v1.6 System Prompt 工程化 + 渐进式技能发现

重构 system prompt 为动态组装系统：PromptComposer 聚合核心身份、AGENTS.md
项目规范和 Skills 目录；新增 read_skill 工具实现技能按需加载；包重命名
internal/context -> internal/prompt 消除 stdlib 冲突。

internal/tools/read_skill.go

@@ -0,0 +1,59 @@
+package tools
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+
+	"go-tiny-claw/internal/prompt"
+	"go-tiny-claw/internal/schema"
+)
+
+type ReadSkillTool struct {
+	loader *prompt.SkillLoader
+}
+
+func NewReadSkillTool(workDir string) *ReadSkillTool {
+	return &ReadSkillTool{
+		loader: prompt.NewSkillLoader(workDir),
+	}
+}
+
+func (t *ReadSkillTool) Name() string {
+	return "read_skill"
+}
+
+func (t *ReadSkillTool) Definition() schema.ToolDefinition {
+	return schema.ToolDefinition{
+		Name:        t.Name(),
+		Description: "按技能名称加载完整的技能指令。在开始任务前可先用 read_skill 获取该技能的详细执行指南。支持技能: git-workflow",
+		InputSchema: map[string]interface{}{
+			"type": "object",
+			"properties": map[string]interface{}{
+				"name": map[string]interface{}{
+					"type":        "string",
+					"description": "要加载的技能名称，如 git-workflow",
+				},
+			},
+			"required": []string{"name"},
+		},
+	}
+}
+
+type readSkillArgs struct {
+	Name string `json:"name"`
+}
+
+func (t *ReadSkillTool) Execute(ctx context.Context, args json.RawMessage) (string, error) {
+	var input readSkillArgs
+	if err := json.Unmarshal(args, &input); err != nil {
+		return "", fmt.Errorf("参数解析失败: %w", err)
+	}
+
+	skill, err := t.loader.Load(input.Name)
+	if err != nil {
+		return "", err
+	}
+
+	return fmt.Sprintf("技能: %s\n描述: %s\n\n--- 技能正文 ---\n%s", skill.Name, skill.Description, skill.Body), nil
+}