基于 SOC 职业分类
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/benbrastmckie/nvim --skill skill-python-research命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | skill-python-research |
| description | Research Python development tasks. Invoke for Python-language research. |
| allowed-tools | Agent, Bash, Edit, Read, Write |
Thin wrapper that delegates Python research to python-research-agent subagent.
This skill activates when:
Validate task_number exists.
Source skill-base.sh once, then follow @.claude/context/patterns/skill-preflight-flow.md in
full for Stage 2 (preflight status update) and Stage 3 (marker creation):
source .claude/scripts/skill-base.sh
padded_num=$(printf "%03d" "$task_number")
skill_name="skill-python-research"
operation="research"
Skip memory retrieval if: clean_flag is true (from --clean).
if [ "$clean_flag" != "true" ]; then
memory_context=$(bash .claude/scripts/memory-retrieve.sh "$description" "$task_type" "$focus_prompt" 2>/dev/null) || memory_context=""
fi
Follow @.claude/context/patterns/lit-stage4a-flow.md in full to resolve --lit and set
lit_context, exactly as skill-researcher does. This skill supplies the shared block's
preconditions: lit_flag, description, orchestrator_mode (default "false" when unset).
Include task_context, focus_prompt, metadata_file_path. If memory_context and/or lit_context
from Stage 4a are non-empty, include them in the prompt (memory context first, then literature
briefing). Do NOT inject an empty block for either.
Use Agent tool with subagent_type: "python-research-agent".
Follow @.claude/context/patterns/skill-self-execution-fallback.md in full. This skill's success
status value for that block's write obligation is "researched".
The following stages MUST execute after work is complete, whether the work was done by a subagent or inline (Stage 5b). Do NOT skip these stages for any reason.
Read the metadata file from specs/{N}_{SLUG}/.return-meta.json, including memory_candidates.
Follow @.claude/context/patterns/skill-postflight-flow.md in full: field_name=**Research**,
next_field=**Plan**.
Return immediately if task not found.
Keep status as "researching", report error.
Non-blocking: Log failure but continue.
Brief text summary (NOT JSON).
Orchestrate multi-agent implementation with parallel phase execution. Spawns teammates for independent phases and coordinates dependent phases. Includes debugger teammate for error recovery.
Implement CSLib proofs with hard-mode contracts (H2 anti-analysis, H7 territory, H9 wrap-up with sorry_inventory). Invoke for --hard cslib implementation tasks.
Research CSLib formalization patterns with hard-mode contracts (H2 anti-analysis, H3 reference grounding with BibKey verification, H4 adversarial verification). Invoke for --hard cslib research tasks.