Workflow·Research

Paper Finder

Finds and organizes ML, CV, NLP, and AI research papers based on textual descriptions and keywords, with a persistent memory bank…

You say
Install this skill Read the source first Free Written by bchao1 · unverified publisher
Context cost
2k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 8.2 kBtext throughout, nothing executable
Licence
free to use
Last change
no release on file
Servers it uses
Noneruns standalone

What it does

Finds and organizes ML, CV, NLP, and AI research papers based on textual descriptions and keywords. Searches across arxiv, Google Scholar, Semantic Scholar, and top venues (CVPR, ECCV, ICCV, NeurIPS, ICML, ICLR, SIGGRAPH, SIGGRAPH Asia, EMNLP, ACL, CoRL, RSS, AAAI, IJCAI, WACV, BMVC, MICCAI, KDD, WWW, NAACL, COLM, and more). Maintains a persistent memory bank of discovered papers, a mind-graph linking papers to topics, individual paper summaries, and BibTeX entries.

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Workflow

Runs a procedure end to end.

literature-searchpapersbibtexarxiv
Filed under

Research

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md8.2 kB · 127 lines
--- name: paper-finder description: "Finds and organizes ML, CV, NLP, and AI research papers based on textual descriptions and keywords. Searches across arxiv, Google Scholar, Semantic Scholar, and top venues (CVPR, ECCV, ICCV, NeurIPS, ICML, ICLR, SIGGRAPH, SIGGRAPH Asia, EMNLP, ACL, CoRL, RSS, AAAI, IJCAI, WACV, BMVC, MICCAI, KDD, WWW, NAACL, COLM, and more). Maintains a persistent memory bank of discovered papers, a mind-graph linking papers to topics, individual paper summaries, and BibTeX entries. Use this skill whenever the user wants to find papers, search for related work, build a literature review, discover what exists on a topic, compare papers, organize references, generate BibTeX, or manage a research paper collection. Also use when the user mentions 'find me papers on...', 'what papers exist about...', 'related work for...', 'literature search', 'paper survey', or references any ML conference/venue by name." ---
6# Paper Finder
7
8Research paper discovery and organization agent. Find relevant ML/AI/CV/NLP papers, organize them into a persistent knowledge base, and connect them across topics.
9
10## Directory Structure
11
12Each search/topic gets its own folder. The folder name should be a short, descriptive kebab-case name for the search topic (e.g., mixed-resolution-diffusion/, video-generation-efficiency/). The user may also specify a custom folder name. Create on first use:
13
14```
15<topic-name>/
16 memory-bank.md # Master list of all discovered papers
17 mind-graph.md # Topic-paper connection graph
18 summaries/ # Per-paper .md files (via research-paper-analyst skill)
19 references.bib # Combined BibTeX for all papers
20 pdfs/ # Downloaded PDFs (only when user asks)
21 discussions/ # Paper comparison logs
22```
23
24If the user references an existing folder (e.g., @mixed-resolution-diffusion/), operate within that folder. If starting a new search without a specified folder, derive a descriptive name from the search query.
25
26## Searching for Papers
27
28### Web search is mandatory
29
30Use WebSearch and WebFetch for every search. Training knowledge alone misses recent papers (2024-2025+). If web tools are denied, retry once, then tell the user you need web access and explain what you'd search for.
31
32### Search strategy
33
34Run 2-3 parallel searches per query:
35
361. **Semantic Scholar API** via WebFetch: https://api.semanticscholar.org/graph/v1/paper/search?query=<query>&limit=20&fields=title,authors,year,venue,abstract,externalIds,citationCount,url
372. **WebSearch** with queries like <topic> paper <venue> <year> — good for Google Scholar results
383. **Venue-specific** when relevant: <topic> CVPR 2025, <topic> site:openreview.net
394. **Follow citations** on Semantic Scholar for highly relevant papers
40
41Relevant venues by field: CV (CVPR, ECCV, ICCV, WACV), ML (NeurIPS, ICML, ICLR, COLM, AAAI), NLP (ACL, EMNLP, NAACL), Graphics (SIGGRAPH, SIGGRAPH Asia, 3DV), Robotics (CoRL, RSS, ICRA), Medical (MICCAI), Preprints (arXiv cs.CV/CL/LG/AI).
42
43### Multi-angle search (mandatory)
44
45A single concept can be described using very different vocabulary depending on the angle. After the initial direct-concept searches, you MUST run at least one additional search round covering these three angles. Skipping these is the #1 cause of missed papers.
46
471. **Cross-domain synonyms**: The same idea often has established names in adjacent fields. Before searching, brainstorm 2-3 alternative terms from related domains (graphics, neuroscience, signal processing, HCI, information theory, etc.). For example, "mixed-resolution spatial tokens" in ML maps to "foveated rendering" in graphics, "saliency-driven attention" in neuroscience, or "non-uniform sampling" in signal processing. Search using these alternative vocabularies.
48
492. **Enabling mechanisms / building blocks**: Search for the specific technical components needed to *implement* the concept — not just the concept itself. Every novel representation requires changes to attention, positional encodings, loss functions, normalization, etc. For example, mixed-resolution tokens require modified RoPE/positional embeddings, cross-resolution attention alignment, and boundary handling. Search for these mechanism-level terms (e.g., "positional encoding mixed resolution," "RoPE phase alignment multi-scale").
50
513. **Motivating applications / problem framing**: Papers solving the same technical problem may frame it as a different goal. Search from the perspective of *why* someone would build this (efficiency, speed, perceptual quality, hardware constraints). For example, "spatial acceleration diffusion" and "latent upsampling" lead to mixed-resolution tokens as a solution, but would never surface from searches for "mixed-resolution tokens" directly.
52
53After initial results come in, also **follow the citation graph**: fetch the related-work section of 1-2 top-relevance papers and scan for references you haven't found yet.
54
55### Understand the concept precisely
56
57Before searching, understand the exact technical distinction the user cares about. If they describe a specific mechanism (e.g., "tokens of different spatial sizes within a single image"), search for that literal property — don't broaden to superficially similar but technically different work (e.g., cascaded pipelines, super-resolution).
58
59### Filtering
60
61- **Prioritize algorithmic contributions** over architecture/engineering/systems papers
62- **Prioritize recent work** (2024-2025+) — skip well-known basics (DiT, VQGAN, etc.) unless directly relevant
63- **Note citation counts** when available
64- **Tier results** by relevance to the user's specific concept
65
66## Memory Bank (memory-bank.md)
67
68Master record of all discovered papers. Append new entries, never overwrite. Read existing file before searching to avoid duplicates.
69
70```markdown
71# Paper Memory Bank
72Last updated: YYYY-MM-DD
73
74### [short-id] Paper Title
75- **Authors**: Author list
76- **Venue**: Conference/Journal, Year
77- **URL**: Link to paper
78- **Citations**: N (if known)
79- **Status**: discovered | summarized | analyzed
80- **Topics**: topic1, topic2
81- **Abstract**: 1-2 sentence description
82- **Notes**: Relevance observations
83---
84```
85
86## Mind Graph (mind-graph.md)
87
88Topic-centric hierarchy — NOT pairwise paper comparisons. Each topic has 1-3 umbrella/landmark papers plus other relevant work.
89
90```markdown
91# Mind Graph
92Last updated: YYYY-MM-DD
93
94### Topic Name
95- **Description**: One-line description
96- **Related topics**: [other topic], [other topic]
97- **Key papers**:
98 - [short-id] Paper Title (Venue Year) — why it's key for this topic
99- **Other relevant papers**:
100 - [short-id] Paper Title — one-line note
101```
102
103## BibTeX (references.bib)
104
105Write a single combined references.bib file with all papers. Use @inproceedings for conferences, @article for journals, @misc for arXiv preprints. Citation key = short-id.
106
107## Paper Summaries and Comparisons
108
109- **Summaries**: Invoke **research-paper-analyst** skill. Save to summaries/<short-id>.md. Only when user explicitly asks — don't auto-summarize.
110- **Comparisons**: Read existing summaries first (create if missing via research-paper-analyst), save discussion to discussions/<descriptive-name>.md.
111- **References to known papers**: Search summaries and memory bank first. Only re-read the original paper if the user explicitly asks.
112
113## PDF Management
114
115Do NOT download PDFs unless the user explicitly asks. When asked:
116
1171. **Read references.bib** to extract the arXiv eprint ID or URL for each paper. This is the canonical source — do NOT read memory-bank.md or other files just to find download URLs.
1182. Construct the PDF URL from the arXiv ID: https://arxiv.org/pdf/<eprint-id>
1193. Download via curl/WebFetch and save to pdfs/<short-id>.pdf
1204. Only fall back to memory-bank.md or web search if a paper has no entry in references.bib.
121
122## Interaction Flow
123
1241. **Search**: Run parallel web searches, present ranked list (title, venue, year, citations, one-line description)
1252. **Record**: Add papers to memory-bank.md, update mind-graph.md, write references.bib
1263. **Ask**: Whether user wants deeper analysis of any specific papers
127
In the file
SKILL.md1,097 words
Files1
Licence
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈230
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
1,820
on trigger
The instruction body, read only when the skill fires.
1.0%
of a 200k window
Ten skills this size would take about 10% of the window before you open a file.
050k100k150k200k context window

2k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption
Installsnone yet
Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for
Writes filesno
Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 8.2 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md8.2 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Paper Finder · 2k tokens when loaded npx mcprush@latest skill add bchao1/paper-finder

Writes to .claude/skills/paper-finder/ in the current project. Add --global to put it in your home directory instead, for every project.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/
Claude Desktop
ChatGPT
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok.grok/skills/
Zed.agents/skills/
Windsurf.windsurf/skills/
Agent SDK.claude/skills/
HTTP / API
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencebchao1/paper-finder

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v
  • No earlier releases have been published to the marketplace.
Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

BC
bchao1

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill