🗑️ remove(tsl_syntax): drop platform-specific agent metadata

docs/superpowers/plans/2026-07-12-tsl-syntax-reference-logic-hardening.md

@@ -12,6 +12,7 @@
 
 - Do not execute any TSL interpreter or validate TSL runtime behavior.
 - Do not modify `skills/tsl-api-reference/**`.
+- Do not add platform-specific adapters such as `agents/openai.yaml`; discovery metadata belongs in `SKILL.md` frontmatter.
 - Preserve unrelated dirty-worktree changes.
 - Use `apply_patch` for repository file edits.
 - Follow RED → GREEN → REFACTOR for every behavior change.
@@ -283,7 +284,6 @@ git commit -m ':sparkles: feat(tsl-syntax): improve natural language topic routi
 
 **Files:**
 - Modify: `skills/tsl-syntax-reference/SKILL.md`
-- Modify: `skills/tsl-syntax-reference/agents/openai.yaml`
 - Modify: `skills/tsl-syntax-reference/references/10_runtime_context_and_with.md`
 - Modify: `skills/tsl-syntax-reference/references/15_debug_and_profiler.md`
 - Modify: `skills/tsl-syntax-reference/references/22_matrix_deep_dive.md`
@@ -348,7 +348,7 @@ Expected: new discovery, two-stage, map and boundary assertions fail.
 - Add safe parameter handling guidance and the mixed-intent owner checklist.
 - Expand run-environment guidance to questions and execution.
 - Clarify code-block identity and environment verification.
-- Expand `agents/openai.yaml` discovery language without embedding workflow shortcuts.
+- Keep discovery metadata exclusively in the portable `SKILL.md` frontmatter.
 
 - [ ] **Step 4: Sanitize concept-map summaries**
 
@@ -371,7 +371,6 @@ Expected: all targeted tests and `--check` pass.
 ```bash
 git add \
   skills/tsl-syntax-reference/SKILL.md \
-  skills/tsl-syntax-reference/agents/openai.yaml \
   skills/tsl-syntax-reference/references/10_runtime_context_and_with.md \
   skills/tsl-syntax-reference/references/15_debug_and_profiler.md \
   skills/tsl-syntax-reference/references/22_matrix_deep_dive.md \

docs/superpowers/specs/2026-07-12-tsl-syntax-reference-logic-hardening-design.md

@@ -18,6 +18,7 @@
 - 概念地图只表达自然语言职责，不输出链接、代码或可照写语法。
 - `--check` 覆盖每页职责、标题层级、Section ID、代码块身份和地图完整性。
 - 用 Python 和文档测试验证全部改动，不运行 TSL。
+- Skill 包不包含 `agents/openai.yaml` 等平台专用适配文件；通用发现元数据只写在 `SKILL.md` frontmatter。
 
 ## 非目标
 
@@ -129,6 +130,7 @@ Summary: 一行纯文本摘要。
 ## SKILL.md 与发现元数据
 
 - frontmatter 补充 `Tinysoft`、`天软`、`TS-SQL`、公式/策略脚本和常见语法报错触发词。
+- 不新增 OpenAI、Claude、Gemini 等平台专用元数据；各运行时直接读取通用 frontmatter。
 - 主流程只展示两阶段检索命令。
 - 增加安全传参要求：不得未经引用把用户文本拼进 shell。
 - 增加混合意图检查表和 API scope × 解释器兼容性阻断条件。

skills/tsl-syntax-reference/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "TSL Syntax Reference"
-  short_description: "检索 Tinysoft/天软 TSL、TSF 与 TS-SQL 语法规则"
-  default_prompt: "Use $tsl-syntax-reference to retrieve candidate sections, then fetch the exact TSL/TSF syntax section before answering."

test/cli/test_install_skills.py

@@ -113,7 +113,7 @@ skills = ["tsl-syntax-reference"]
             skill = target / "skills" / "tsl-syntax-reference"
             self.assertEqual(result.returncode, 0, msg=result.stdout + result.stderr)
             self.assertTrue((skill / "SKILL.md").is_file())
-            self.assertTrue((skill / "agents" / "openai.yaml").is_file())
+            self.assertFalse((skill / "agents" / "openai.yaml").exists())
             self.assertTrue((skill / "scripts" / "lookup.py").is_file())
             self.assertFalse((skill / "references" / "index.md").exists())