Agent skill

Writing Data Contracts

by flyrank-bih in flyrank-bih/flyrank-ml-internship-starter

Writes a data contract — what a row means, which fields are features vs labels vs context vs excluded, over which time windows — and verifies every claim with a query.

Custom licenceAuto-check passedData & Analytics

Install Writing Data Contracts

skills CLI
$ npx skills add flyrank-bih/flyrank-ml-internship-starter --skill writing-data-contracts -a claude-code

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

GitHub CLI
$ gh skill install flyrank-bih/flyrank-ml-internship-starter writing-data-contracts --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/flyrank-bih/flyrank-ml-internship-starter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/writing-data-contracts .claude/skills/writing-data-contracts && 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
writing-data-contracts
GitHub stars
140
Token cost
~680 tokens
SKILL.md length
380 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
Custom licence

At a glance

Writes a data contract — what a row means, which fields are features vs labels vs context vs excluded, over which time windows — and verifies every claim with a query.

  • Works in 5 steps: Unit of analysis. One row = one WHAT? (a… → Time window. Which dates does each field… → Field classification. Every field you… → …
  • Tasks that involve Data governance
  • SKILL.md covers The contract, section by section, Verify every claim with a query, Traps that look innocent and How to verify
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Writing Data Contracts is an agent skill from flyrank-bih/flyrank-ml-internship-starter. Writes a data contract — what a row means, which fields are features vs labels vs context vs excluded, over which time windows — and verifies every claim with a query. Use before any feature building or modeling, or when results look wrong and the data definition is suspect.

Its SKILL.md is about 680 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 Data & Analytics, covering Data governance. The repository describes itself as: Starter repo for the FlyRank ML Internship - a runnable ML pipeline on real anonymized Google Search data, with Colab notebooks. Fork it, build your capstone in it.

When your agent uses it

  • Tasks that involve Data governance

Example prompts

  • “Use the writing-data-contracts skill to write a data contract — what a row means, which fields are features vs labels vs context vs excluded, over…”
  • “/writing-data-contracts”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Unit of analysis. One row = one WHAT? (a page? a page-day? a client?) State it.
  2. Time window. Which dates does each field cover? Draw the windows if they differ.
  3. Field classification. Every field you may touch goes in exactly one bucket
  4. Missing values. Which fields go blank, how often, and is the missingness random or does it
  5. Output. What the analysis hands to the human, in one sentence.

What it can do on your machine

Read from SKILL.md and the folder at commit 882b73e. 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

Writing Data Contracts loads about 680 tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 380 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~680

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 380 words (~680 tokens).

“Most weak analysis fails here, before any model: nobody wrote down what a row means. A data contract is that write-down — and a contract your code has checked, not just stated.”

— opening of SKILL.md by flyrank-bih, Custom licence
name
writing-data-contracts

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/writing-data-contracts of flyrank-bih/flyrank-ml-internship-starter.

Open the folder on GitHubat commit 882b73e

Compare with similar skills

Writing Data Contracts 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.

Writing Data Contracts compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writing Data Contracts this skillflyrank-bih/flyrank-ml-internship-starter140—~680Automated safety check: PassCustom licence
Jeecg Systemjeecgboot/skills239—~3.2kAutomated safety check: PassApache-2.0
Openalgo Chart Indicatormarketcalls/openalgo-charts146—~3.4kAutomated safety check: NotesApache-2.0
Data Quality Frameworkswshobson/agents40k11 repos~1.1kAutomated safety check: PassMIT
Research Data Feasibility and Leakage ChecksLight0305/Light-skills640—~4.9kAutomated safety check: PassMIT
Annotating Task Lineageastronomer/agents451—~2.8kAutomated safety check: PassApache-2.0

Similar skills

  • Jeecg System

    jeecgboot/skills

    JeecgBoot 系统主数据查询与管理。Use when user asks to query/create/manage system master data, or says "查询角色", "查询用户", "查询部门", "查询字典", "创建字典", "创建角色", "查岗位", "查职务", "查租户", "查数据源", "查定时任务", "系统主数据", "query…

    239 GitHub stars~3.2k tokensUpdated 22 days ago
    Data & AnalyticsAuto-check passed
  • Openalgo Chart Indicator

    marketcalls/openalgo-charts

    Add a built-in openalgo-charts indicator, restyle it, build a settings UI from its descriptor, or author a custom indicator with registerIndicator or the Tier-2 external-data contract.

    146 GitHub stars~3.4k tokensUpdated 9 days ago
    Data & AnalyticsAuto-check: notes
  • Sets up data quality checks with Great Expectations, dbt tests and data contracts, with checkpoints and pass-fail reports for pipelines.

    40k GitHub starsUsed in 11 repos~1.1k tokens
    Data & AnalyticsAuto-check passed
  • Finds usable public datasets, judges whether the data can support a research idea, and checks train and test splits for leakage before results are trusted.

    640 GitHub stars~4.9k tokensUpdated 3 mo ago
    Data & AnalyticsAuto-check passed
  • Annotating Task Lineage

    astronomer/agents

    Annotate Airflow tasks with data lineage using inlets and outlets.

    451 GitHub stars~2.8k tokensUpdated 2 days ago
    Data & AnalyticsAuto-check passed
  • Data Catalog Entry

    nimrodfisher/data-analytics-skills

    Create standardized metadata for data assets. An agent skill from nimrodfisher/data-analytics-skills.

    470 GitHub stars~616 tokensUpdated 15 days ago
    Data & AnalyticsAuto-check passed

More from flyrank-bih/flyrank-ml-internship-starter

All 13 skills in this repo
  • Querying Big Datasets

    flyrank-bih/flyrank-ml-internship-starter

    Works with datasets far too big to download or load in pandas — SQL over remote Parquet with DuckDB, aggregate-then-model, iterate on samples.

    140 GitHub stars~750 tokensUpdated 1 mo ago
    Auto-check passed
  • Building Baselines

    flyrank-bih/flyrank-ml-internship-starter

    Builds the transparent rule-based baseline every model must beat — a hand-written score with reason codes, ranked output, and precision@K evaluation.

    140 GitHub stars~587 tokensUpdated 1 mo ago
    Auto-check passed
  • Deploying Static Pages

    flyrank-bih/flyrank-ml-internship-starter

    Deploys a static page (research paper, portfolio piece) for free from a GitHub repo using GitHub Pages — setup, file layout, verification, and recording the final URL.

    140 GitHub stars~564 tokensUpdated 1 mo ago
    Auto-check passed
  • Framing ML Problems

    flyrank-bih/flyrank-ml-internship-starter

    Frames a data/ML problem before any modeling — the decision, the action, the cost of a wrong call, task type, target, and success metric.

    140 GitHub stars~700 tokensUpdated 1 mo ago
    Auto-check passed
  • Training Honest Models

    flyrank-bih/flyrank-ml-internship-starter

    Trains a first model the honest way — method chosen to fit the question, compared against the baseline on the same split and metric, errors read before scores are believed.

    140 GitHub stars~588 tokensUpdated 1 mo ago
    Auto-check passed
  • Writing Honest Claims

    flyrank-bih/flyrank-ml-internship-starter

    Writes findings in language the evidence can carry — the claim ladder (observed → directional → decision-support, never causal without a design), effect sizes over drama, banned phrasings.

    140 GitHub stars~665 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Writing Data Contracts

What does Writing Data Contracts do?

Writes a data contract — what a row means, which fields are features vs labels vs context vs excluded, over which time windows — and verifies every claim with a query. Writing Data Contracts is an agent skill from flyrank-bih/flyrank-ml-internship-starter. Writes a data contract — what a row means, which fields are features vs labels vs context vs excluded, over which time windows — and verifies every claim with a query.

When should I use Writing Data Contracts?

Writing Data Contracts fits situations like: tasks that involve Data governance.

How do I install Writing Data Contracts in Claude Code?

Run `npx skills add flyrank-bih/flyrank-ml-internship-starter --skill writing-data-contracts -a claude-code`. Or copy the skill folder (skills/writing-data-contracts in flyrank-bih/flyrank-ml-internship-starter) into .claude/skills/writing-data-contracts in your project. Claude Code loads it when a task matches its description.

How do I install Writing Data Contracts in Codex?

Run `npx skills add flyrank-bih/flyrank-ml-internship-starter --skill writing-data-contracts -a codex`. Or copy the skill folder (skills/writing-data-contracts in flyrank-bih/flyrank-ml-internship-starter) into .agents/skills/writing-data-contracts in your project. Codex loads it when a task matches its description.

Can I use Writing Data Contracts 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 flyrank-bih/flyrank-ml-internship-starter --skill writing-data-contracts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-data-contracts, .gemini/skills/writing-data-contracts, .github/skills/writing-data-contracts and .opencode/skills/writing-data-contracts in your project.

What does Writing Data Contracts need to run?

SKILL.md names no scripts, command-line tools or credentials: Writing Data Contracts is instructions for the agent only.

Does Writing Data Contracts 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 Writing Data Contracts 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 Writing Data Contracts use?

Writing Data Contracts 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 Writing Data Contracts use?

About 680 tokens (SKILL.md is roughly 2.7k 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 Writing Data Contracts?

Skills that share tags, products or a category with Writing Data Contracts: Jeecg System (jeecgboot/skills, 239 stars), Openalgo Chart Indicator (marketcalls/openalgo-charts, 146 stars), Data Quality Frameworks (wshobson/agents, 40k stars) and Research Data Feasibility and Leakage Checks (Light0305/Light-skills, 640 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Data Contracts?

flyrank-bih (a GitHub organization) maintains it in flyrank-bih/flyrank-ml-internship-starter, which has 140 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on August 20, 2026.

Source: flyrank-bih/flyrank-ml-internship-starter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.