fix(skills): track current active skill explicitly and relocate to .agents/skills/

.agents/skills/python-scratchpad/SKILL.md

@@ -21,7 +21,7 @@ Workflow:
 1. If the task needs computation or a repeatable transformation, activate this skill.
 2. If you need examples, call `read_skill_file` for `references/examples.md`.
 3. Write a short Python script for the exact task.
-4. Prefer `run_python_script` with the script in its `script` argument.
+4. Prefer `execute_code`.
 5. Use the script output in the final answer.
 6. Keep scripts small and task-specific.
 

.agents/skills/rest-api-caller/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: rest-api-caller
 description: Call REST APIs from Python, parse JSON responses, and report the useful fields back to the user.
-allowed-tools: run_python_script execute_code
+allowed-tools: execute_code
 ---
 
 # REST API Caller
@@ -14,14 +14,14 @@ This skill is intended for:
 - endpoints where the user specifies headers, query params, or environment variable names
 
 Requirements:
-- The agent should have access to `run_python_script` or `execute_code`.
+- The agent should have access to `execute_code`.
 
 Workflow:
 1. Activate this skill when the task requires calling an API.
 2. If you need examples, call `read_skill_file` for `references/examples.md`.
 3. Write a short Python script that performs the request.
 4. Prefer the `requests` library if available in the environment.
-5. Prefer `run_python_script`; if it is unavailable, fall back to `execute_code`.
+5. Prefer `execute_code`.
 6. Parse the response and print only the fields needed for the final answer.
 7. Summarize the API result clearly for the user.
 

docs/user_guide/en/nodes/agent.md

@@ -33,14 +33,14 @@ The Agent node is the most fundamental node type in the DevAll platform, used to
 | Field | Type | Default | Description |
 |-------|------|---------|-------------|
 | `enabled` | bool | `false` | Enable Agent Skills discovery for this node |
-| `allow` | list[object] | `[]` | Optional allowlist of skills from the project-level `skills/` directory; each entry uses `name` |
+| `allow` | list[object] | `[]` | Optional allowlist of skills from the project-level `.agents/skills/` directory; each entry uses `name` |
 
 ### Agent Skills Notes
 
-- Skills are discovered from the fixed project-level `skills/` directory.
+- Skills are discovered from the fixed project-level `.agents/skills/` directory.
 - The runtime exposes two built-in skill tools: `activate_skill` and `read_skill_file`.
 - `read_skill_file` only works after the relevant skill has been activated.
-- Skill `SKILL.md` frontmatter may include optional `allowed-tools` using the Agent Skills spec format, for example `allowed-tools: run_python_script execute_code`.
+- Skill `SKILL.md` frontmatter may include optional `allowed-tools` using the Agent Skills spec format, for example `allowed-tools: execute_code`.
 - If a selected skill requires tools that are not bound on the node, that skill is skipped at runtime.
 - If no compatible skills remain, the agent is explicitly instructed not to claim skill usage.
 

docs/user_guide/zh/nodes/agent.md

@@ -33,14 +33,14 @@ Agent 节点是 DevAll 平台中最核心的节点类型，用于调用大语言
 | 字段 | 类型 | 默认值 | 说明 |
 |------|------|--------|------|
 | `enabled` | bool | `false` | 是否为该节点启用 Agent Skills |
-| `allow` | list[object] | `[]` | 可选的技能白名单，来源于项目级 `skills/` 目录；每个条目使用 `name` |
+| `allow` | list[object] | `[]` | 可选的技能白名单，来源于项目级 `.agents/skills/` 目录；每个条目使用 `name` |
 
 ### Agent Skills 说明
 
-- 技能统一从固定的项目级 `skills/` 目录中发现。
+- 技能统一从固定的项目级 `.agents/skills/` 目录中发现。
 - 运行时会暴露两个内置技能工具：`activate_skill` 和 `read_skill_file`。
 - `read_skill_file` 只有在对应技能已经激活后才可用。
-- 技能 `SKILL.md` 的 frontmatter 可以包含可选的 `allowed-tools`，格式遵循 Agent Skills 规范，例如 `allowed-tools: run_python_script execute_code`。
+- 技能 `SKILL.md` 的 frontmatter 可以包含可选的 `allowed-tools`，格式遵循 Agent Skills 规范，例如 `allowed-tools: execute_code`。
 - 如果某个已选择技能依赖的工具没有绑定到当前节点，该技能会在运行时被跳过。
 - 如果最终没有任何兼容技能可用，Agent 会被明确告知不要声称自己使用了技能。
 

entity/configs/node/skills.py

@@ -18,7 +18,7 @@ from entity.configs.base import (
 
 
 REPO_ROOT = Path(__file__).resolve().parents[3]
-DEFAULT_SKILLS_ROOT = (REPO_ROOT / "skills").resolve()
+DEFAULT_SKILLS_ROOT = (REPO_ROOT / ".agents" / "skills").resolve()
 def _discover_default_skills() -> List[tuple[str, str]]:
     if not DEFAULT_SKILLS_ROOT.exists() or not DEFAULT_SKILLS_ROOT.is_dir():
         return []

runtime/node/agent/skills/manager.py

@@ -11,7 +11,7 @@ from entity.tool_spec import ToolSpec
 
 
 REPO_ROOT = Path(__file__).resolve().parents[4]
-DEFAULT_SKILLS_ROOT = (REPO_ROOT / "skills").resolve()
+DEFAULT_SKILLS_ROOT = (REPO_ROOT / ".agents" / "skills").resolve()
 MAX_SKILL_FILE_BYTES = 128 * 1024
 
 
@@ -126,6 +126,7 @@ class AgentSkillManager:
         self._skills_by_name: Dict[str, SkillMetadata] | None = None
         self._skill_content_cache: Dict[str, str] = {}
         self._activation_state: Dict[str, bool] = {}
+        self._current_skill_name: str | None = None
         self._discovery_warnings: List[str] = []
 
     def discover(self) -> List[SkillMetadata]:
@@ -176,6 +177,7 @@ class AgentSkillManager:
             cached = skill.skill_file.read_text(encoding="utf-8")
             self._skill_content_cache[skill.name] = cached
         self._activation_state[skill.name] = True
+        self._current_skill_name = skill.name
         return {
             "skill_name": skill.name,
             "path": str(skill.skill_file),
@@ -214,10 +216,12 @@ class AgentSkillManager:
         return bool(self._activation_state.get(skill_name))
 
     def active_skill(self) -> SkillMetadata | None:
-        for skill in self.discover():
-            if self.is_activated(skill.name):
-                return skill
+        if self._current_skill_name is None:
             return None
+        skills = self._skills_by_name
+        if skills is None:
+            return None
+        return skills.get(self._current_skill_name)
 
     def discovery_warnings(self) -> List[str]:
         self.discover()