菜单
Run a measured improvement loop for a skill by defining a yes/no checklist, capturing a baseline, scoring candidate outputs, and logging each iteration's keep/revert decision. Use when a skill works inconsistently and you want evidence-driven iteration instead of random prompt edits.
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。
Open local review artifacts in Xiaoer Omia when users ask to open, preview, inspect, or review a file.
Build a static HTML report site from CSV, JSON, Markdown, or HTML inputs. Use when the user wants to turn existing data into a human-readable site, generate a data showcase page, create a static report website, or optionally publish the built site.
Add offline multilingual support to static HTML, small web projects, or reports by extracting text into tokens, maintaining language dictionaries, applying translated outputs, and optionally embedding a local language switcher. Use when the user asks for bilingual support, tokenizing Chinese copy, offline language switching, or i18n for reports and lightweight sites.
Unified entrypoint for Obsidian note operations such as cleanup, merge, lint/fix, meeting archive, daily rollover, and docs sync. Use when the user wants one command surface over an existing notes-tools repo instead of calling many atomic scripts by hand.
Test, tune, and regression-check LLM system prompts with a golden dataset. Use when the user wants to optimize a prompt, run prompt regression tests, manage `cases.yaml`, compare expected vs actual outputs, or follow a TDD workflow for prompts.
Evaluate whether a proposed skill is worth building by scoring it against five moat-oriented questions: differentiation, vertical fit, learning loop, user difficulty, and defensibility. Use when someone proposes a new skill and you want a fast build / deepen / reject decision before implementation.
基于 SOC 职业分类
| name | autoresearch |
| description | Run a measured improvement loop for a skill by defining a yes/no checklist, capturing a baseline, scoring candidate outputs, and logging each iteration's keep/revert decision. Use when a skill works inconsistently and you want evidence-driven iteration instead of random prompt edits. |
| version | 1.0.0 |
| author | Vivi |
| tags | ["research","iteration","evaluation","prompt","skill-quality"] |
| platforms | ["all"] |
| dependencies | ["python3"] |
Turn the method into a stable workflow. This skill does not pretend to be a fully autonomous optimizer yet; instead it gives the team a reproducible workspace for iterative skill improvement with checklist scoring, baseline capture, and iteration logs.
autoresearch/ workspace.Initialize a workspace:
python3 main.py init --root /tmp/autoresearch-demo --skill-name "landing-page-skill" --author Developer_Lead --questions "标题是否具体?|是否没有 buzzwords?|CTA 是否具体?"
Score one run:
python3 main.py score --skill-name "landing-page-skill" --answers y,n,y
Log one iteration:
python3 main.py log-iteration --root /tmp/autoresearch-demo --iteration iter-01 --change "Add explicit headline rule" --before 56 --after 72 --keep
autoresearch/ workspace with checklist.md, baseline.md, CHANGELOG.md, runbook.md, and optional JSONL scoring logsMinimum validation commands:
python3 -m py_compile main.py
python3 main.py score --skill-name "landing-page-skill" --answers y,n,y