Agent skill

Building Baselines

by flyrank-bih in 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.

Custom licenceAuto-check passed

Install Building Baselines

skills CLI
$ npx skills add flyrank-bih/flyrank-ml-internship-starter --skill building-baselines -a claude-code

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

GitHub CLI
$ gh skill install flyrank-bih/flyrank-ml-internship-starter building-baselines --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/building-baselines .claude/skills/building-baselines && 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
building-baselines
GitHub stars
140
Token cost
~587 tokens
SKILL.md length
279 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
Custom licence

At a glance

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

  • SKILL.md covers Build it in this order, Also useful and How to verify
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Building Baselines is an agent skill from 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. Use before training any model, or when someone reports model results with nothing to compare against.

Its SKILL.md is about 590 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

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.

Example prompts

  • “Use the building-baselines skill to build the transparent rule-based baseline every model must beat — a hand-written score with reason codes, ranked…”
  • “/building-baselines”

Requirements

  • Python 3

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 (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

Building Baselines loads about 587 tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 279 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~587

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 279 words (~587 tokens).

“A model without a baseline is a number without a meaning. The baseline is a rule a human can read — and its job is to be honestly beatable.”

— opening of SKILL.md by flyrank-bih, Custom licence
name
building-baselines

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/building-baselines of flyrank-bih/flyrank-ml-internship-starter.

Open the folder on GitHubat commit 882b73e

Compare with similar skills

Building Baselines 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.

Building Baselines compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Building Baselines this skillflyrank-bih/flyrank-ml-internship-starter140—~587Automated safety check: PassCustom licence
Codex Rules Referencecode-yeongyu/oh-my-openagent70k—~269Automated safety check: PassCustom licence
Rules Distillationaffaan-m/ECC276k2 repos~2.3kAutomated safety check: PassMIT
Hookify Rulesaffaan-m/ECC276k—~605Automated safety check: NotesMIT
Rules Distillaffaan-m/ECC276k—~1.5kAutomated safety check: PassMIT
Rules Distillaffaan-m/ECC276k1 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • Codex Rules Reference

    code-yeongyu/oh-my-openagent

    Explains how the Codex Rules plugin injects project instructions and file-specific rules into a session, which rule files it reads and which settings control it.

    70k GitHub stars~269 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    276k GitHub starsUsed in 2 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • Hookify Rules

    affaan-m/ECC

    当用户要求创建hookify规则、编写hook规则、配置hookify、添加hookify规则或需要关于hookify规则语法和模式的指导时,应使用此技能。

    276k GitHub stars~605 tokensUpdated 5 days ago
    Agent WorkflowsAuto-check: notes
  • Rules Distill

    affaan-m/ECC

    スキルをスキャンしてドメイン横断的な原則を抽出し、ルールに蒸留する——既存のルールファイルへの追記、修正、または新規作成

    276k GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed
  • Rules Distill

    affaan-m/ECC

    扫描技能以提取跨领域原则并将其提炼为规则——追加、修订或创建新的规则文件

    276k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • Odoo Security Rules

    sickn33/agentic-awesome-skills

    Expert in Odoo access control: ir.model.access.csv, record rules (ir.rule), groups, and multi-company security patterns.

    47k GitHub starsUsed in 2 repos~1.1k tokens
    Documents & OfficeAuto-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
  • 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
  • Writing Research Papers

    flyrank-bih/flyrank-ml-internship-starter

    Structures and writes a public research page — canonical sections (abstract through limitations), storytelling that carries findings, chart hygiene, referencing for credibility, repurposing for…

    140 GitHub stars~787 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Building Baselines

What does Building Baselines do?

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

How do I install Building Baselines in Claude Code?

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

How do I install Building Baselines in Codex?

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

Can I use Building Baselines 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 building-baselines -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/building-baselines, .gemini/skills/building-baselines, .github/skills/building-baselines and .opencode/skills/building-baselines in your project.

What does Building Baselines need to run?

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

Does Building Baselines 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 Building Baselines 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 Building Baselines use?

Building Baselines 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 Building Baselines use?

About 587 tokens (SKILL.md is roughly 2.3k 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 Building Baselines?

Skills that share tags, products or a category with Building Baselines: Codex Rules Reference (code-yeongyu/oh-my-openagent, 70k stars), Rules Distillation (affaan-m/ECC, 276k stars), Hookify Rules (affaan-m/ECC, 276k stars) and Rules Distill (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Building Baselines?

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.