菜单
Import .md dialog files (Claude.ai exports, custom markdown conversations) to create or update advisor profiles. Use when the user wants to import a conversation file, update an advisor with new dialog data, or add .md chat history to the advisor library. Invoked with /import-dialog.
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
Use when running the autoresearch loop for a project whose survey and validator gates have passed — executes batches of attempts (one git worktree + LOG.md each, scored only by the validator under a hard time limit), then reflects, reports, and re-plans; continues autonomously while authorized_rounds remain, otherwise stops for user review. Stage 4 of the autoresearch pipeline.
Use when setting the goal and building the validator for an autoresearch topic — defines the publishable bar with the user, splits dev instances from a sealed gitignored holdout, builds a Docker-canonical strict environment (recorded fallback allowed), implements the validate CLI with rich JSON errors, and passes the strictness self-test against negative controls. Owns the validator gate. Stage 3 of the autoresearch pipeline.
Use when building the evidence base for a chosen autoresearch topic — maps the insight areas needed to propose new ideas, downloads references to cover them via download-ref, distills each area into research/INSIGHTS.md for user selection, builds a structured domain database and pinned reference implementations, and catalogs all algorithms/software in research/CATALOG.md. Owns the survey gate. Stage 2 of the autoresearch pipeline.
Use when starting or resuming an autoresearch project — reads research/STATE.md to find the current stage of the pipeline (topics → db → validator → run), verifies the previous stage's gate artifacts exist on disk, and routes to the matching stage skill. Triggers on "start autoresearch", "resume autoresearch", "autoresearch status", "what stage is my research project at".
Use when choosing research topics within a domain that suit autoresearch and defining their score metrics — brainstorms candidates, scores each on machine-checkable success, cheap per-attempt evaluation, iteration headroom, and publishability, lets the user pick, then derives primary/guard metrics (with computation cost and gaming risks) for each chosen topic and writes everything to topics.md. Stage 1 of the autoresearch pipeline; invoked via the autoresearch dispatcher or directly with a domain.
Use when building a slide deck in Typst + Touying for a scientific talk, lecture, or project briefing — ships a browsable zoo of color themes, layout templates, and gadgets (callouts, theory boxes, CeTZ diagrams, pin annotations) that compose into projector-safe slides. Distinct from slide-writing (HTML, QudeLeap brand) and paper-writer (full manuscripts).
| name | import-dialog |
| description | Import .md dialog files (Claude.ai exports, custom markdown conversations) to create or update advisor profiles. Use when the user wants to import a conversation file, update an advisor with new dialog data, or add .md chat history to the advisor library. Invoked with /import-dialog. |
Import exported markdown dialog files, convert them to the standard dialog JSON format, then hand off to the existing advisor-profile pipeline. This skill is intentionally a thin wrapper around conversation-dump, soul-extraction, and incarnate so their taxonomies and profile rules stay single-sourced.
Ask the user for:
.md dialog files to import. Accept glob patterns (e.g., docs/*.md).advisors/index.md) or a new advisor name. If new, also gather background info (field, themes, skills) for the profile header.Run the bundled parser to convert .md files into standard JSON turns:
python3 <skill-base-dir>/../conversation-dump/parse_md_dialog.py parse <file.md>
For multiple files:
python3 <skill-base-dir>/../conversation-dump/parse_md_dialog.py batch <directory> --outdir docs/dialog/md-import/raw/
Save JSON outputs to docs/dialog/md-import/raw/. Verify each file parsed correctly (non-zero turns).
Follow conversation-dump Phases 2–3 on docs/dialog/md-import/raw/:
conversation-dump only.docs/dialog/md-import/<topic>/.docs/dialog/md-import/<topic>/.For each selected topic, follow soul-extraction Phases 2–4 and write thinking-pattern.md + master-thinking.md to docs/dialog/md-import/<topic>/.
Use incarnate Step 3–4 to synthesize or update advisors/<slug>/profile.md from the new soul-extraction outputs. Preserve existing topic sections that were not re-analyzed, and update advisors/index.md.
Present the updated profile to the user for review:
Your advisor profile has been updated at
advisors/<slug>/profile.md. The new analysis added/updated the following topic sections: [list]. Please review — raw dialog data stays indocs/dialog/md-import/and is not included in the profile.
The parser (parse_md_dialog.py) auto-detects these role marker patterns:
| Format | Human marker | Assistant marker |
|---|---|---|
| Claude.ai export | ## **Human** | ## **Claude** |
| Bold variant | ## **User** | ## **Assistant** |
| Plain heading | ## Human | ## Claude or ## Assistant |
| Colon format | **Human:** | **Claude:** or **Assistant:** |
Messages are separated by --- lines (ignored during parsing). Nested markdown headings within assistant responses are preserved as content.