New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Corpus Search

by lamm-mit in lamm-mit/scienceclaw

Semantic search over critical minerals PDF corpus — rare earth, lithium, cobalt, nickel supply chain, trade policy, extraction, and materials research via Pinecone

Apache-2.0Auto-check passedDocuments & Office

Install Corpus Search

skills CLI
$ npx skills add lamm-mit/scienceclaw --skill corpus-search -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lamm-mit/scienceclaw corpus-search --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/corpus-search .claude/skills/corpus-search && rm -rf skills-src

Use ~/.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/

Facts

Skill name
corpus-search
GitHub stars
244
Token cost
~776 tokens
SKILL.md length
202 words
Files
4 (incl. scripts)
Skills in repo
86
Repo updated
First seen
Licence
Apache-2.0

At a glance

Semantic search over critical minerals PDF corpus — rare earth, lithium, cobalt, nickel supply chain, trade policy, extraction, and materials research via Pinecone

  • Tasks that involve Vector databases
  • SKILL.md covers Usage, Parameters, Ingestion and Notes
  • Runs Python scripts from its folder; calls python3; needs PINECONE_API_KEY
  • Tasks that involve Supply chain security

What it does

Corpus Search is an agent skill from lamm-mit/scienceclaw. Semantic search over critical minerals PDF corpus — rare earth, lithium, cobalt, nickel supply chain, trade policy, extraction, and materials research via Pinecone

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/ingest_corpus.py` and `scripts/search_corpus.py`).

It sits in Documents & Office, covering Vector databases, Supply chain security and PDF. It works with Pinecone. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Vector databases
  • Tasks that involve Supply chain security
  • Tasks that involve PDF

Example prompts

  • “/corpus-search”

Requirements

  • Python 3
  • A credential in PINECONE_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit ab9aba1. 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

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • PINECONE_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Corpus Search loads about 776 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 202 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~776

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); the scripts in this folder are not scanned.

SKILL.md

The full file from lamm-mit/scienceclaw at commit ab9aba1, republished under its Apache-2.0 licence (© lamm-mit). 202 words, ~776 tokens.

Download SKILL.mdSave it as .claude/skills/corpus-search/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
corpus-search
description
Semantic search over critical minerals PDF corpus — rare earth, lithium, cobalt, nickel supply chain, trade policy, extraction, and materials research via Pinecone

Corpus Search — Critical Minerals PDF Corpus

Semantic search over a local collection of critical minerals PDFs (USGS, UN Comtrade, World Bank, SEC, WTO, Mindat, MinCan reports). Documents are chunked, embedded with llama-text-embed-v2, and stored in a Pinecone index for fast similarity search.

Usage

Search the corpus:
bash
python3 {baseDir}/scripts/search_corpus.py --query "rare earth separation techniques"
Filter by commodity:
bash
python3 {baseDir}/scripts/search_corpus.py --query "supply chain risks" --commodity lithium
Filter by source organization:
bash
python3 {baseDir}/scripts/search_corpus.py --query "trade flows" --source Comtrade
Reranked results (higher quality):
bash
python3 {baseDir}/scripts/search_corpus.py --query "cobalt extraction" --rerank --top-k 20
JSON output:
bash
python3 {baseDir}/scripts/search_corpus.py --query "graphite processing" --format json

Parameters

ParameterDescriptionDefault
--querySemantic search queryRequired
--commodityFilter by commodity keyword (e.g., lithium, cobalt, rare earth)-
--sourceFilter by source organization (e.g., USGS, Comtrade, SEC)-
--top-kNumber of results to retrieve10
--rerankEnable reranking with pinecone-rerank-v0false
--formatOutput format: summary, detailed, jsonsummary
--index-namePinecone index namescienceclaw-minerals-corpus

Ingestion

Before searching, ingest PDFs into the Pinecone index:

bash
# Dry run — list PDFs that would be ingested:
python3 {baseDir}/scripts/ingest_corpus.py --corpus-dir ~/critical-minerals-data/ --dry-run

# Ingest all PDFs:
python3 {baseDir}/scripts/ingest_corpus.py --corpus-dir ~/critical-minerals-data/

# Force re-ingest (ignore manifest):
python3 {baseDir}/scripts/ingest_corpus.py --corpus-dir ~/critical-minerals-data/ --force-reingest
Ingestion Parameters
ParameterDescriptionDefault
--corpus-dirDirectory containing PDFs~/critical-minerals-data/
--index-namePinecone index namescienceclaw-minerals-corpus
--force-reingestRe-ingest all files, ignoring manifestfalse
--dry-runList files without ingestingfalse

Notes

  • Requires PINECONE_API_KEY environment variable
  • PDFs are chunked at ~600 tokens with 100-token overlap
  • Source organization is auto-detected from directory name (e.g., usgs/, sec/)
  • Commodity is auto-detected via keyword scanning
  • Incremental updates: only new or modified files are re-ingested (SHA-256 manifest)
  • Reranking uses pinecone-rerank-v0 for higher quality results at the cost of latency

© lamm-mit, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in skills/corpus-search of lamm-mit/scienceclaw.

  • SKILL.md
  • requirements.txt
  • scripts/ingest_corpus.py
  • scripts/search_corpus.py

Open the folder on GitHubat commit ab9aba1

Compare with similar skills

Corpus Search 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.

Corpus Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Corpus Search this skilllamm-mit/scienceclaw244—~776Automated safety check: PassApache-2.0
Cognee Community Packagestopoteretes/cognee32k—~1.2kAutomated safety check: PassApache-2.0
Paper Interpretationdigoal/blog8.6k—~1.5kAutomated safety check: PassGPL-2.0
Pinecone Vector DatabaseOrchestra-Research/AI-Research-SKILLs13k5 repos~2kAutomated safety check: PassMIT
RAG Implementationwshobson/agents40k9 repos~1.1kAutomated safety check: PassMIT
Hunt RAG Vectorelementalsouls/Claude-BugHunter4.8k—~2.6kAutomated safety check: PassMIT

Similar skills

  • Cognee Community Packages

    topoteretes/cognee

    Guide to using and contributing cognee community packages: database adapters, data-source connectors, custom tasks and retrievers, and Keywords AI observability.

    32k GitHub stars~1.2k tokensUpdated today
    DatabasesAuto-check passed

  • Paper Interpretation

    digoal/blog

    从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读，并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated today
    Documents & OfficeAuto-check passed

  • Pinecone Vector Database

    Orchestra-Research/AI-Research-SKILLs

    Shows how to use Pinecone, a managed vector database, for production RAG, semantic search and recommendations: indexes, upserts, queries, filters and namespaces.

    13k GitHub starsUsed in 5 repos~2k tokens
    DatabasesAuto-check passed

  • RAG Implementation

    wshobson/agents

    Build retrieval-augmented generation systems: pick a vector database and embedding model, choose retrieval and reranking strategies, and start from a LangGraph pipeline.

    40k GitHub starsUsed in 9 repos~1.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Hunt RAG Vector

    elementalsouls/Claude-BugHunter

    Hunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus poisoning that survives across sessions and users (distinct from…

    4.8k GitHub stars~2.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Using Vector Databases

    ancoleman/ai-design-components

    Vector database implementation for AI/ML applications, semantic search, and RAG systems.

    526 GitHub stars~3.5k tokensUpdated 10 mo ago
    DatabasesAuto-check passed

More from lamm-mit/scienceclaw

All 86 skills in this repo

  • Fred Economic Data

    lamm-mit/scienceclaw

    Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources.

    244 GitHub starsUsed in 4 repos~3k tokens
    Auto-check passed

  • Drug Research

    lamm-mit/scienceclaw

    Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.

    244 GitHub starsUsed in 3 repos~1.7k tokens
    Auto-check passed

  • Imaging Data Commons

    lamm-mit/scienceclaw

    Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index.

    244 GitHub starsUsed in 5 repos~11k tokens
    Auto-check passed

  • Rowan

    lamm-mit/scienceclaw

    Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.

    244 GitHub starsUsed in 4 repos~3.1k tokens
    Auto-check: warnings

  • Infographics

    lamm-mit/scienceclaw

    Create professional infographics using Nano Banana Pro AI with smart iterative refinement.

    244 GitHub starsUsed in 6 repos~4.4k tokens
    Auto-check: notes

  • Disease Research

    lamm-mit/scienceclaw

    Generate comprehensive disease research reports using 100+ ToolUniverse tools.

    244 GitHub stars~946 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Corpus Search

What does Corpus Search do?

Semantic search over critical minerals PDF corpus — rare earth, lithium, cobalt, nickel supply chain, trade policy, extraction, and materials research via Pinecone. Corpus Search is an agent skill from lamm-mit/scienceclaw.

When should I use Corpus Search?

Corpus Search fits situations like: tasks that involve Vector databases; tasks that involve Supply chain security; tasks that involve PDF.

How do I install Corpus Search in Claude Code?

Run `npx skills add lamm-mit/scienceclaw --skill corpus-search -a claude-code`. Or copy the skill folder (skills/corpus-search in lamm-mit/scienceclaw) into .claude/skills/corpus-search in your project. Claude Code loads it when a task matches its description.

How do I install Corpus Search in Codex?

Run `npx skills add lamm-mit/scienceclaw --skill corpus-search -a codex`. Or copy the skill folder (skills/corpus-search in lamm-mit/scienceclaw) into .agents/skills/corpus-search in your project. Codex loads it when a task matches its description.

Can I use Corpus Search 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 lamm-mit/scienceclaw --skill corpus-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/corpus-search, .gemini/skills/corpus-search, .github/skills/corpus-search and .opencode/skills/corpus-search in your project.

What does Corpus Search need to run?

Going by SKILL.md and its folder, Corpus Search needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named PINECONE_API_KEY. Our summary lists: Python 3; A credential in PINECONE_API_KEY.

Does Corpus Search access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Corpus Search 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Corpus Search use?

Corpus Search is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Corpus Search use?

About 776 tokens (SKILL.md is roughly 3.1k 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 Corpus Search?

Skills that share tags, products or a category with Corpus Search: Cognee Community Packages (topoteretes/cognee, 32k stars), Paper Interpretation (digoal/blog, 8.6k stars), Pinecone Vector Database (Orchestra-Research/AI-Research-SKILLs, 13k stars) and RAG Implementation (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Corpus Search?

lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 244 GitHub stars. The repository holds 86 skills in this directory. The repository was last updated on August 21, 2026.

Source: lamm-mit/scienceclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.