一键导入
module-management
Validate and maintain module registry. Use after adding new scripts, features, or modules to ensure proper documentation and integration.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Validate and maintain module registry. Use after adding new scripts, features, or modules to ensure proper documentation and integration.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Define extraction schema, extract study data from full texts, and store it in a structured database for meta-analysis. Use when moving from full-text collection to statistical analysis.
End-to-end AI-assisted meta-analysis pipeline orchestration from TOPIC.txt to final manuscript and reviewer responses. Use when the user provides a topic and wants the full meta-analysis workflow, tracking, and final paper.
Orchestrate agent team for meta-analysis pipeline. Creates team, spawns teammates, manages task list and handoffs between pipeline stages.
Intake a meta-analysis topic from TOPIC.txt, translate it into a PICO or PECO protocol, and define eligibility, outcomes, and search scope. Use when starting a new meta-analysis project or refining a research question.
Collect and manage full-text PDFs for included studies, track provenance, and prepare documents for extraction. Use when moving from screening to data extraction.
Conduct literature searches for meta-analysis using Python with uv, query PubMed and other databases, deduplicate results, and store round-based bibliographies with notes. Use when building or updating the evidence corpus.
| name | module-management |
| description | Validate and maintain module registry. Use after adding new scripts, features, or modules to ensure proper documentation and integration. |
Ensure every new script, template, or feature is properly registered across all documentation layers. Prevents "orphan scripts" (undocumented code) and "ghost references" (docs pointing to non-existent files).
ma-*/scripts/ or tooling/python/ma-*/references/Every user-facing script must be registered in 4 layers:
| Layer | File | Purpose | Required |
|---|---|---|---|
| 1. Module SKILL.md | ma-*/SKILL.md | Module-level documentation | Yes |
| 2. CLAUDE.md | CLAUDE.md | Agent instructions (commands reference) | Yes |
| 3. GETTING_STARTED.md | GETTING_STARTED.md | User-facing quick-start guide | Yes |
| 4. tests/README.md | tests/README.md | Test instructions and expected results | Recommended |
Place it in the correct module:
ma-{module}/scripts/{name}.pytooling/python/{name}.pyIn the script's parent module SKILL.md:
In the relevant <details> stage section:
uv run command with all flagsreferences/Add a user-friendly command example under the appropriate stage section.
Add a test command using test fixtures:
uv run ../../ma-{module}/scripts/{name}.py \
--input ../../tests/fixtures/... \
--output /tmp/test_output
# Expected: description of expected output
Add a row to the Expected Results table.
cd tooling/python
uv run ../../ma-end-to-end/scripts/validate_module_registry.py \
--root ../.. \
--out-md ../../09_qa/module_registry_report.md \
--out-json ../../09_qa/module_registry.json
Fix any errors before committing.
Run the new script against test fixtures or real data to verify it works:
cd tooling/python
uv run ../../ma-{module}/scripts/{name}.py --help
uv run ../../ma-{module}/scripts/{name}.py [args using test fixtures]
ma-{name}/ directory with:
SKILL.md (with YAML frontmatter: name, description)scripts/ directoryreferences/ directory (if templates needed)ma-end-to-end/SKILL.md pipeline stage listgrep -r "script_name.py" --include="*.md"rip not rm)# Basic check (warnings only for missing test docs)
uv run ../../ma-end-to-end/scripts/validate_module_registry.py --root ../..
# Strict check (all warnings become errors)
uv run ../../ma-end-to-end/scripts/validate_module_registry.py --root ../.. --strict
# Full report output
uv run ../../ma-end-to-end/scripts/validate_module_registry.py \
--root ../.. \
--out-md ../../09_qa/module_registry_report.md \
--out-json ../../09_qa/module_registry.json
0 = all checks pass1 = warnings only (missing test docs)2 = errors (orphan scripts or ghost references)When adding a new feature, use this checklist:
SKILL.md updated (Outputs, Resources, Workflow)CLAUDE.md updated (Commands Reference section)GETTING_STARTED.md updated (user-facing docs)tests/README.md updated (test command + expected results)validate_module_registry.py passes (exit code 0)