Not in the top 1,000 by GitHub stars

OvOhao/auto-paper-collecter

📚🔭 Your personal research radar — an LLM-powered tool that auto-aggregates the latest papers for your keywords across arXiv / Crossref / Semantic Scholar / GitHub / RSS.

Claude Code Codex Research

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`skills/auto-paper-collecter/SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

54209b920ac4 → 54209b920ac4

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 54209b920ac4

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 54209b920ac4f2a551a7a5cf798e8cd681d374eb

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/OvOhao/auto-paper-collecter.git .hotskills/ovohao-auto-paper-collecter && git -C .hotskills/ovohao-auto-paper-collecter checkout --detach 54209b920ac4f2a551a7a5cf798e8cd681d374eb
# Copy each selected skill directory from .hotskills/ovohao-auto-paper-collecter into .claude/skills/<skill-name>/

Version-pinned installation · Codex

git clone --filter=blob:none --no-checkout https://github.com/OvOhao/auto-paper-collecter.git .hotskills/ovohao-auto-paper-collecter && git -C .hotskills/ovohao-auto-paper-collecter checkout --detach 54209b920ac4f2a551a7a5cf798e8cd681d374eb
# Copy each selected skill directory from .hotskills/ovohao-auto-paper-collecter into .agents/skills/<skill-name>/

64GitHub stars

0stars in 7 days

1skill in this repository

0commits in 30 days

Heat

0.3

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

auto-paper-collecter skills/auto-paper-collecter

How it works

auto-paper-collecter

When your agent uses it

Personal research-paper radar. Fetches the latest papers and code repos for the user's keyword subscriptions across arXiv, Crossref (IEEE/ACM), Semantic Scholar, GitHub, HuggingFace, Papers with Code and RSS; deduplicates against history; then YOU (the assistant) expand the queries, filter for computer-science relevance, write Chinese summaries, detect hot sub-fields, and emit a Markdown + HTML digest (optionally emailed). Use when the user asks to "run my paper radar / 文献雷达", "check for new papers", "what's new in my topics", "今天有什么新论文 / 最新文献", "today's research digest", or to configure their keyword subscriptions / sources / schedule.

What it loads into context

Frontmatter

159 tokens

Always available to the agent

SKILL.md

1,399 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Layout
Config — `state/config.json`
The run pipeline — follow IN ORDER
Notes

Scripts executed separately

scripts/common.py
scripts/fetch.py
scripts/notify.py
scripts/render.py

Files

../../.claude-plugin/marketplace.jsonasset660 bytes
../../.claude-plugin/marketplace.jsonasset660 bytes
../../.claude-plugin/plugin.jsonasset779 bytes
.gitignoreasset145 bytes
SKILL.mdcore5,413 bytes
SKILL.mdcore5,413 bytes
SKILL.mdcore5,413 bytes
SKILL.mdcore5,413 bytes
SKILL.mdcore5,413 bytes
SKILL.mdcore5,413 bytes
SKILL.mdcore5,413 bytes
SKILL.mdcore5,413 bytes
SKILL.mdcore5,413 bytes
scripts/common.pyruns2,446 bytes
scripts/fetch.pyruns11,119 bytes
scripts/notify.pyruns4,146 bytes
scripts/render.pyruns4,856 bytes
state/config.jsonasset390 bytes

Read SKILL.md


# auto-paper-collecter (skill)

A self-hosted research-literature radar that runs inside a coding agent.
**The Python scripts do only the deterministic work** (API fetch, dedup, render,
email). **YOU — the assistant running this skill — do all the judgement work**:
query expansion, computer-science relevance filtering, Chinese summaries, and
hot-topic synthesis. That means **no AI API key is needed** — whichever model is
running this skill (Claude in Claude Code, GPT in Codex, …) is the LLM.

## Layout
```
skill/
├── SKILL.md
├── scripts/   common.py · fetch.py · render.py · notify.py   (stdlib only)

View the complete source on GitHub

Skills included

auto-paper-collecter

Repository facts

License: MIT
Created: Jun 25, 2026
Last pushed: Jun 28, 2026
Forks: 7
Open issues: 2
Project activity: Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 9 notes

.claude-plugin/marketplace.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/auto-paper-collecter/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/auto-paper-collecter/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/auto-paper-collecter/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/auto-paper-collecter/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/auto-paper-collecter/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/auto-paper-collecter/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/auto-paper-collecter/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/auto-paper-collecter/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
52 network referencesin 7 files: auto-paper-collecter/scripts/fetch.py:18 auto-paper-collecter/scripts/notify.py:24 auto-paper-collecter/scripts/common.py:39 and 4 more
No hidden or obfuscated text
No instruction overrides
4 executable scriptsin 4 files: auto-paper-collecter/scripts/common.py:1 auto-paper-collecter/scripts/fetch.py:1 auto-paper-collecter/scripts/notify.py:1 and 1 more
14 references to secretsin 3 files: auto-paper-collecter/scripts/notify.py:51 auto-paper-collecter/scripts/fetch.py:97 auto-paper-collecter/SKILL.md:35
No requests to vote in Hot

Show all 70 signals by file

`.claude-plugin/marketplace.json`

Network accessline 13

"version": "1.0.0",       "license": "MIT",       "homepage": "https://github.com/OvOhao/auto-paper-collecter",

Network accessline 14

"license": "MIT",       "homepage": "https://github.com/OvOhao/auto-paper-collecter",       "keywords": ["arxiv", "research", "papers", "literature-review", "rag", "research-assistant"]

Network accessline 15

"homepage": "https://github.com/OvOhao/auto-paper-collecter",

`.claude-plugin/plugin.json`

Network accessline 4

"version": "1.0.0",   "author": { "name": "Penghao Jiang" },   "homepage": "https://github.com/OvOhao/auto-paper-collecter",

Network accessline 5

"author": { "name": "Penghao Jiang" },   "homepage": "https://github.com/OvOhao/auto-paper-collecter",   "repository": "https://github.com/OvOhao/auto-paper-collecter",

Network accessline 6

"homepage": "https://github.com/OvOhao/auto-paper-collecter",

Network accessline 7

"repository": "https://github.com/OvOhao/auto-paper-collecter",

`skills/auto-paper-collecter/SKILL.md`

Network accessline 27

- `domain`: the field to constrain relevance to (default `computer science`). - `sources`: toggle `arXiv / Crossref / Semantic Scholar / GitHub / HuggingFace / PapersWithCode / RSS`. - `lookback_days`: how far back to fetch (dedup stops rep

Network accessline 28

- `sources`: toggle `arXiv / Crossref / Semantic Scholar / GitHub / HuggingFace / PapersWithCode / RSS`. - `lookback_days`: how far back to fetch (dedup stops repeats anyway). - `max_per_source`, `rss_feeds`.

Network accessline 29

- `lookback_days`: how far back to fetch (dedup stops repeats anyway).

Access to secretsline 35
```
[Credential-related source omitted]
```

`skills/auto-paper-collecter/scripts/common.py`

Executable scriptline 1
```
Executable file
```

Network accessline 39

"RSS": True},         "lookback_days": 5, "max_per_source": 15,         "rss_feeds": ["http://export.arxiv.org/rss/cs.PL"],

Network accessline 40

"lookback_days": 5, "max_per_source": 15,         "rss_feeds": ["http://export.arxiv.org/rss/cs.PL"],     })

Network accessline 41

"rss_feeds": ["http://export.arxiv.org/rss/cs.PL"],

Network accessline 47

req = urllib.request.Request(url, headers={

Network accessline 49

"Accept-Encoding": "gzip", **(headers or {})})     try:         with urllib.request.urlopen(req, timeout=timeout) as r:

Network accessline 50

try:         with urllib.request.urlopen(req, timeout=timeout) as r:             raw = r.read()

Network accessline 51

with urllib.request.urlopen(req, timeout=timeout) as r:

`skills/auto-paper-collecter/scripts/fetch.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 18

A_NS = {"a": "http://www.w3.org/2005/Atom"}

Network accessline 31

def src_arxiv(query, n):     url = "http://export.arxiv.org/api/query?" + C.qs({

Network accessline 32

url = "http://export.arxiv.org/api/query?" + C.qs({

Network accessline 63

def src_crossref(query, n):     data = C.http_json("https://api.crossref.org/works?" + C.qs({

Network accessline 64

data = C.http_json("https://api.crossref.org/works?" + C.qs({

Network accessline 65

"query": query, "sort": "published", "order": "desc", "rows": n,         "select": "DOI,title,author,abstract,URL,container-title,published"}),         headers={"User-Agent": "auto-paper-collecter-skill/1.0 (https://github.com/)"})

Network accessline 66

"select": "DOI,title,author,abstract,URL,container-title,published"}),         headers={"User-Agent": "auto-paper-collecter-skill/1.0 (https://github.com/)"})     out = []

Network accessline 67

headers={"User-Agent": "auto-paper-collecter-skill/1.0 (https://github.com/)"})

Access to secretsline 97
```
[Credential-related source omitted]
```

Network accessline 98

if key:         headers["x-api-key"] = key     data = C.http_json("https://api.semanticscholar.org/graph/v1/paper/search?" + C.qs({

Network accessline 99

headers["x-api-key"] = key     data = C.http_json("https://api.semanticscholar.org/graph/v1/paper/search?" + C.qs({         "query": query, "limit": n, "fieldsOfStudy": "Computer Science",

Network accessline 100

data = C.http_json("https://api.semanticscholar.org/graph/v1/paper/search?" + C.qs({

Access to secretsline 129
```
[Credential-related source omitted]
```

Network accessline 133

data = C.http_json("https://api.github.com/search/repositories?" + C.qs({

Network accessline 157

def src_huggingface(query, n):     data = C.http_json("https://huggingface.co/api/papers/search?" + C.qs({"q": query}))

Network accessline 158

data = C.http_json("https://huggingface.co/api/papers/search?" + C.qs({"q": query}))

Network accessline 174

"title": " ".join((p.get("title") or "").split()),             "abstract": (p.get("summary") or "").strip(),             "url": f"https://huggingface.co/papers/{pid}" if pid else "",

Network accessline 175

"abstract": (p.get("summary") or "").strip(),             "url": f"https://huggingface.co/papers/{pid}" if pid else "",             "authors": [a.get("name", "") if isinstance(a, dict) else str(a)

Network accessline 176

"url": f"https://huggingface.co/papers/{pid}" if pid else "",

Network accessline 185

def src_paperswithcode(query, n):     data = C.http_json("https://paperswithcode.com/api/v1/papers/?" + C.qs(

Network accessline 186

data = C.http_json("https://paperswithcode.com/api/v1/papers/?" + C.qs(

`skills/auto-paper-collecter/scripts/notify.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 24

def _post_json(url, payload, timeout=20):     req = urllib.request.Request(url, data=json.dumps(payload).encode("utf-8"),

Network accessline 25

req = urllib.request.Request(url, data=json.dumps(payload).encode("utf-8"),

Network accessline 26

headers={"Content-Type": "application/json"})     with urllib.request.urlopen(req, timeout=timeout) as r:         return r.status

Network accessline 27

with urllib.request.urlopen(req, timeout=timeout) as r:

Network accessline 31

def _post_form(url, data, timeout=20):     req = urllib.request.Request(url, data=urllib.parse.urlencode(data).encode("utf-8"))

Network accessline 32

req = urllib.request.Request(url, data=urllib.parse.urlencode(data).encode("utf-8"))

Network accessline 33

with urllib.request.urlopen(req, timeout=timeout) as r:

Access to secretsline 51
```
[Credential-related source omitted]
```
Access to secretsline 52
```
[Credential-related source omitted]
```
Access to secretsline 53
```
[Credential-related source omitted]
```
Access to secretsline 54
```
[Credential-related source omitted]
```
Access to secretsline 66
```
[Credential-related source omitted]
```
Access to secretsline 70
```
[Credential-related source omitted]
```
Access to secretsline 83
```
[Credential-related source omitted]
```

Network accessline 84

if tok and chat:         try:             _post_json(f"https://api.telegram.org/bot{tok}/sendMessage",

Network accessline 85

try:             _post_json(f"https://api.telegram.org/bot{tok}/sendMessage",                        {"chat_id": chat, "text": text, "disable_web_page_preview": True})

Network accessline 86

_post_json(f"https://api.telegram.org/bot{tok}/sendMessage",

Access to secretsline 91
```
[Credential-related source omitted]
```
Access to secretsline 98
```
[Credential-related source omitted]
```
Network accessline 105
```
[Credential-related source omitted]
```
Access to secretsline 105
```
[Credential-related source omitted]
```

Network accessline 106

try:             _post_form(f"https://sctapi.ftqq.com/{os.environ['SERVERCHAN_KEY']}.send",                        {"title": f"文献雷达 · {C.today()}", "desp": text})

Network accessline 107
```
[Credential-related source omitted]
```
Access to secretsline 107
```
[Credential-related source omitted]
```

`skills/auto-paper-collecter/scripts/render.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/auto-paper-collecter/state/config.json`

Network accessline 13

"lookback_days": 5,   "max_per_source": 12,   "rss_feeds": ["http://export.arxiv.org/rss/cs.CL"]

Network accessline 14

"max_per_source": 12,   "rss_feeds": ["http://export.arxiv.org/rss/cs.CL"] }

Network accessline 15

"rss_feeds": ["http://export.arxiv.org/rss/cs.CL"]

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 9 facts

Contacts export.arxiv.org, which SKILL.md, the README and the plugin manifest do not mentionauto-paper-collecter/scripts/common.py:41High confidence
Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionauto-paper-collecter/scripts/fetch.py:18High confidence
Contacts export.arxiv.org, which SKILL.md, the README and the plugin manifest do not mentionauto-paper-collecter/scripts/fetch.py:32High confidence
Contacts api.crossref.org, which SKILL.md, the README and the plugin manifest do not mentionauto-paper-collecter/scripts/fetch.py:64High confidence
Contacts api.semanticscholar.org, which SKILL.md, the README and the plugin manifest do not mentionauto-paper-collecter/scripts/fetch.py:100High confidence
Contacts huggingface.co, which SKILL.md, the README and the plugin manifest do not mentionauto-paper-collecter/scripts/fetch.py:158High confidence
Contacts paperswithcode.com, which SKILL.md, the README and the plugin manifest do not mentionauto-paper-collecter/scripts/fetch.py:186High confidence
Contacts api.telegram.org, which SKILL.md, the README and the plugin manifest do not mentionauto-paper-collecter/scripts/notify.py:86High confidence
Contacts sctapi.ftqq.com, which SKILL.md, the README and the plugin manifest do not mentionauto-paper-collecter/scripts/notify.py:107High confidence

Signal confidence: 60 facts

Network access in prose of the SKILL.mdauto-paper-collecter/SKILL.md:27Low confidence
Network access in prose of the SKILL.mdauto-paper-collecter/SKILL.md:28Low confidence
Network access in prose of the SKILL.mdauto-paper-collecter/SKILL.md:29Low confidence
Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueauto-paper-collecter/SKILL.md:35Low confidence
Executable script in prose of a file that runsauto-paper-collecter/scripts/common.py:1Low confidence
Network access in code of a file that runsauto-paper-collecter/scripts/common.py:39High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/common.py:40High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/common.py:41High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/common.py:47High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/common.py:49High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/common.py:50High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/common.py:51High confidence
Executable script in code of a file that runsauto-paper-collecter/scripts/fetch.py:1High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:18High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:31High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:32High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:63High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:64High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:65High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:66High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:67High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueauto-paper-collecter/scripts/fetch.py:97Low confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:98High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:99High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:100High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueauto-paper-collecter/scripts/fetch.py:129Low confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:133High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:157High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:158High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:174High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:175High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:176High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:185High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/fetch.py:186High confidence
Executable script in code of a file that runsauto-paper-collecter/scripts/notify.py:1High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/notify.py:24High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/notify.py:25High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/notify.py:26High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/notify.py:27High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/notify.py:31High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/notify.py:32High confidence
Network access in code of a file that runsauto-paper-collecter/scripts/notify.py:33High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueauto-paper-collecter/scripts/notify.py:51Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueauto-paper-collecter/scripts/notify.py:52Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueauto-paper-collecter/scripts/notify.py:53Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueauto-paper-collecter/scripts/notify.py:54Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueauto-paper-collecter/scripts/notify.py:66Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueauto-paper-collecter/scripts/notify.py:70Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueauto-paper-collecter/scripts/notify.py:83Low confidence
Network access in code of a file that runsauto-paper-collecter/scripts/notify.py:84High confidence

and 10 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Manifest .claude-plugin/marketplace.json	`.claude/skills/<skill-name>/`
Codex	Native	Manifest AGENTS.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md skills/auto-paper-collecter/SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md skills/auto-paper-collecter/SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md skills/auto-paper-collecter/SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md skills/auto-paper-collecter/SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

OvOhao/auto-paper-collecter

History

skills/auto-paper-collecter/SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

auto-paper-collecter

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

.claude-plugin/marketplace.json

.claude-plugin/plugin.json

skills/auto-paper-collecter/SKILL.md

skills/auto-paper-collecter/scripts/common.py

skills/auto-paper-collecter/scripts/fetch.py

skills/auto-paper-collecter/scripts/notify.py

skills/auto-paper-collecter/scripts/render.py

skills/auto-paper-collecter/state/config.json

How the signals fit together

Works with

You might also use

zsyggg/paper-craft-skills

LeonChaoX/qinyan-academic-skills

stephenlzc/AI-Powered-Literature-Review-Skills

Jesseovo/PaperCash

LofiSu/recruiting-skills

federicodeponte/opendraft

`skills/auto-paper-collecter/SKILL.md`

`.claude-plugin/marketplace.json`

`.claude-plugin/plugin.json`

`skills/auto-paper-collecter/SKILL.md`

`skills/auto-paper-collecter/scripts/common.py`

`skills/auto-paper-collecter/scripts/fetch.py`

`skills/auto-paper-collecter/scripts/notify.py`

`skills/auto-paper-collecter/scripts/render.py`

`skills/auto-paper-collecter/state/config.json`