User-Facing Text Cleanup
guillaumemeyer/watermarks-remover
Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.
Canonicalise antigen.gene and antigen.species in a VDJdb chunk against the epitope dictionary and the gene and species alias tables, detect spurious values (UniProt descriptions, "[species]"…
Install Vdjdb Harmonize
$ npx skills add antigenomics/vdjdb-db --skill vdjdb-harmonize -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install antigenomics/vdjdb-db vdjdb-harmonize --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/antigenomics/vdjdb-db.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/vdjdb-harmonize .claude/skills/vdjdb-harmonize && rm -rf skills-srcUse ~/.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/
Install the "vdjdb-harmonize" agent skill from https://github.com/antigenomics/vdjdb-db/tree/master/skills/vdjdb-harmonize into .claude/skills/vdjdb-harmonize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vdjdb-harmonize", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/antigenomics/vdjdb-db/tree/master/skills/vdjdb-harmonizeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add antigenomics/vdjdb-db --skill vdjdb-harmonize -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install antigenomics/vdjdb-db vdjdb-harmonize --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/antigenomics/vdjdb-db.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/vdjdb-harmonize .agents/skills/vdjdb-harmonize && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "vdjdb-harmonize" agent skill from https://github.com/antigenomics/vdjdb-db/tree/master/skills/vdjdb-harmonize into .agents/skills/vdjdb-harmonize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vdjdb-harmonize", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add antigenomics/vdjdb-db --skill vdjdb-harmonize -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install antigenomics/vdjdb-db vdjdb-harmonize --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/antigenomics/vdjdb-db.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/vdjdb-harmonize .cursor/skills/vdjdb-harmonize && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "vdjdb-harmonize" agent skill from https://github.com/antigenomics/vdjdb-db/tree/master/skills/vdjdb-harmonize into .cursor/skills/vdjdb-harmonize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vdjdb-harmonize", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/antigenomics/vdjdb-db.git --path skills/vdjdb-harmonize--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add antigenomics/vdjdb-db --skill vdjdb-harmonize -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install antigenomics/vdjdb-db vdjdb-harmonize --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/antigenomics/vdjdb-db.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/vdjdb-harmonize .gemini/skills/vdjdb-harmonize && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "vdjdb-harmonize" agent skill from https://github.com/antigenomics/vdjdb-db/tree/master/skills/vdjdb-harmonize into .gemini/skills/vdjdb-harmonize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vdjdb-harmonize", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install antigenomics/vdjdb-db vdjdb-harmonizeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add antigenomics/vdjdb-db --skill vdjdb-harmonize -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/antigenomics/vdjdb-db.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/vdjdb-harmonize .github/skills/vdjdb-harmonize && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "vdjdb-harmonize" agent skill from https://github.com/antigenomics/vdjdb-db/tree/master/skills/vdjdb-harmonize into .github/skills/vdjdb-harmonize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vdjdb-harmonize", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add antigenomics/vdjdb-db --skill vdjdb-harmonize -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install antigenomics/vdjdb-db vdjdb-harmonize --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/antigenomics/vdjdb-db.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/vdjdb-harmonize .opencode/skills/vdjdb-harmonize && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "vdjdb-harmonize" agent skill from https://github.com/antigenomics/vdjdb-db/tree/master/skills/vdjdb-harmonize into .opencode/skills/vdjdb-harmonize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vdjdb-harmonize", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
vdjdb-harmonize- GitHub stars
- 157
- Token cost
- ~715 tokens
- SKILL.md length
- 283 words
- Files
- 1
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Canonicalise antigen.gene and antigen.species in a VDJdb chunk against the epitope dictionary and the gene and species alias tables, detect spurious values (UniProt descriptions, "[species]"…
- Antigen.species carry free text rather than symbols
- SKILL.md covers Inspect existing harmonisation, Resolve findings from the… and Record the result
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Vdjdb-proofread reports antigen fields that disagree across a chunk
What it does
Vdjdb Harmonize is an agent skill from antigenomics/vdjdb-db. Canonicalise antigen.gene and antigen.species in a VDJdb chunk against the epitope dictionary and the gene and species alias tables, detect spurious values (UniProt descriptions, "[species]" annotations, "Probable"/"Chain A," prefixes, multi-word organism names), resolve blanks from the publication, flag one epitope that is a substring of another, and extend the alias tables where they have no entry. Use when antigen.gene or antigen.species carry free text rather than symbols, or when vdjdb-proofread reports…
Its SKILL.md is about 720 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 Writing & Content, covering Copy editing and proofreading. It works with UniProt. The repository describes itself as: Git-based antigen specificity database storage & management.
When your agent uses it
- Antigen.species carry free text rather than symbols
- Vdjdb-proofread reports antigen fields that disagree across a chunk
Example prompts
- “[species]”
- “Probable”
- “Chain A,”
- “/vdjdb-harmonize”
What it can do on your machine
Read from SKILL.md and the folder at commit 5dfc25f. 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.
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
Vdjdb Harmonize loads about 715 tokens when it runs. Until then it costs about 144 tokens; SKILL.md has 283 words of instructions outside code blocks.
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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 283 words (~715 tokens).
“Read AUTHORITIES.md and terminology. antigen.gene and antigen.species describe peptide provenance. Recognition is assigned to the peptide-MHC complex.”
- name
- vdjdb-harmonize
Files
Just SKILL.md in skills/vdjdb-harmonize of antigenomics/vdjdb-db.
Open the folder on GitHubat commit 5dfc25f
Compare with similar skills
Vdjdb Harmonize 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Vdjdb Harmonize this skillantigenomics/vdjdb-db | 157 | — | ~715 | Automated safety check: Pass | Custom licence | |
| User-Facing Text Cleanupguillaumemeyer/watermarks-remover | 24k | — | ~3.5k | Automated safety check: Pass | MIT | |
| Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode | 7.4k | 3 repos | ~3k | Automated safety check: Pass | MIT | |
| Chinese Text Humanizerop7418/Humanizer-zh | 19k | — | ~2k | Automated safety check: Pass | MIT | |
| Korean AI-Text Humanizerepoko77-ai/im-not-ai | 5.9k | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Natural Japanese Business Writingcoji/natural-japanese | 1.9k | — | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Story Multi-Perspective Review
zenstory-ai/oh-story-claudecode
Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.
Chinese Text Humanizer
op7418/Humanizer-zh
Edits Chinese articles, comments and documents to remove filler, repetition and template phrasing while keeping the facts, the level of certainty and the author's voice.
Korean AI-Text Humanizer
epoko77-ai/im-not-ai
Rewrites Korean text written by AI so it reads like a human wrote it, detecting translationese and other AI patterns while leaving the content untouched.
Natural Japanese Business Writing
coji/natural-japanese
Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.
Defensive Writing Editor
lennney/stop-that-shit
Cuts defensive disclaimers, stacked hedging and self-protective narration from proposals and summaries, keeping only limits that affect the reader's decision.
More from antigenomics/vdjdb-db
All 8 skills in this repoVdjdb Publish
antigenomics/vdjdb-db
Publish proofread VDJdb chunks through dev, reconcile publication issues, preserve record identity, keep validation changes separate, and close completed imports while tracking unresolved…
Vdjdb Build Integrity
antigenomics/vdjdb-db
Validate VDJdb build code, CI, output contracts and release promotions against a released corpus.
Vdjdb Duplicates
antigenomics/vdjdb-db
Review repeated paired receptor-pMHC observations and metadata synonyms within and across VDJdb publications, preserving distinct experiments and reports.
Vdjdb Extract
antigenomics/vdjdb-db
Extract TCR:pMHC specificity records from raw submission sources - supplementary XLS/CSV tables, PDF manuscripts, 10x Genomics contig and clonotype files, AIRR Rearrangement TSVs, Adaptive ImmunoSEQ…
Vdjdb Proofread
antigenomics/vdjdb-db
Validate a VDJdb chunk with vdjdb qc and vdjdb submission, explain every finding with a specific suggested fix and the authority behind it, resolve method-field and MHC problems the rules cannot…
Vdjdb Structures
antigenomics/vdjdb-db
Extract and proofread deposited TCR-pMHC observations with the local tcren pipeline, then update the PDB aggregate chunk.
Related
Works with
Categories
Questions about Vdjdb Harmonize
What does Vdjdb Harmonize do?
Canonicalise antigen.gene and antigen.species in a VDJdb chunk against the epitope dictionary and the gene and species alias tables, detect spurious values (UniProt descriptions, "[species]"…. Vdjdb Harmonize is an agent skill from antigenomics/vdjdb-db.species in a VDJdb chunk against the epitope dictionary and the gene and species alias tables, detect spurious values (UniProt descriptions, "[species]" annotations, "Probable"/"Chain A," prefixes, multi-word organism names), resolve blanks from the publication, flag one epitope that is a substring of another, and extend the alias tables where they have no entry.
When should I use Vdjdb Harmonize?
Vdjdb Harmonize fits situations like: antigen.species carry free text rather than symbols; vdjdb-proofread reports antigen fields that disagree across a chunk.
How do I install Vdjdb Harmonize in Claude Code?
Run `npx skills add antigenomics/vdjdb-db --skill vdjdb-harmonize -a claude-code`. Or copy the skill folder (skills/vdjdb-harmonize in antigenomics/vdjdb-db) into .claude/skills/vdjdb-harmonize in your project. Claude Code loads it when a task matches its description.
How do I install Vdjdb Harmonize in Codex?
Run `npx skills add antigenomics/vdjdb-db --skill vdjdb-harmonize -a codex`. Or copy the skill folder (skills/vdjdb-harmonize in antigenomics/vdjdb-db) into .agents/skills/vdjdb-harmonize in your project. Codex loads it when a task matches its description.
Can I use Vdjdb Harmonize 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 antigenomics/vdjdb-db --skill vdjdb-harmonize -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vdjdb-harmonize, .gemini/skills/vdjdb-harmonize, .github/skills/vdjdb-harmonize and .opencode/skills/vdjdb-harmonize in your project.
What does Vdjdb Harmonize need to run?
SKILL.md names no scripts, command-line tools or credentials: Vdjdb Harmonize is instructions for the agent only.
Does Vdjdb Harmonize 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 Vdjdb Harmonize 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 Vdjdb Harmonize use?
Vdjdb Harmonize has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Vdjdb Harmonize use?
About 715 tokens (SKILL.md is roughly 2.9k 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 Vdjdb Harmonize?
Skills that share tags, products or a category with Vdjdb Harmonize: User-Facing Text Cleanup (guillaumemeyer/watermarks-remover, 24k stars), Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.4k stars), Chinese Text Humanizer (op7418/Humanizer-zh, 19k stars) and Korean AI-Text Humanizer (epoko77-ai/im-not-ai, 5.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Vdjdb Harmonize?
antigenomics (a GitHub organization) maintains it in antigenomics/vdjdb-db, which has 157 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 7, 2026.
Source: antigenomics/vdjdb-db on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.