
     # 如果需要，创建模板文件
     if create_templates:

agent/protocol/agent_stream.py

@@ -708,7 +708,6 @@ class AgentStreamExecutor:
             if not tool_id:
                 import uuid
                 tool_id = f"call_{uuid.uuid4().hex[:24]}"
-                logger.debug(f"⚠️ Tool call missing ID for '{tc.get('name')}', generated fallback: {tool_id}")
 
             try:
                 # Safely get arguments, handle None case

agent/skills/formatter.py

@@ -23,18 +23,15 @@ def format_skills_for_prompt(skills: List[Skill]) -> str:
         return ""
     
     lines = [
-        "\n\nThe following skills provide specialized instructions for specific tasks.",
-        "Use the read tool to load a skill's file when the task matches its description.",
         "",
         "<available_skills>",
     ]
-    
+
     for skill in visible_skills:
         lines.append("  <skill>")
         lines.append(f"    <name>{_escape_xml(skill.name)}</name>")
         lines.append(f"    <description>{_escape_xml(skill.description)}</description>")
         lines.append(f"    <location>{_escape_xml(skill.file_path)}</location>")
-        lines.append(f"    <base_dir>{_escape_xml(skill.base_dir)}</base_dir>")
         lines.append("  </skill>")
     
     lines.append("</available_skills>")

agent/skills/loader.py

@@ -188,16 +188,14 @@ class SkillLoader:
         import json
         
         config_path = os.path.join(skill_dir, "config.json")
-        template_path = os.path.join(skill_dir, "config.json.template")
         
-        # Try to load config.json or fallback to template
+        # Without config.json, skip this skill entirely (return empty to trigger exclusion)
-        config_file = config_path if os.path.exists(config_path) else template_path
+        if not os.path.exists(config_path):
-        
+            logger.debug(f"[SkillLoader] linkai-agent skipped: no config.json found")
-        if not os.path.exists(config_file):
+            return ""
-            return default_description
         
         try:
-            with open(config_file, 'r', encoding='utf-8') as f:
+            with open(config_path, 'r', encoding='utf-8') as f:
                 config = json.load(f)
             
             apps = config.get("apps", [])

agent/tools/bash/bash.py

@@ -20,10 +20,11 @@ class Bash(BaseTool):
     name: str = "bash"
     description: str = f"""Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last {DEFAULT_MAX_LINES} lines or {DEFAULT_MAX_BYTES // 1024}KB (whichever is hit first). If truncated, full output is saved to a temp file.
 
-IMPORTANT SAFETY GUIDELINES:
+ENVIRONMENT: All API keys from env_config are auto-injected. Use $VAR_NAME directly.
-- You can freely create, modify, and delete files within the current workspace
+
-- For operations outside the workspace or potentially destructive commands (rm -rf, system commands, etc.), always explain what you're about to do and ask for user confirmation first
+SAFETY:
-- When in doubt, describe the command's purpose and ask for permission before executing"""
+- Freely create/modify/delete files within the workspace
+- For destructive and out-of-workspace commands, explain and confirm first"""
 
     params: dict = {
         "type": "object",
@@ -92,13 +93,7 @@ IMPORTANT SAFETY GUIDELINES:
                     logger.debug("[Bash] python-dotenv not installed, skipping .env loading")
                 except Exception as e:
                     logger.debug(f"[Bash] Failed to load .env: {e}")
-            
+
-            # Debug logging
-            logger.debug(f"[Bash] CWD: {self.cwd}")
-            logger.debug(f"[Bash] Command: {command[:500]}")
-            logger.debug(f"[Bash] OPENAI_API_KEY in env: {'OPENAI_API_KEY' in env}")
-            logger.debug(f"[Bash] SHELL: {env.get('SHELL', 'not set')}")
-            logger.debug(f"[Bash] Python executable: {sys.executable}")
             # getuid() only exists on Unix-like systems
             if hasattr(os, 'getuid'):
                 logger.debug(f"[Bash] Process UID: {os.getuid()}")

agent/tools/env_config/env_config.py

@@ -202,7 +202,8 @@ class EnvConfig(BaseTool):
                         "key": key,
                         "value": self._mask_value(value),
                         "description": description,
-                        "exists": True
+                        "exists": True,
+                        "note": f"Value is masked for security. In bash, use ${key} directly — it is auto-injected."
                     })
                 else:
                     return ToolResult.success({

agent/tools/read/read.py

@@ -67,10 +67,12 @@ class Read(BaseTool):
         :param args: Contains file path and optional offset/limit parameters
         :return: File content or error message
         """
-        path = args.get("path", "").strip()
+        # Support 'location' as alias for 'path' (LLM may use it from skill listing)
+        path = args.get("path", "") or args.get("location", "")
+        path = path.strip() if isinstance(path, str) else ""
         offset = args.get("offset")
         limit = args.get("limit")
-        
+
         if not path:
             return ToolResult.fail("Error: path parameter is required")
         

config-template.json

@@ -1,6 +1,6 @@
 {
   "channel_type": "web",
-  "model": "MiniMax-M2.1",
+  "model": "glm-4.7",
   "claude_api_key": "",
   "claude_api_base": "https://api.anthropic.com/v1",
   "open_ai_api_key": "",

skills/bocha-search/SKILL.md

@@ -1,91 +0,0 @@
----
-name: bocha-search
-description: High-quality web search with AI-optimized results. Use when user needs to search the internet for current information, news, or research topics.
-homepage: https://open.bocha.cn/
-metadata:
-  emoji: 🔍
-  requires:
-    bins: ["curl"]
-    env: ["BOCHA_API_KEY"]
-  primaryEnv: "BOCHA_API_KEY"
----
-
-# Bocha Search
-
-High-quality web search powered by Bocha AI, optimized for AI consumption. Returns web pages, images, and detailed metadata.
-
-## Setup
-
-This skill requires a Bocha API key. If not configured:
-
-1. Visit https://open.bocha.cn to get an API key
-2. Set the key using: `env_config(action="set", key="BOCHA_API_KEY", value="your-key")`
-3. Or manually add to `~/cow/.env`: `BOCHA_API_KEY=your-key`
-
-## Usage
-
-**Important**: Scripts are located relative to this skill's base directory.
-
-When you see this skill in `<available_skills>`, note the `<base_dir>` path.
-
-```bash
-# General pattern:
-bash "<base_dir>/scripts/search.sh" "<query>" [count] [freshness] [summary]
-
-# Parameters:
-# - query: Search query (required)
-# - count: Number of results (1-50, default: 10)
-# - freshness: Time range filter (default: noLimit)
-#   Options: noLimit, oneDay, oneWeek, oneMonth, oneYear, YYYY-MM-DD..YYYY-MM-DD
-# - summary: Include text summary (true/false, default: false)
-```
-
-## Examples
-
-### Basic search
-```bash
-bash "<base_dir>/scripts/search.sh" "latest AI news"
-```
-
-### Search with more results
-```bash
-bash "<base_dir>/scripts/search.sh" "Python tutorials" 20
-```
-
-### Search recent content with summary
-```bash
-bash "<base_dir>/scripts/search.sh" "阿里巴巴ESG报告" 10 oneWeek true
-```
-
-### Search specific date range
-```bash
-bash "<base_dir>/scripts/search.sh" "tech news" 15 "2025-01-01..2025-02-01"
-```
-
-## Response Format
-
-The API returns structured data compatible with Bing Search API:
-
-**Web Pages** (in `data.webPages.value`):
-- `name`: Page title
-- `url`: Page URL
-- `snippet`: Short description
-- `summary`: Full text summary (if requested)
-- `siteName`: Website name
-- `siteIcon`: Website icon URL
-- `datePublished`: Publication date (UTC+8)
-- `language`: Page language
-
-**Images** (in `data.images.value`):
-- `contentUrl`: Image URL
-- `hostPageUrl`: Source page URL
-- `width`, `height`: Image dimensions
-- `thumbnailUrl`: Thumbnail URL
-
-## Notes
-
-- **Optimized for AI**: Results include summaries and structured metadata
-- **Time range**: Use `noLimit` for best results (algorithm auto-optimizes time range)
-- **Timeout**: 30 seconds
-- **Rate limits**: Check your API plan at https://open.bocha.cn
-- **Response format**: Compatible with Bing Search API for easy integration

skills/bocha-search/scripts/search.sh

@@ -1,75 +0,0 @@
-#!/usr/bin/env bash
-# Bocha Web Search API wrapper
-# API Docs: https://open.bocha.cn/
-
-set -euo pipefail
-
-query="${1:-}"
-count="${2:-10}"
-freshness="${3:-noLimit}"
-summary="${4:-false}"
-
-if [ -z "$query" ]; then
-    echo '{"error": "Query is required", "usage": "bash search.sh <query> [count] [freshness] [summary]"}'
-    exit 1
-fi
-
-if [ -z "${BOCHA_API_KEY:-}" ]; then
-    echo '{"error": "BOCHA_API_KEY environment variable is not set", "help": "Visit https://open.bocha.cn to get an API key"}'
-    exit 1
-fi
-
-# Validate count (1-50)
-if ! [[ "$count" =~ ^[0-9]+$ ]] || [ "$count" -lt 1 ] || [ "$count" -gt 50 ]; then
-    count=10
-fi
-
-# Build JSON request body
-request_body=$(cat <<EOF
-{
-  "query": "$query",
-  "count": $count,
-  "freshness": "$freshness",
-  "summary": $summary
-}
-EOF
-)
-
-# Call Bocha API
-response=$(curl -sS --max-time 30 \
-    -X POST \
-    -H "Authorization: Bearer $BOCHA_API_KEY" \
-    -H "Content-Type: application/json" \
-    -H "Accept: application/json" \
-    -d "$request_body" \
-    "https://api.bocha.cn/v1/web-search" 2>&1)
-
-curl_exit_code=$?
-
-if [ $curl_exit_code -ne 0 ]; then
-    echo "{\"error\": \"Failed to call Bocha API\", \"details\": \"$response\"}"
-    exit 1
-fi
-
-# Simple JSON validation - check if response starts with { or [
-if [[ ! "$response" =~ ^[[:space:]]*[\{\[] ]]; then
-    echo "{\"error\": \"Invalid JSON response from API\", \"response\": \"$response\"}"
-    exit 1
-fi
-
-# Extract API code using grep and sed (basic JSON parsing)
-api_code=$(echo "$response" | grep -o '"code"[[:space:]]*:[[:space:]]*[0-9]*' | grep -o '[0-9]*' | head -1)
-
-# If code extraction failed or code is not 200, check for error
-if [ -n "$api_code" ] && [ "$api_code" != "200" ]; then
-    # Try to extract error message
-    api_msg=$(echo "$response" | grep -o '"msg"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/"msg"[[:space:]]*:[[:space:]]*"\(.*\)"/\1/' | head -1)
-    if [ -z "$api_msg" ]; then
-        api_msg="Unknown error"
-    fi
-    echo "{\"error\": \"API returned error\", \"code\": $api_code, \"message\": \"$api_msg\"}"
-    exit 1
-fi
-
-# Return the full response
-echo "$response"

skills/skill-creator/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: skill-creator
-description: Create or update skills. Use when designing, structuring, or packaging skills with scripts, references, and assets. COW simplified version - skills are used locally in workspace.
+description: Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
 license: Complete terms in LICENSE.txt
 ---
 
@@ -93,9 +93,16 @@ Do NOT create auxiliary documentation files:
 
 **Critical Rule**: Only create files that the agent will actually execute (scripts) or that are too large for SKILL.md (references). Documentation, examples, and guides ALL belong in SKILL.md.
 
-## Skill Creation Process
+## Installing a Skill from URL
 
-**COW Simplified Version** - Skills are used locally, no packaging/sharing needed.
+1. Fetch the URL content (curl or web-fetch skill)
+2. Extract `name` from YAML frontmatter
+3. Create directory `<workspace>/skills/<name>/` and save content as `SKILL.md`
+4. Check the saved SKILL.md for an installation/setup section — if it defines additional steps (e.g., downloading scripts, installing dependencies), execute them; otherwise installation is complete
+
+The `<workspace>` is the working directory from the "工作空间" section.
+
+## Skill Creation Process (from scratch)
 
 1. **Understand** - Clarify use cases with concrete examples
 2. **Plan** - Identify needed scripts, references, assets
@@ -181,11 +188,13 @@ scripts/init_skill.py <skill-name> --path <output-directory> [--resources script
 Examples:
 
 ```bash
-scripts/init_skill.py my-skill --path ~/cow/skills
+scripts/init_skill.py my-skill --path <workspace>/skills
-scripts/init_skill.py my-skill --path ~/cow/skills --resources scripts,references
+scripts/init_skill.py my-skill --path <workspace>/skills --resources scripts,references
-scripts/init_skill.py my-skill --path ~/cow/skills --resources scripts --examples
+scripts/init_skill.py my-skill --path <workspace>/skills --resources scripts --examples
 ```
 
+Where `<workspace>` is your workspace directory shown in the "工作空间" section of the system prompt.
+
 The script:
 
 - Creates the skill directory at the specified path
@@ -195,7 +204,7 @@ The script:
 
 After initialization, customize the SKILL.md and add resources as needed. If you used `--examples`, replace or delete placeholder files.
 
-**Important**: Always create skills in workspace directory (`~/cow/skills`), NOT in project directory.
+**Important**: Always create skills in workspace skills directory (`<workspace>/skills`), NOT in project directory. Check the "工作空间" section for the actual workspace path.
 
 ### Step 4: Edit the Skill
 
@@ -335,7 +344,7 @@ scripts/quick_validate.py <path/to/skill-folder>
 Example:
 
 ```bash
-scripts/quick_validate.py ~/cow/skills/weather-api
+scripts/quick_validate.py <workspace>/skills/weather-api
 ```
 
 Validation checks: