From dc18cf459144ce6b4912e027ac09e32329cd853b Mon Sep 17 00:00:00 2001 From: jilinchen Date: Fri, 10 Apr 2026 12:44:31 +0800 Subject: [PATCH] Fix missing frontmatter name fields and hardcoded paths in skills Add missing `name` field to all research-zh and research-en SKILL.md frontmatter (fixes #1). Replace hardcoded /home/weizhena/ paths with ~ and {project_dir} placeholders in research-deep skills (fixes #2). Co-Authored-By: Claude Opus 4.6 (1M context) --- skills/research-codex-en/research-deep/SKILL.md | 10 +++++----- skills/research-codex-zh/research-deep/SKILL.md | 10 +++++----- skills/research-en/research-add-fields/SKILL.md | 1 + skills/research-en/research-add-items/SKILL.md | 1 + skills/research-en/research-deep/SKILL.md | 9 +++++---- skills/research-en/research-report/SKILL.md | 1 + skills/research-en/research/SKILL.md | 1 + skills/research-zh/research-add-fields/SKILL.md | 1 + skills/research-zh/research-add-items/SKILL.md | 1 + skills/research-zh/research-deep/SKILL.md | 9 +++++---- skills/research-zh/research-report/SKILL.md | 1 + skills/research-zh/research/SKILL.md | 1 + 12 files changed, 28 insertions(+), 18 deletions(-) diff --git a/skills/research-codex-en/research-deep/SKILL.md b/skills/research-codex-en/research-deep/SKILL.md index f67c3dd..7bfdbcb 100644 --- a/skills/research-codex-en/research-deep/SKILL.md +++ b/skills/research-codex-en/research-deep/SKILL.md @@ -51,7 +51,7 @@ Read {fields_path} to get all field definitions ## Validation After completing JSON output, run validation script to ensure complete field coverage: -python /home/weizhena/.codex/skills/research/validate_json.py -f {fields_path} -j {output_path} +python ~/.codex/skills/research/validate_json.py -f {fields_path} -j {output_path} Task is complete only after validation passes. """ ``` @@ -61,10 +61,10 @@ Task is complete only after validation passes. ## Task Research name: GitHub Copilot category: International Product -description: Developed by Microsoft/GitHub, first mainstream AI coding assistant, ~40% market share, output structured JSON to /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +description: Developed by Microsoft/GitHub, first mainstream AI coding assistant, ~40% market share, output structured JSON to {project_dir}/results/GitHub_Copilot.json ## Field Definitions -Read /home/weizhena/AIcoding/aicoding-history/fields.yaml to get all field definitions +Read {project_dir}/fields.yaml to get all field definitions ## Output Requirements 1. Output JSON according to fields defined in fields.yaml @@ -73,11 +73,11 @@ Read /home/weizhena/AIcoding/aicoding-history/fields.yaml to get all field defin 4. All field values must be in English ## Output Path -/home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +{project_dir}/results/GitHub_Copilot.json ## Validation After completing JSON output, run validation script to ensure complete field coverage: -python /home/weizhena/.codex/skills/research/validate_json.py -f /home/weizhena/AIcoding/aicoding-history/fields.yaml -j /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +python ~/.codex/skills/research/validate_json.py -f {project_dir}/fields.yaml -j {project_dir}/results/GitHub_Copilot.json Task is complete only after validation passes. ``` diff --git a/skills/research-codex-zh/research-deep/SKILL.md b/skills/research-codex-zh/research-deep/SKILL.md index f67c3dd..7bfdbcb 100644 --- a/skills/research-codex-zh/research-deep/SKILL.md +++ b/skills/research-codex-zh/research-deep/SKILL.md @@ -51,7 +51,7 @@ Read {fields_path} to get all field definitions ## Validation After completing JSON output, run validation script to ensure complete field coverage: -python /home/weizhena/.codex/skills/research/validate_json.py -f {fields_path} -j {output_path} +python ~/.codex/skills/research/validate_json.py -f {fields_path} -j {output_path} Task is complete only after validation passes. """ ``` @@ -61,10 +61,10 @@ Task is complete only after validation passes. ## Task Research name: GitHub Copilot category: International Product -description: Developed by Microsoft/GitHub, first mainstream AI coding assistant, ~40% market share, output structured JSON to /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +description: Developed by Microsoft/GitHub, first mainstream AI coding assistant, ~40% market share, output structured JSON to {project_dir}/results/GitHub_Copilot.json ## Field Definitions -Read /home/weizhena/AIcoding/aicoding-history/fields.yaml to get all field definitions +Read {project_dir}/fields.yaml to get all field definitions ## Output Requirements 1. Output JSON according to fields defined in fields.yaml @@ -73,11 +73,11 @@ Read /home/weizhena/AIcoding/aicoding-history/fields.yaml to get all field defin 4. All field values must be in English ## Output Path -/home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +{project_dir}/results/GitHub_Copilot.json ## Validation After completing JSON output, run validation script to ensure complete field coverage: -python /home/weizhena/.codex/skills/research/validate_json.py -f /home/weizhena/AIcoding/aicoding-history/fields.yaml -j /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +python ~/.codex/skills/research/validate_json.py -f {project_dir}/fields.yaml -j {project_dir}/results/GitHub_Copilot.json Task is complete only after validation passes. ``` diff --git a/skills/research-en/research-add-fields/SKILL.md b/skills/research-en/research-add-fields/SKILL.md index 283610b..e5a09c9 100644 --- a/skills/research-en/research-add-fields/SKILL.md +++ b/skills/research-en/research-add-fields/SKILL.md @@ -1,4 +1,5 @@ --- +name: research-add-fields user-invocable: true description: Add field definitions to existing research outline. allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestion diff --git a/skills/research-en/research-add-items/SKILL.md b/skills/research-en/research-add-items/SKILL.md index 27b669c..32e0f7b 100644 --- a/skills/research-en/research-add-items/SKILL.md +++ b/skills/research-en/research-add-items/SKILL.md @@ -1,4 +1,5 @@ --- +name: research-add-items user-invocable: true description: Add items (research objects) to existing research outline. allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestion diff --git a/skills/research-en/research-deep/SKILL.md b/skills/research-en/research-deep/SKILL.md index 86b5847..19c4ebc 100644 --- a/skills/research-en/research-deep/SKILL.md +++ b/skills/research-en/research-deep/SKILL.md @@ -1,4 +1,5 @@ --- +name: research-deep user-invocable: true description: Read research outline, launch independent agent for each item for deep research. Disable task output. allowed-tools: Bash, Read, Write, Glob, WebSearch, Task @@ -62,10 +63,10 @@ Task is complete only after validation passes. ## Task Research name: GitHub Copilot category: International Product -description: Developed by Microsoft/GitHub, first mainstream AI coding assistant, ~40% market share, output structured JSON to /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +description: Developed by Microsoft/GitHub, first mainstream AI coding assistant, ~40% market share, output structured JSON to {project_dir}/results/GitHub_Copilot.json ## Field Definitions -Read /home/weizhena/AIcoding/aicoding-history/fields.yaml to get all field definitions +Read {project_dir}/fields.yaml to get all field definitions ## Output Requirements 1. Output JSON according to fields defined in fields.yaml @@ -74,11 +75,11 @@ Read /home/weizhena/AIcoding/aicoding-history/fields.yaml to get all field defin 4. All field values must be in English ## Output Path -/home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +{project_dir}/results/GitHub_Copilot.json ## Validation After completing JSON output, run validation script to ensure complete field coverage: -python ~/.claude/skills/research/validate_json.py -f /home/weizhena/AIcoding/aicoding-history/fields.yaml -j /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +python ~/.claude/skills/research/validate_json.py -f {project_dir}/fields.yaml -j {project_dir}/results/GitHub_Copilot.json Task is complete only after validation passes. ``` diff --git a/skills/research-en/research-report/SKILL.md b/skills/research-en/research-report/SKILL.md index 0ed386b..494c486 100644 --- a/skills/research-en/research-report/SKILL.md +++ b/skills/research-en/research-report/SKILL.md @@ -1,4 +1,5 @@ --- +name: research-report user-invocable: true description: Summarize deep research results into markdown report, cover all fields, skip uncertain values. allowed-tools: Read, Write, Glob, Bash, AskUserQuestion diff --git a/skills/research-en/research/SKILL.md b/skills/research-en/research/SKILL.md index 5c9fbcd..46f0962 100644 --- a/skills/research-en/research/SKILL.md +++ b/skills/research-en/research/SKILL.md @@ -1,4 +1,5 @@ --- +name: research user-invocable: true allowed-tools: Read, Write, Glob, WebSearch, Task, AskUserQuestion description: Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc. diff --git a/skills/research-zh/research-add-fields/SKILL.md b/skills/research-zh/research-add-fields/SKILL.md index a5e23f6..17b5b7d 100644 --- a/skills/research-zh/research-add-fields/SKILL.md +++ b/skills/research-zh/research-add-fields/SKILL.md @@ -1,4 +1,5 @@ --- +name: research-add-fields user-invocable: true description: 向现有调研outline补充字段定义。 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestion diff --git a/skills/research-zh/research-add-items/SKILL.md b/skills/research-zh/research-add-items/SKILL.md index aa161fb..729521d 100644 --- a/skills/research-zh/research-add-items/SKILL.md +++ b/skills/research-zh/research-add-items/SKILL.md @@ -1,4 +1,5 @@ --- +name: research-add-items user-invocable: true description: 向现有调研outline补充items（调研对象）。 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestion diff --git a/skills/research-zh/research-deep/SKILL.md b/skills/research-zh/research-deep/SKILL.md index 0ea5db2..36605fe 100644 --- a/skills/research-zh/research-deep/SKILL.md +++ b/skills/research-zh/research-deep/SKILL.md @@ -1,4 +1,5 @@ --- +name: research-deep user-invocable: true description: 读取调研outline，为每个item启动独立agent进行深度调研。禁用task output。 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task @@ -62,10 +63,10 @@ python ~/.claude/skills/research/validate_json.py -f {fields_path} -j {output_pa ## 任务 调研 name: GitHub Copilot category: 国际产品 -description: Microsoft/GitHub开发，首个主流AI编程助手，市场份额约40%，输出结构化JSON到 /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +description: Microsoft/GitHub开发，首个主流AI编程助手，市场份额约40%，输出结构化JSON到 {project_dir}/results/GitHub_Copilot.json ## 字段定义 -读取 /home/weizhena/AIcoding/aicoding-history/fields.yaml 获取所有字段定义 +读取 {project_dir}/fields.yaml 获取所有字段定义 ## 输出要求 1. 按fields.yaml定义的字段输出JSON @@ -74,11 +75,11 @@ description: Microsoft/GitHub开发，首个主流AI编程助手，市场份额 4. 所有字段值必须使用中文输出（调研过程可用英文，但最终JSON值为中文） ## 输出路径 -/home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +{project_dir}/results/GitHub_Copilot.json ## 验证 完成JSON输出后，运行验证脚本确保字段完整覆盖： -python ~/.claude/skills/research/validate_json.py -f /home/weizhena/AIcoding/aicoding-history/fields.yaml -j /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json +python ~/.claude/skills/research/validate_json.py -f {project_dir}/fields.yaml -j {project_dir}/results/GitHub_Copilot.json 验证通过后才算完成任务。 ``` diff --git a/skills/research-zh/research-report/SKILL.md b/skills/research-zh/research-report/SKILL.md index 91abcba..523c16a 100644 --- a/skills/research-zh/research-report/SKILL.md +++ b/skills/research-zh/research-report/SKILL.md @@ -1,4 +1,5 @@ --- +name: research-report user-invocable: true description: 将deep调研结果汇总为markdown报告，覆盖所有字段，跳过不确定值。 allowed-tools: Read, Write, Glob, Bash, AskUserQuestion diff --git a/skills/research-zh/research/SKILL.md b/skills/research-zh/research/SKILL.md index 13fbae9..708c428 100644 --- a/skills/research-zh/research/SKILL.md +++ b/skills/research-zh/research/SKILL.md @@ -1,4 +1,5 @@ --- +name: research user-invocable: true allowed-tools: Read, Write, Glob, WebSearch, Task, AskUserQuestion description: 对目标话题进行初步调研，生成调研outline。用于学术调研、benchmark调研、技术选型等场景。