📄
DataPython

Calibration

by Ontos-AI

Calibration is a Data skill for Claude Code, published by Ontos-AI in knowhere.

2.5K stars290 forkson Ontos-AI/knowhereAdded 2026/08/18+4% in starsRepository updated 2026/08/16
View source on GitHubDownload repo ZIP
agent-harnessai-agentsclaude-codecodexcursordocument-intelligencelangchainmutli-agentrag-pipelineskillsvector-database
Install in seconds
Install Calibration
Copy Calibration into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/Ontos-AI/knowhere/tree/main/apps/worker/app/services/document_agent/agents/calibration ~/.claude/skills/calibration

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Ontos-AI/knowhere.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
apps/worker/app/services/document_agent/agents/calibration/SKILL.md in Ontos-AI/knowhere
Installs to
~/.claude/skills/calibration
Collection
The only skill cataloged from this repository
Category
Data — 668 skills

What Calibration does

Calibration partitions table-of-contents page labels into numbering regimes and submits candidate physical-to-printed page offsets for deterministic completion. Use it during document intelligence pipelines to calibrate scanned book anchors without guessing pages.

Calibration is cataloged under Data on DirSkills. Calibration comes from a repository tagged agent-harness, ai-agents, claude-code, codex and cursor.

Documentation

README

Calibration SubAgent Skill

Goal

For the current TOC region, discover page-numbering regimes and an initial offset for each regime that has usable entries. Submit candidate offsets via calibration.submit. After submit, a deterministic completion pass runs the production tail-verify → binary-search → small-step recalibrate loop (using the same visual page confirmer as production). Only complete segments are usable for coarse structure; unrecognized pages are treated as no TOC.

Do not use

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Calibration

  • How does Calibration compare to other Data skills?

    Calibration ranks #319 by stars among the 668 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Calibration against them. Open each page to compare what they document and how they install.

More Data skills

Calibration is one of 668 Data skills cataloged on DirSkills, ranked #319 by stars among them.

Browse all Data skills →
📊
3w ago

Benchmark Methodology

Benchmark Methodology scores competitors across nine weighted dimensions using explicit 1–5 rubrics and a tension plot. Use it after competitive-platform-analysis to produce comparable, evidence-anchored profile cards for a competitive report.
Data
239.8K36.4K
📓
3w ago

Jupyter Notebook

Jupyter Notebook provides a stateful Python REPL via a live Jupyter kernel (hamelnb) so variables persist across executions. Use it for iterative data exploration, API inspection, and complex code development.
Data
229.7K45.3K
🪙
3w ago

Solana

Solana queries wallets, token holdings, transactions, NFTs, whale transfers, and network stats on the Solana blockchain with USD pricing via CoinGecko. Use it when you need to inspect an address, verify a transaction, check token metadata or prices, or monitor network health.
Data
229.7K45.3K