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

Evidence Citation

by harrisongzhang in harrisongzhang/TheVirtualBiotech

How to report findings so they can be cited — writing evidence to files before asserting it, choosing where outputs belong, describing what each artifact shows, and returning findings with…

MITAuto-check passedResearch & Science

Install Evidence Citation

skills CLI
$ npx skills add harrisongzhang/TheVirtualBiotech --skill evidence-citation -a claude-code

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

GitHub CLI
$ gh skill install harrisongzhang/TheVirtualBiotech evidence-citation --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/harrisongzhang/TheVirtualBiotech.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/evidence-citation .claude/skills/evidence-citation && 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
evidence-citation
GitHub stars
122
Token cost
~1.4k tokens
SKILL.md length
582 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

How to report findings so they can be cited — writing evidence to files before asserting it, choosing where outputs belong, describing what each artifact shows, and returning findings with…

  • Works in 5 steps: Write it down before you assert it → Put it in the right place → Say what each output shows → …
  • You are a specialist producing analysis for the CSO
  • SKILL.md covers Why this exists, 1. Write it down before you…, 2. Put it in the right place and 3. Say what each output shows, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Evidence Citation is an agent skill from harrisongzhang/TheVirtualBiotech. How to report findings so they can be cited — writing evidence to files before asserting it, choosing where outputs belong, describing what each artifact shows, and returning findings with machine-checkable evidence pointers. Use when you are a specialist producing analysis for the CSO, before writing your final response, or when deciding whether a result needs to be saved.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Citation management. The repository describes itself as: Multi-agent AI system for drug-target identification and due diligence. The licence is MIT.

When your agent uses it

  • You are a specialist producing analysis for the CSO
  • Before writing your final response
  • Deciding whether a result needs to be saved

Example prompts

  • “/evidence-citation”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Write it down before you assert it
  2. Put it in the right place
  3. Say what each output shows
  4. Return findings with evidence attached
  5. Report what you could not establish

What it can do on your machine

Read from SKILL.md and the folder at commit 71f9da6. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    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 no API keys, tokens, secrets or passwords.

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

Context cost

Evidence Citation loads about 1.4k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 582 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from harrisongzhang/TheVirtualBiotech at commit 71f9da6, republished under its MIT licence (© harrisongzhang). 582 words, ~1,361 tokens.

Download SKILL.mdSave it as .claude/skills/evidence-citation/SKILL.md (or your agent's skills folder).
name
evidence-citation
description
How to report findings so they can be cited — writing evidence to files before asserting it, choosing where outputs belong, describing what each artifact shows, and returning findings with machine-checkable evidence pointers. Use when you are a specialist producing analysis for the CSO, before writing your final response, or when deciding whether a result needs to be saved.

Evidence Citation

Why this exists

Your findings become claims in the CSO's answer to the user. Each claim is clickable: a reader opens it and sees the table, figure, code line or tool call behind it. The CSO can only build that from what you hand it, and it must not invent citations — the system rejects evidence pointers that do not resolve.

So a finding you report without evidence is one the CSO has to present as unsupported. Everything below is about making sure that does not happen to work you actually did.

1. Write it down before you assert it

A number that exists only in your prose cannot be cited.

Before stating a result, save the thing that shows it:

You want to saySave
"highest in mast cells"the per-cell-type table
"L2G score 0.75"the credible-set table you read it from
"expression is bimodal"the plot
"no black-box warning"the query result

This is not bookkeeping. If the only record of a result is a sentence, nobody can check it, and in six months neither can you.

2. Put it in the right place

You have your own directory. Use the layout:

work/<your-agent-name>/
├── code/scripts/         analysis scripts you write
├── data/raw/             data as pulled from a tool or database
├── data/processed/       data after your QC / transformation
└── results/
    ├── figures/          plots (.png, .pdf)
    ├── tables/           result tables (.csv, .tsv, .parquet)
    └── reports/          your written findings (.md)

Absolute paths, always. Do not write into another specialist's directory or into the run root.

Name for content, not sequence. il33_celltype_expression.csv, not analysis2.csv. gwas_credible_sets_chr9.parquet, not cs_2fd0.parquet. Every file you leave behind is something a human has to interpret without you there.

3. Say what each output shows

The system records every file you write automatically — you do not need to do anything for an artifact to exist. What it cannot infer is what the file demonstrates. For each output that carries a finding:

python
register_artifact(
  path="results/tables/il33_celltype_expression.csv",
  description="Mean IL1RL1 expression per lung cell type across 12 donors; "
              "mast cells highest at 2.4 CPM")

One line. What is in it, and what it shows.

4. Return findings with evidence attached

Structure your response to the CSO so each substantive finding carries its evidence:

FINDING: IL1RL1 is most highly expressed in lung mast cells (mean 2.4 CPM,
         3.1x the next-highest cell type).
EVIDENCE: results/tables/il33_celltype_expression.csv (row: mast cell)
          results/figures/il33_celltype.png
CONFIDENCE: strong — direct measurement, n=12 donors, consistent across 3 datasets

FINDING: Expression in cardiac tissue is low but non-zero.
EVIDENCE: results/tables/il33_critical_organs.csv (rows: cardiac_*)
CONFIDENCE: moderate — only 2 donors with cardiac tissue; wide CI

Paths relative to your own directory are fine — the CSO resolves them.

If a specific tool call is the evidence (an MCP query whose result you are reporting directly rather than a file you wrote), give its tool_use_id.

Show full SKILL.md (237 more words)Show less

5. Report what you could not establish

If a query failed, returned nothing, or the evidence is too thin to support a conclusion — that is your result. Say it:

NOT ESTABLISHED: Cardiac expression could not be assessed. The Census query for
heart tissue returned 0 cells after QC filtering. Retried with relaxed filters
(min_genes 200 → 100), still 0. This gap should be closed before a cardiac
safety claim is made either way.

An acknowledged gap is usable — the CSO can scope its answer around it, or send someone back for it. A confident claim with nothing behind it is worse than silence, because it looks the same as a supported one until someone checks.

Checklist before you respond

  • Every number I state exists in a file I wrote
  • Files are under my own work/<agent>/ tree, in the right subdirectory
  • Filenames say what the files contain
  • register_artifact called for each output carrying a finding
  • Each finding in my response has an EVIDENCE line
  • Confidence stated honestly, with the reason
  • Anything I could not establish is stated, not omitted

Anti-patterns

Reporting a summary statistic without saving the underlying table. The summary is the claim; the table is the evidence. Both are needed.

results_final_v3.csv. If there are three versions, either two are dead — delete them — or they differ in a way the filename should say.

Burying the finding in a long narrative. The CSO extracts claims from what you return. A clearly delimited FINDING/EVIDENCE/CONFIDENCE block survives that extraction; a paragraph where the result is in the fourth sentence may not.

Overstating confidence to sound useful. moderate with an honest reason is more useful than strong that a reviewer later has to walk back.

© harrisongzhang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/evidence-citation of harrisongzhang/TheVirtualBiotech.

Open the folder on GitHubat commit 71f9da6

Compare with similar skills

Evidence Citation 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.

Evidence Citation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Evidence Citation this skillharrisongzhang/TheVirtualBiotech122—~1.4kAutomated safety check: PassMIT
Content Research Writerweapp-tailwindcss/weapp-tailwindcss1.9k25 repos~3.5kAutomated safety check: PassMIT
Systematic Review ScreenerImbad0202/academic-research-skills51k—~8.4kAutomated safety check: PassCustom licence
NetworkxzLanqing/codex-claude-academic-skills4.7k15 repos~3.2kAutomated safety check: PassBSD-3-Clause
Literature Reviewneflibata-feng/MyArxiv-Agent12620 repos~5.9kAutomated safety check: NotesMIT
Openalex Databaseneflibata-feng/MyArxiv-Agent12612 repos~3kAutomated safety check: PassCustom licence

Similar skills

  • Content Research Writer

    weapp-tailwindcss/weapp-tailwindcss

    Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.

    1.9k GitHub starsUsed in 25 repos~3.5k tokens
    Research & ScienceAuto-check passed

  • Systematic Review Screener

    Imbad0202/academic-research-skills

    Screens records for systematic, scoping and rapid reviews against fixed eligibility rules, using two blinded AI reviewers and a third adjudicator, with traceable PRISMA counts.

    51k GitHub stars~8.4k tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Networkx

    zLanqing/codex-claude-academic-skills

    Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python.

    4.7k GitHub starsUsed in 15 repos~3.2k tokens
    Research & ScienceAuto-check passed

  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes

  • Openalex Database

    neflibata-feng/MyArxiv-Agent

    Query and analyze scholarly literature using the OpenAlex database.

    126 GitHub starsUsed in 12 repos~3k tokens
    Research & ScienceAuto-check passed

  • Citation Verification Guide

    Galaxy-Dawn/claude-scholar

    Reference guidance for checking every citation in academic writing against canonical sources such as DOI, arXiv, CrossRef and Semantic Scholar, to catch fake or wrong references.

    5.7k GitHub starsUsed in 2 repos~1.9k tokens
    Research & ScienceAuto-check passed

More from harrisongzhang/TheVirtualBiotech

  • Run Organization

    harrisongzhang/TheVirtualBiotech

    How to organise a session run so a human can audit it — directory layout, artifact naming, recording the analysis plan, filing claim-evidence objects, and the end-of-run checklist.

    122 GitHub stars~1.8k tokensUpdated 24 days ago
    Auto-check passed

  • Single Cell Analysis

    harrisongzhang/TheVirtualBiotech

    Statistical analysis and reporting for single-cell RNA-seq data.

    122 GitHub stars~3.2k tokensUpdated 24 days ago
    Auto-check passed

  • Single Cell Data Prep Qc

    harrisongzhang/TheVirtualBiotech

    Single-cell RNA-seq data preparation and quality control pipeline.

    122 GitHub stars~2.9k tokensUpdated 24 days ago
    Auto-check passed

Categories

Questions about Evidence Citation

What does Evidence Citation do?

How to report findings so they can be cited — writing evidence to files before asserting it, choosing where outputs belong, describing what each artifact shows, and returning findings with…. Evidence Citation is an agent skill from harrisongzhang/TheVirtualBiotech. How to report findings so they can be cited — writing evidence to files before asserting it, choosing where outputs belong, describing what each artifact shows, and returning findings with machine-checkable evidence pointers.

When should I use Evidence Citation?

Evidence Citation fits situations like: you are a specialist producing analysis for the CSO; before writing your final response; deciding whether a result needs to be saved.

How do I install Evidence Citation in Claude Code?

Run `npx skills add harrisongzhang/TheVirtualBiotech --skill evidence-citation -a claude-code`. Or copy the skill folder (.claude/skills/evidence-citation in harrisongzhang/TheVirtualBiotech) into .claude/skills/evidence-citation in your project. Claude Code loads it when a task matches its description.

How do I install Evidence Citation in Codex?

Run `npx skills add harrisongzhang/TheVirtualBiotech --skill evidence-citation -a codex`. Or copy the skill folder (.claude/skills/evidence-citation in harrisongzhang/TheVirtualBiotech) into .agents/skills/evidence-citation in your project. Codex loads it when a task matches its description.

Can I use Evidence Citation 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 harrisongzhang/TheVirtualBiotech --skill evidence-citation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evidence-citation, .gemini/skills/evidence-citation, .github/skills/evidence-citation and .opencode/skills/evidence-citation in your project.

What does Evidence Citation need to run?

SKILL.md names no scripts, command-line tools or credentials: Evidence Citation is instructions for the agent only. Our summary lists: Python 3.

Does Evidence Citation 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 Evidence Citation 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. Review the folder before installing.

What licence does Evidence Citation use?

Evidence Citation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Evidence Citation use?

About 1.4k tokens (SKILL.md is roughly 5.4k 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 Evidence Citation?

Skills that share tags, products or a category with Evidence Citation: Content Research Writer (weapp-tailwindcss/weapp-tailwindcss, 1.9k stars), Systematic Review Screener (Imbad0202/academic-research-skills, 51k stars), Networkx (zLanqing/codex-claude-academic-skills, 4.7k stars) and Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Evidence Citation?

harrisongzhang (a GitHub user) maintains it in harrisongzhang/TheVirtualBiotech, which has 122 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 17, 2026.

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