BITE: Skill for Claude Code

.claude/skills/papers-collect-from-github-repo/SKILL.md

papers-collect-from-github-repo is a skill for Claude Code from RipeMangoBox/BITE. It costs 90 tokens per session (1,787 once invoked), scanned A, original, MIT.

A GitHub research tool that extracts paper candidates from repository READMEs or documentation, including curated lists, lab paper pages, conference lists, surveys, benchmarks, and leaderboards.

In plain words
What is it for?
Use it with a GitHub repository, an optional target file or directory, and optional keyword filters to produce rows matching `paper_list.csv`. It is for GitHub sources; ordinary web pages use a separate add-on.
Why use it?
GitHub paper lists use many formats, such as tables, bullets, HTML, and nested files. This tool creates one-off parsing logic for the specific repository instead of relying on one fixed format.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is RipeMangoBox/BITE's own configuration. It tells Claude Code how to work on BITE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything BITE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RipeMangoBox/BITE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/RipeMangoBox/BITE/main/.claude/skills/papers-collect-from-github-repo/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/RipeMangoBox/BITE

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for papers-collect-from-github-repo

README.md
[![agentmods](https://agentmods.dev/badge/skills/ripemangobox/bite/papers-collect-from-github-repo.svg)](https://agentmods.dev/skills/ripemangobox/bite/papers-collect-from-github-repo)
Your own site
<a href="https://agentmods.dev/skills/ripemangobox/bite/papers-collect-from-github-repo"><img src="https://agentmods.dev/badge/skills/ripemangobox/bite/papers-collect-from-github-repo.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,787 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.01787
Opus 5 $0.00045 $0.00894
Sonnet 5 $0.00018 $0.00357
Haiku 4.5 $0.00009 $0.00179

Measured 8d ago against content hash 469e41c5b785, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

papers-collect-from-github-repo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/papers-collect-from-github-repo/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Papers Collect From GitHub Repo

Purpose

Extract paper candidates from any GitHub repository and output rows aligned with obsidian-vault/paper_list.csv.

Supported repo types (non-exhaustive):

Type Example
Awesome / curated list Foruck/Awesome-Human-Motion
Survey companion repo ChenHsing/Awesome-Video-Diffusion-Models (CSUR)
Lab / group paper list showlab/showlab.github.io
Conference accepted papers ICLR/ICLR-2026-accepted-papers
Benchmark / leaderboard repo open-compass/opencompass
Topic-specific collection soraproducer/Awesome-Human-Interaction-Motion-Generation
Any repo with a structured paper list in README or docs

Because repo formats vary widely (Markdown tables, bullet lists, mixed HTML, nested docs, multiple files, etc.), this skill does not include fixed scripts. The agent writes one-off parsing logic for each target.

Input

User provides:

  • GitHub repo URL: e.g. https://github.com/Foruck/Awesome-Human-Motion
  • target file (optional): defaults to README.md; can be a specific path like docs/papers.md or a directory to scan
  • include/exclude keywords (optional): e.g. include motion generation, exclude survey
  • target category (optional): e.g. Motion_Generation_Text_Speech_Music_Driven
  • venue/year hint (optional): e.g. CVPR 2025 — used as default when venue cannot be parsed

Output Format

Output must align with the column format of obsidian-vault/paper_list.csv:

state,importance,paper_title,venue,project_link_or_github_link,paper_link,sort,pdf_path

Field notes:

Column Initial default Description
state Wait Later can be changed manually to Skip, or remain Wait for download
importance empty Later manually labeled as S/A/B/C
paper_title parsed from repo paper title
venue parsed from repo, fallback Unknown e.g., CVPR 2025, ICLR 2026; if only on open platforms, use arXiv YYYY
project_link_or_github_link project page or GitHub link prefer project page; if confirmed no open source, use N/A
paper_link arXiv / OpenReview link prefer arXiv abs link
sort section/category heading in source join words with _, e.g. Motion_Generation
pdf_path empty filled later by papers-download-from-list

Read the full file on GitHub · 149 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 149 lines · 90 tokens per session scan A 469e41c5b785

Subscribe to this mod's changes

papers-collect-from-github-repo is a skill published in the GitHub repository RipeMangoBox/BITE (61 stars, last pushed 25d ago), licensed MIT. It adds 90 tokens to every session and 1,787 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

results-report

A workflow for turning completed experiment analyses into a structured research report with findings, limitations, failures, and next steps.

Galaxy-Dawn/claude-scholar · 78 tokens

kaggle-learner

This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.

Galaxy-Dawn/claude-scholar · 69 tokens

academic-paper

An academic writing workflow covering planning, drafting, revising, reviewing, citations, abstracts, formatting, and disclosure statements. It supports several paper types, citation styles, and outputs such as LaTeX, DOCX, PDF, and Markdown.

yinqd3/workbuddy-skills · 137 tokens

academic-paper-reviewer

A multi-perspective review process for academic papers, which are research articles submitted to scholarly journals. It simulates an editor, several subject reviewers, a methods reviewer, and a critic to produce an editorial decision and revision plan.

yinqd3/workbuddy-skills · 120 tokens

using-academic-research

A collection of skills for academic research, from finding and checking sources to writing papers and simulating peer review. It is adapted from a Claude Code workflow and includes support for research reports, citations, LaTeX, and DOCX output when local tools are available.

yinqd3/workbuddy-skills · 75 tokens

asa-reader-layer-writer

Use when turning structured skill decomposition artifacts into beginner, expert, report, or Obsidian reading layers.

3yesore/LetUenforskills · 27 tokens