Paperclip

What it does

When your agent uses it

• A task names GXL paperclip
• Asks to install
• Authenticate it
• Requests literature retrieval and evidence extraction through Paperclip

Example prompts

• “Use the paperclip skill to search and reads biomedical papers, FDA/PMDA/EMA documents, clinical trials, and protein records with the GXL Paperclip…”
• “/paperclip”

Requirements

• Python 3
• A credential in PAPERCLIP_API_KEY
• Compatibility (from SKILL.md): Requires network access and the GXL paperclip CLI. The macOS/Linux installer requires Python 3.8+ plus curl or wget; it installs a Python launcher and private library, not an interpreter. Use PAPERCLIP_API_KEY or existing browser-login credentials. Hosted MCP is available without local CLI installation. Reviewed against CLI/SDK 0.7.92.
• Pre-approved tools (allowed-tools): Bash, Read, Write

What it can do on your machine

Read from SKILL.md and the folder at commit 92ace75. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Write

  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 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:

  • paperclip.gxl.ai

  Also links to:

  • arxiv.org
  • doi.org
  • export.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.

• Compatibility

  Requires network access and the GXL paperclip CLI. The macOS/Linux installer requires Python 3.8+ plus curl or wget; it installs a Python launcher and private library, not an interpreter. Use PAPERCLIP_API_KEY or existing browser-login credentials. Hosted MCP is available without local CLI installation. Reviewed against CLI/SDK 0.7.92.

  From compatibility in the SKILL.md frontmatter.

Context cost

Paperclip loads about 3.2k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 119 tokens; SKILL.md has 1,220 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~119

When it runs · the whole SKILL.md, loaded when a task matches

~3.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~18k

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

• NoteMentions a .env fileSKILL.md:41

  p does not automatically load a project `.env`. If the user has supplied a **trusted,

• NoteMentions a .env fileSKILL.md:42

  shell-compatible** `.env`, export it in the same shell invocation as the command:

• NoteMentions a .env fileSKILL.md:45

  if [ -f .env ]; then

• NoteMentions a .env fileSKILL.md:47

  . ./.env

• NoteMentions a .env fileSKILL.md:53

  Sourcing `.env` executes shell code: use only a trusted file, and keep it out of Git. Repeat the

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Write

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 K-Dense-AI/scientific-agent-skills at commit 92ace75, republished under its MIT licence (© K-Dense-AI). 1,220 words, ~3,241 tokens.

name

paperclip

description

Searches and reads biomedical papers, FDA/PMDA/EMA documents, clinical trials, and protein records with the GXL Paperclip CLI and Python SDK. Supports source-scoped search, full-text grep, metadata SQL, map/reduce extraction, figure analysis, optional repositories and claim verification, and line-pinned citations. Use when a task names GXL paperclip, asks to install or authenticate it, or requests literature retrieval and evidence extraction through Paperclip.

allowed-tools

Bash, Read, Write

compatibility

Requires network access and the GXL paperclip CLI. The macOS/Linux installer requires Python 3.8+ plus curl or wget; it installs a Python launcher and private library, not an interpreter. Use PAPERCLIP_API_KEY or existing browser-login credentials. Hosted MCP is available without local CLI installation. Reviewed against CLI/SDK 0.7.92.

license

MIT

metadata.version

1.5

metadata.skill-author

K-Dense Inc.

metadata.last-reviewed

2026-09-30

metadata.upstream-version

0.7.92

command -v paperclip
paperclip --version
paperclip --help

if [ -f .env ]; then
  set -a
  . ./.env
  set +a
fi
paperclip config 2>&1 | grep -E 'Auth:|Health:'

paperclip search -s pmc "CRISPR base editing delivery" -n 5
paperclip cat /papers/PMC10945750/meta.json
paperclip head -40 /papers/PMC10945750/content.lines
paperclip ls /papers/PMC10945750/sections/
paperclip grep -n "lipid nanoparticle" /papers/PMC10945750/content.lines
paperclip scan /papers/PMC10945750/content.lines "IC50" "off-target" "efficiency"

paperclip search -s pmc "lipid nanoparticle mRNA delivery" -n 5
# Substitute the actual search ID below.
paperclip filter --from s_ID "in vivo delivery with quantified efficiency"
paperclip map --from s_ID "Report delivery vector, target cell type, efficiency, and supporting lines. State 'not reported' when absent."
paperclip results m_ID --save map.txt

paperclip search -s fda "pembrolizumab accelerated approval" -n 5
paperclip search -s trials/us "HER2 breast cancer trastuzumab deruxtecan" -n 5
paperclip cat /trials/NCT04752059/meta.json
paperclip ls /papers/PMC10945750/figures/
# Use the actual filename returned by ls.
paperclip ask-image /papers/PMC10945750/figures/pnas.2307796121fig01.jpg "What is plotted on each axis?"

/papers/        PMC, arXiv, bioRxiv, medRxiv
/fda/           us/, jp/ (PMDA), eu/ (EMA/EPAR)
/trials/        us/, cn/, jp/, eu/, intl/; /clinicaltrials/ is an alias
/proteins/      UniProt, PDB, ChEMBL, addressed by UniProt accession
/geo/           GEO Series; inspect current domain instructions before querying
/patents/       Patent publication records; inspect paperclip skill patents
/clipboard/     User uploads, corpus links, and generated artifacts
/.gxl/          Server scratch; persistence/readability depends on the server session

[1] Authors. "Title." Journal (year). doi:DOI
    https://paperclip.gxl.ai/citations/papers/DOCUMENT_ID#L45-L52

paperclip skill
paperclip routines list
paperclip routines search "meta-analysis"
paperclip routines show paperclip-meta-analysis
paperclip skill proteins

© K-Dense-AI, MIT. 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 6 other files (references) in skills/paperclip of K-Dense-AI/scientific-agent-skills.

• SKILL.md
• references/cli-reference.md
• references/installation.md
• references/map-reduce.md
• references/python-sdk.md
• references/repos-and-workspace.md
• references/search-and-retrieval.md

Open the folder on GitHubat commit 92ace75

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in K-Dense-AI/scientific-agent-skills, which our catalogue first saw on October 7, 2026.

• lingxling/awesome-skills-cnclaude-scientific-skills/skills/paperclip