User Research Cookiy
cookiy-ai/user-research-skill
End-to-end user research assistant — qualitative and quantitative.
Maintain and visualize the user research preference profile.
Install Research Profile
$ npx skills add AlphaLab-USTC/ResearchClaw --skill research-profile -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AlphaLab-USTC/ResearchClaw research-profile --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/research-profile .claude/skills/research-profile && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "research-profile" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/research-profile into .claude/skills/research-profile/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-profile", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/research-profileType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AlphaLab-USTC/ResearchClaw --skill research-profile -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AlphaLab-USTC/ResearchClaw research-profile --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/research-profile .agents/skills/research-profile && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "research-profile" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/research-profile into .agents/skills/research-profile/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-profile", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AlphaLab-USTC/ResearchClaw --skill research-profile -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AlphaLab-USTC/ResearchClaw research-profile --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/research-profile .cursor/skills/research-profile && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "research-profile" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/research-profile into .cursor/skills/research-profile/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-profile", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AlphaLab-USTC/ResearchClaw.git --path skills/research-profile--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AlphaLab-USTC/ResearchClaw --skill research-profile -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AlphaLab-USTC/ResearchClaw research-profile --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/research-profile .gemini/skills/research-profile && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "research-profile" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/research-profile into .gemini/skills/research-profile/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-profile", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AlphaLab-USTC/ResearchClaw research-profileInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AlphaLab-USTC/ResearchClaw --skill research-profile -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/research-profile .github/skills/research-profile && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "research-profile" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/research-profile into .github/skills/research-profile/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-profile", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AlphaLab-USTC/ResearchClaw --skill research-profile -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AlphaLab-USTC/ResearchClaw research-profile --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/research-profile .opencode/skills/research-profile && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "research-profile" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/research-profile into .opencode/skills/research-profile/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-profile", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
research-profile- GitHub stars
- 134
- Token cost
- ~1.8k tokens
- SKILL.md length
- 622 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
Maintain and visualize the user research preference profile.
- Works in 4 steps: Ask the user (or parse from their… → Update the config file → Regenerate HTML profile → …
- User says: 更新我的研究画像
- SKILL.md covers ⚙️ Step 0 — Read the Research…, ⚠️ Error Handling and 🛠️ HTML Template Usage —…
- Reaches ar5iv.labs.arxiv.org
What it does
Research Profile is an agent skill from AlphaLab-USTC/ResearchClaw. Maintain and visualize the user research preference profile. Use when user says: 更新我的研究画像, 我的研究画像, research profile.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Product & Project Management, covering User research. The repository describes itself as: 上朝式科研：AI-powered research workflow showcase. The licence is MIT.
When your agent uses it
- User says: 更新我的研究画像
- Research profile
Example prompts
- “/research-profile”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Ask the user (or parse from their message) for updated
- Update the config file
- Regenerate HTML profile
- Confirm in chat
What it can do on your machine
Read from SKILL.md and the folder at commit 9d64c4b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
ar5iv.labs.arxiv.org
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Research Profile loads about 1.8k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 622 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from AlphaLab-USTC/ResearchClaw at commit 9d64c4b, republished under its MIT licence (© AlphaLab-USTC). 622 words, ~1,814 tokens.
Download SKILL.mdSave it as
.claude/skills/research-profile/SKILL.md (or your agent's skills folder).- name
- research-profile
- description
- Maintain and visualize the user research preference profile. Use when user says: 更新我的研究画像, 我的研究画像, research profile.
Research Taste Profile
⚙️ Step 0 — Read the Research Profile (Always First)
Before running any capability, load the user's research profile.
Location: ~/.openclaw/workspace/research-claw-config.md
If this file does not exist, use these defaults silently and mention at the end:
💡 想定制推荐兴趣？试试说「更新我的研究画像」
# Default profile (used when no config found)
research_direction: "Large language models, reinforcement learning, agentic AI"
seed_papers: []
keywords:
- large language models
- reinforcement learning
- agentic AI / AI agents
- retrieval-augmented generation
- multimodal models
whitelist_authors: []
learned_preferences:
accept: []
reject: []Config fields reference:
research_direction— free-text description of the user's research focusseed_papers— list of arXiv IDs the user considers gold-standard referenceskeywords— interest topics used for Paper Scout search querieswhitelist_authors— researcher names to prioritize in recommendationslearned_preferences.accept— keywords/topics user has explicitly likedlearned_preferences.reject— keywords/topics user has skipped or disliked
Goal: Maintain the user's research preference profile and render it as a visual HTML page.
Triggers: 更新我的研究画像 · 我的研究画像 · research profile · auto-learn (from Paper Scout feedback)
Config file format
Location: ~/.openclaw/workspace/research-claw-config.md
# ResearchClaw Config
# Auto-maintained by the agent. You can also edit manually.
research_direction: >
PhD researcher in large reasoning models and agentic memory systems.
Focus on RL-based training, long-context reasoning, and retrieval-augmented agents.
seed_papers:
- 2503.19823 # AutoRefine
- 2412.XXXXX # MemOCR
- 2502.XXXXX # ReMemR1
keywords:
- large language models
- reinforcement learning
- agentic memory
- long-context reasoning
- retrieval-augmented generation
- multimodal agents
whitelist_authors:
- Yaorui Shi
- An Zhang
- Xiang Wang
learned_preferences:
accept:
- RL-based reasoning
- verifiable rewards
- memory augmentation
reject:
- pure NLP classification
- computer vision only
- medical imaging
topic_stats:
- topic: "Reinforcement Learning" count: 12 pct: 35
- topic: "LLM Reasoning" count: 9 pct: 26
- topic: "Agentic AI" count: 7 pct: 20
- topic: "Multimodal" count: 4 pct: 12
- topic: "RAG" count: 2 pct: 7Operations
View profile (我的研究画像):
- Load config, regenerate HTML visual profile (see HTML step below)
- In chat, show a compact text summary:
🧠 你的研究画像 方向: {research_direction (first sentence)} 关键词: {keywords joined by · } 种子论文: {N} 篇 关注作者: {whitelist_authors joined by , } 偏好: +{accept topics} / −{reject topics}
Update profile (更新我的研究画像 [any description]):
- Ask the user (or parse from their message) for updated:
- Research direction description
- New keywords to add/remove
- New seed paper IDs to add
- New author names to whitelist
- Update the config file
- Regenerate HTML profile
- Confirm in chat
Auto-learn (triggered by feedback on Paper Scout results):
- Parse the user's feedback signal
- Update
learned_preferences.acceptor.reject - Update
topic_statsby incrementing count for relevant topics - Save config silently (no need for separate confirmation, just note briefly)
Generate HTML profile
Template location: {SKILL_DIR}/templates/research-profile.html
- Load with
read - Replace placeholders:
| Placeholder | Content |
|---|---|
{{USER_NAME}} | User's name from config or "Researcher" |
{{USER_TITLE}} | User's title/affiliation if known |
{{RESEARCH_DIRECTION}} | Full research direction text |
{{LAST_UPDATED}} | Today's date |
{{KEYWORD_COUNT}} | Total number of keywords |
{{KW_1}} … {{KW_10}} | Keyword names (fill up to 10) |
{{SEED_COUNT}} | Number of seed papers |
{{SEED_ID_1}}, {{SEED_TITLE_1}} | First seed paper ID + title |
{{SEED_ID_2}}, {{SEED_TITLE_2}} | Second seed paper ID + title |
{{SEED_ID_3}}, {{SEED_TITLE_3}} | Third seed paper ID + title |
{{AUTHOR_1}} … {{AUTHOR_5}} | Whitelist author names |
{{TOPIC_1}} … {{TOPIC_5}} | Top topic names |
{{CNT_1}} … {{CNT_5}} | Paper counts per topic |
{{PCT_1}} … {{PCT_5}} | Percentage per topic |
{{TOTAL_PAPERS}} | Total papers across all topics |
{{PREF_ACCEPT_1}}, {{PREF_ACCEPT_2}}, {{PREF_ACCEPT_3}} | Accept preference strings |
{{PREF_REJECT_1}}, {{PREF_REJECT_2}} | Reject preference strings |
- Save to
~/.openclaw/workspace/research-claw-output/research-profile.html - Report:
🧠 研究画像已更新 → ~/.openclaw/workspace/research-claw-output/research-profile.html
Show full SKILL.md (276 more words)Show less
⚠️ Error Handling
| Error | Handling |
|---|---|
| arXiv API returns empty results | Retry once with broader query; if still empty, note "arXiv API temporarily unavailable" |
| PDF tool times out | Fall back to abstract-only mode; note [Abstract only — PDF timeout] in the note |
| PDF tool returns error for a paper | Try fetching https://ar5iv.labs.arxiv.org/html/{ARXIV_ID} as HTML fallback |
| Config file missing | Use defaults silently; add a note at end: "💡 想定制？说「更新我的研究画像」" |
| Reading list JSON missing or malformed | Start fresh with an empty list; inform user: "未找到现有列表，已新建空列表" |
| Template file not found | Report the expected path and ask user to check installation |
| No papers in last 3 days | Extend to 7 days, note it: "（近3天论文较少，已扩展至7天）" |
| Fewer than 3 read papers for Idea Generator | Proceed anyway, but note the limitation |
| User provides PDF/DOI instead of arXiv | Try to extract arXiv ID from DOI or search arXiv by title |
🛠️ HTML Template Usage — General Guide
This section applies to Capabilities 2, 3, and 4.
Finding the skill directory
The skill directory (where templates live) is the folder containing this SKILL.md file.
Typical path: ~/.openclaw/skills/research-claw/
Templates are at: ~/.openclaw/skills/research-claw/templates/
If you cannot determine the skill directory, use exec to find it:
find ~/.openclaw/skills -name "paper-note.html" 2>/dev/null | head -1Output directory
Default: ~/.openclaw/workspace/research-claw-output/
Create if needed:
mkdir -p ~/.openclaw/workspace/research-claw-outputThe user can override the output directory by setting output_dir in their config.
Filling placeholders
- Load template with
readtool - In your reasoning, create a complete mapping of
{{PLACEHOLDER}}→ value - Perform a full string replacement for every placeholder
- If a placeholder has no content (e.g., no code URL), use a sensible default:
- URLs:
# - Text:
N/Aor an empty string - Counts:
0
- URLs:
- Write the result with
writetool
Never leave unfilled {{PLACEHOLDER}} tags in the output HTML.
© AlphaLab-USTC, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/research-profile of AlphaLab-USTC/ResearchClaw.
Open the folder on GitHubat commit 9d64c4b
Compare with similar skills
Research Profile next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Research Profile this skillAlphaLab-USTC/ResearchClaw | 134 | — | ~1.8k | Automated safety check: Pass | MIT | |
| User Research Cookiycookiy-ai/user-research-skill | 1.6k | — | ~954 | Automated safety check: Pass | MIT | |
| Fable DomainSahir619/fable-method | 2.3k | — | ~2.6k | Automated safety check: Pass | MIT | |
| Produck Feedback To Buildtryproduck/produck-skills | 510 | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Customer InterviewsRefoundAI/lenny-skills | 1.4k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Product Discovery Brief Builderopen-mercato/skills | 231 | — | ~3k | Automated safety check: Pass | MIT |
Similar skills
Fable Domain
Sahir619/fable-method
Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke…
Produck Feedback To Build
tryproduck/produck-skills
Pulls full in-context user feedback tickets through the Produck MCP server and turns them into an aligned product change instead of a guess.
Customer Interviews
RefoundAI/lenny-skills
Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.
Product Discovery Brief Builder
open-mercato/skills
Guides a product discovery conversation and writes product-brief.md with the problem, evidence, scope, decisions and the next open question, for existing, client or own ideas.
Ingest User Interview
egregore-labs/egregore
Analyze a user interview from Granola, pasted text, or a file into an evidence-backed briefing, journey insights, product findings, patterns, and actions.
More from AlphaLab-USTC/ResearchClaw
Idea Generator
AlphaLab-USTC/ResearchClaw
Analyze connections across read papers and generate actionable research ideas.
Paper Reader
AlphaLab-USTC/ResearchClaw
Deep-read an arXiv paper and generate structured Deep Note reading notes.
Paper Scout
AlphaLab-USTC/ResearchClaw
Discover and recommend latest arXiv papers matching user research interests.
Paper Writer
AlphaLab-USTC/ResearchClaw
Help write research papers: outline, draft sections, auto-review, and rebuttal.
Reading List
AlphaLab-USTC/ResearchClaw
Manage a personal reading list with kanban-style statuses and HTML dashboard.
Research Claw
AlphaLab-USTC/ResearchClaw
Complete AI research assistant with 6 core capabilities: paper discovery, deep reading notes, reading list management, research taste learning, idea generation, and paper writing.
Related
Categories
Questions about Research Profile
What does Research Profile do?
Maintain and visualize the user research preference profile. Research Profile is an agent skill from AlphaLab-USTC/ResearchClaw. Maintain and visualize the user research preference profile.
When should I use Research Profile?
Research Profile fits situations like: user says: 更新我的研究画像; research profile.
How do I install Research Profile in Claude Code?
Run `npx skills add AlphaLab-USTC/ResearchClaw --skill research-profile -a claude-code`. Or copy the skill folder (skills/research-profile in AlphaLab-USTC/ResearchClaw) into .claude/skills/research-profile in your project. Claude Code loads it when a task matches its description.
How do I install Research Profile in Codex?
Run `npx skills add AlphaLab-USTC/ResearchClaw --skill research-profile -a codex`. Or copy the skill folder (skills/research-profile in AlphaLab-USTC/ResearchClaw) into .agents/skills/research-profile in your project. Codex loads it when a task matches its description.
Can I use Research Profile in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AlphaLab-USTC/ResearchClaw --skill research-profile -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-profile, .gemini/skills/research-profile, .github/skills/research-profile and .opencode/skills/research-profile in your project.
What does Research Profile need to run?
SKILL.md names no scripts, command-line tools or credentials: Research Profile is instructions for the agent only.
Does Research Profile access the network?
SKILL.md names 1 domain. In commands or code: ar5iv.labs.arxiv.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Research Profile safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Research Profile use?
Research Profile is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Research Profile use?
About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Research Profile?
Skills that share tags, products or a category with Research Profile: User Research Cookiy (cookiy-ai/user-research-skill, 1.6k stars), Fable Domain (Sahir619/fable-method, 2.3k stars), Produck Feedback To Build (tryproduck/produck-skills, 510 stars) and Customer Interviews (RefoundAI/lenny-skills, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Research Profile?
AlphaLab-USTC (a GitHub user) maintains it in AlphaLab-USTC/ResearchClaw, which has 134 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on April 7, 2026.
Source: AlphaLab-USTC/ResearchClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.