Agent skill

Eazyr Repo Onboarding Kit

by buildfastwithai in buildfastwithai/gen-ai-experiments

Creates a QUICKSTART, doctor scripts and a documented .env.example for an unfamiliar repo from facts scanned in the repo, and audits how easy it is to onboard.

MITAuto-check: notesDevelopment

Install Eazyr Repo Onboarding Kit

skills CLI
$ npx skills add buildfastwithai/gen-ai-experiments --skill eazyr -a claude-code

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

GitHub CLI
$ gh skill install buildfastwithai/gen-ai-experiments eazyr --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/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/eazyr-main .claude/skills/eazyr && 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
eazyr
GitHub stars
785
Token cost
~1.4k tokens
SKILL.md length
688 words
Files
24 (incl. references, assets)
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Creates a QUICKSTART, doctor scripts and a documented .env.example for an unfamiliar repo from facts scanned in the repo, and audits how easy it is to onboard.

  • Works in 4 steps: Scan → Generate the first draft → Edit it into something true → …
  • Someone cannot get a project running from the existing instructions
  • SKILL.md covers The one rule, Workflow, When the scanner comes up empty and Scope, plus 1 more section
  • Runs PowerShell, Shell and JavaScript scripts from its folder; calls npx and bash; needs STRIPE_SECRET_KEY

What it does

Eazyr produces an onboarding kit that lives in the repository: `QUICKSTART.md`, `scripts/doctor.sh` with `scripts/doctor.ps1` for checks that fail early, and `.env.example` listing every variable the app reads. Its one rule is to never write a step it has not verified against the repo. Where a fact is missing, the agent marks the gap and says what it needs instead of filling it with something plausible.

`npx eazyr scan --json` returns the detected ecosystems, environment variables with required and secret flags and file-and-line sources, compose services, ports, a verification command and the ordered setup steps, plus a list of gaps. The scanner is regex-based, skips `node_modules` and stops at 4000 files, so `references/detect.md` serves as the manual fallback. `npx eazyr init` writes a first draft, skipping existing files unless `--force` is used, and the agent then edits it into something true by resolving gaps and checking each cited source.

When your agent uses it

  • Someone cannot get a project running from the existing instructions
  • Onboarding a new developer to an undocumented repo
  • Writing a QUICKSTART, a doctor script or a documented .env.example
  • Auditing whether a repository can be set up by a newcomer at all

Example prompts

  • “Scan this repo and write a QUICKSTART that takes a new hire from clone to running app.”
  • “Create a .env.example documenting every variable the code reads.”
  • “Add doctor scripts that check prerequisites before setup, for both bash and PowerShell.”
  • “Audit whether this repository is onboardable and list the gaps.”

Requirements

  • npx, to run the eazyr scanner

Workflow steps

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

  1. Scan
  2. Generate the first draft
  3. Edit it into something true
  4. Verify

What it can do on your machine

Read from SKILL.md and the folder at commit 7b62043. 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

    Ships script files (PowerShell, Shell and JavaScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • npx
    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • STRIPE_SECRET_KEY

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

Context cost

Eazyr Repo Onboarding Kit loads about 1.4k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 104 tokens; SKILL.md has 688 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~104
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.7k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:114
    er copy a real value out of an existing `.env`; use a placeholder

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 buildfastwithai/gen-ai-experiments at commit 7b62043, republished under its MIT licence (© buildfastwithai). 688 words, ~1,363 tokens.

Download SKILL.mdSave it as .claude/skills/eazyr/SKILL.md (or your agent's skills folder). This skill also uses 23 other files; get the full folder from GitHub.
name
eazyr
description
Make an unfamiliar or undocumented repo easy to run. Use when someone cannot get a project running, when onboarding a new developer, or when asked to write a QUICKSTART, a setup/prerequisite check ("doctor") script, or a documented .env.example. Also use when setup instructions are missing, stale, or spread across a wiki, a chat thread, and someone's head — or to audit whether a repo is onboardable at all.

eazyr

Turn "clone it and good luck" into a five-minute path from clone to a running app.

You produce an onboarding kit that lives in the repo:

ArtifactPurpose
QUICKSTART.mdThe shortest correct path from clone to "it works"
scripts/doctor.sh + scripts/doctor.ps1Runnable checks that fail loudly before setup wastes an hour
.env.exampleEvery variable the app reads, documented, with safe defaults

The one rule

Never write a step you have not verified against the repo. Invented steps are worse than absent ones — they cost the reader the time it takes to discover they're fake.

This ships with a scanner so you don't have to rely on memory. eazyr scan --json returns detected facts with the file each one came from. Prefer it over reading twenty files by hand, and cite its provenance rather than guessing.

If a fact is missing, write > **TODO:** and say what you'd need. Never fill the hole with something plausible.

Workflow

1. Scan
bash
npx eazyr scan --json

Returns: ecosystems (stack, package manager, version ranges, real commands from the manifest), env.vars (each with required, secret, and sources: ["file:line"]), compose and services, ports, verify (health endpoint or test command), steps (the ordered setup path), and gaps (what's missing).

Read the human summary first if you just want orientation:

bash
npx eazyr scan

The scanner is a strong first pass, not an oracle. It is regex-based, skips node_modules, and caps at 4000 files. Verify anything surprising by opening the file it cites. If ecosystems is empty or truncated is true, fall back to reading the repo yourself — references/detect.md is the manual lookup table.

2. Generate the first draft
bash
npx eazyr init          # add --force to overwrite, --dry-run to preview

Writes all four files from the scan. Existing files are skipped unless --force, so this is safe to run in a repo that already has some docs.

This is a draft, not a deliverable. It knows the facts; it does not know your project.

3. Edit it into something true

This is the part only you can do. Work through the generated files and:

  • Resolve every TODO. The generator emits one wherever it couldn't determine a fact.
  • Read the sources. For each sources: ["src/config.ts:14"], open that line and write what the variable actually does. "Stripe API key" beats a repeated variable name.
  • Name where secrets come from. STRIPE_SECRET_KEY → "Create a test-mode key at dashboard.stripe.com/apikeys". The generator cannot know this; a reader is stuck without it.
  • Check CI. .github/workflows/ is the setup that provably works. If it does something the quickstart doesn't, the quickstart is wrong.
  • Fix the ordering if the project has a real constraint the scanner missed — a seed step that must precede first boot, a service that needs a warm-up.
  • Cut what isn't on the critical path. Under 120 lines. Everything else is README material.

references/quickstart.md has the section-by-section spec, references/doctor.md the check conventions, references/detect.md the manual detection table.

Show full SKILL.md (226 more words)Show less
4. Verify
bash
npx eazyr doctor        # runs the derived checks against this machine, writes nothing
bash scripts/doctor.sh  # and confirm the committed script agrees

Then run the install and start commands if you can. Best effort, in this order:

  1. doctor passes, and fails informatively when you unset a required variable.
  2. The install step completes.
  3. The app starts and the verify step returns what the quickstart claims.

Report honestly: what you ran, what passed, what you could not check. If you couldn't run the app, say so plainly rather than implying the path is proven.

When the scanner comes up empty

Unrecognised stack, or a repo too unusual to detect? Fall back to the manual workflow — the artifacts are still the goal:

  1. Read CI, then the task runner, then the container files. CI has to pass, so it doesn't lie.
  2. Reconstruct: prerequisites → clone → install → configure → services → run → verify.
  3. Copy assets/doctor.sh and assets/doctor.ps1 into scripts/, and edit only the CHECKS block — the runner is complete.
  4. Write QUICKSTART.md from assets/QUICKSTART.template.md.

Scope

Write the kit and the scripts that support it. Don't refactor the project, change its dependencies, or rewrite the main README — QUICKSTART.md links from the README, it doesn't replace it. Never copy a real value out of an existing .env; use a placeholder and say you did.

Files

  • references/detect.md — manual stack detection, per ecosystem
  • references/quickstart.md — QUICKSTART.md section spec
  • references/doctor.md — check catalog and script conventions
  • assets/QUICKSTART.template.md, assets/doctor.sh, assets/doctor.ps1, assets/env.example.template — the templates init fills in

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

Files

SKILL.md and 23 other files (references, assets) in apps/eazyr-main of buildfastwithai/gen-ai-experiments.

  • SKILL.md
  • .gitattributes
  • .github/workflows/ci.yml
  • .gitignore
  • LICENSE
  • README.md
  • assets/QUICKSTART.template.md
  • assets/doctor.ps1
  • assets/doctor.sh
  • assets/env.example.template
  • bin/eazyr.mjs
  • package.json
  • references/detect.md
  • references/doctor.md
  • references/quickstart.md
  • src
  • … and 8 more

Open the folder on GitHubat commit 7b62043

Compare with similar skills

Eazyr Repo Onboarding Kit 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.

Eazyr Repo Onboarding Kit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Eazyr Repo Onboarding Kit this skillbuildfastwithai/gen-ai-experiments785—~1.4kAutomated safety check: NotesMIT
Project Onboarding Guide from Knowledge GraphEgonex-AI/Understand-Anything86k—~1.2kAutomated safety check: PassMIT
Deepwiki Rssopaco/deepwiki-rs3.1k—~748Automated safety check: PassMIT
Acquire Codebase Knowledgegithub/awesome-copilot40k1 repos~2.3kAutomated safety check: PassMIT
Codex Proxy RS Development Guidezyycn/codex-proxy-rs766—~618Automated safety check: PassApache-2.0
Githits Codegithits-com/githits-cli114—~2.6kAutomated safety check: PassApache-2.0

Similar skills

  • Writes an onboarding guide for new team members from a project's existing knowledge graph, after checking that the graph still matches the current commit.

    86k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Deepwiki Rs

    sopaco/deepwiki-rs

    AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation.

    3.1k GitHub stars~748 tokensUpdated 25 days ago
    DevelopmentAuto-check passed
  • Acquire Codebase Knowledge

    github/awesome-copilot

    Official

    Maps an unfamiliar codebase into seven evidence-backed documents in docs/codebase/, using a scan script and templates, for onboarding or architecture write-ups.

    40k GitHub starsUsed in 1 repo~2.3k tokens
    DevelopmentAuto-check passed
  • Routes development, troubleshooting, review and documentation tasks on the Codex Proxy RS repository to the right section of its docs, instead of loading the whole architecture or contributing guide.

    766 GitHub stars~618 tokensUpdated today
    DevelopmentAuto-check passed
  • Githits Code

    githits-com/githits-cli

    A skill your agent uses whenever invoking the GitHits CLI for open-source code, documentation, or example evidence, including code search/grep, file navigation, source verification, docs lookup, or…

    114 GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Evidence-Grounded Explainer

    EveryInc/compound-engineering-plugin

    Produces an evidence-backed explanation of how and why something has its current shape, or what happened over a stretch of work, tuned to its intended reader.

    25k GitHub stars~2.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from buildfastwithai/gen-ai-experiments

All 13 skills in this repo
  • Landing Page Generator

    buildfastwithai/gen-ai-experiments

    Builds a single self-contained HTML landing page from a template with copy frameworks, four themes and SEO meta, then runs bundled audit scripts for conversion and speed.

    785 GitHub stars~1.5k tokensUpdated 17 days ago
    Auto-check passed
  • Talking Avatar Voice Chat App

    buildfastwithai/gen-ai-experiments

    Builds a realtime voice-chat app around a talking character portrait made from your photo or a text description, with mouth sprites driven by the audio.

    785 GitHub stars~1.7k tokensUpdated 17 days ago
    Auto-check passed
  • LaunchAudit

    buildfastwithai/gen-ai-experiments

    Audits a startup, app or landing page from a URL, localhost, repository, screenshots or copy, then gives a launch-readiness verdict, prioritized fixes and an HTML report.

    785 GitHub stars~1.8k tokensUpdated 17 days ago
    Auto-check passed
  • Startupblueprint

    buildfastwithai/gen-ai-experiments

    Turn a startup, SaaS, app, developer tool, website, repository, or product idea into an evidence-backed business plan, monetization strategy, pricing architecture, editable 12-month financial model…

    785 GitHub stars~2.2k tokensUpdated 17 days ago
    Auto-check passed
  • Mutation Test Strength Audit

    buildfastwithai/gen-ai-experiments

    Measures how well a Python pytest suite catches behavior changes through diff-scoped mutation testing, then proposes and verifies tests for surviving mutants.

    785 GitHub stars~641 tokensUpdated 17 days ago
    Auto-check passed
  • Customer Finder

    buildfastwithai/gen-ai-experiments

    Find and qualify evidence-backed potential first customers, early adopters, design partners, or beta users for a startup using recent public pain and buying signals.

    785 GitHub stars~1.4k tokensUpdated 17 days ago
    Auto-check passed

Categories

Questions about Eazyr Repo Onboarding Kit

What does Eazyr Repo Onboarding Kit do?

Creates a QUICKSTART, doctor scripts and a documented .env.example for an unfamiliar repo from facts scanned in the repo, and audits how easy it is to onboard. example` listing every variable the app reads. Its one rule is to never write a step it has not verified against the repo.

When should I use Eazyr Repo Onboarding Kit?

Eazyr Repo Onboarding Kit fits situations like: someone cannot get a project running from the existing instructions; onboarding a new developer to an undocumented repo; writing a QUICKSTART, a doctor script or a documented .env.example; auditing whether a repository can be set up by a newcomer at all.

How do I install Eazyr Repo Onboarding Kit in Claude Code?

Run `npx skills add buildfastwithai/gen-ai-experiments --skill eazyr -a claude-code`. Or copy the skill folder (apps/eazyr-main in buildfastwithai/gen-ai-experiments) into .claude/skills/eazyr in your project. Claude Code loads it when a task matches its description.

How do I install Eazyr Repo Onboarding Kit in Codex?

Run `npx skills add buildfastwithai/gen-ai-experiments --skill eazyr -a codex`. Or copy the skill folder (apps/eazyr-main in buildfastwithai/gen-ai-experiments) into .agents/skills/eazyr in your project. Codex loads it when a task matches its description.

Can I use Eazyr Repo Onboarding Kit 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 buildfastwithai/gen-ai-experiments --skill eazyr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/eazyr, .gemini/skills/eazyr, .github/skills/eazyr and .opencode/skills/eazyr in your project.

What does Eazyr Repo Onboarding Kit need to run?

Going by SKILL.md and its folder, Eazyr Repo Onboarding Kit needs PowerShell, a shell and JavaScript for the scripts in its folder, the command-line tools its instructions call (npx and bash) and credentials named STRIPE_SECRET_KEY. Our summary lists: npx, to run the eazyr scanner.

Does Eazyr Repo Onboarding Kit access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Eazyr Repo Onboarding Kit safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Eazyr Repo Onboarding Kit use?

Eazyr Repo Onboarding Kit is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Eazyr Repo Onboarding Kit use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Eazyr Repo Onboarding Kit?

Skills that share tags, products or a category with Eazyr Repo Onboarding Kit: Project Onboarding Guide from Knowledge Graph (Egonex-AI/Understand-Anything, 86k stars), Deepwiki Rs (sopaco/deepwiki-rs, 3.1k stars), Acquire Codebase Knowledge (github/awesome-copilot, 40k stars) and Codex Proxy RS Development Guide (zyycn/codex-proxy-rs, 766 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Eazyr Repo Onboarding Kit?

buildfastwithai (a GitHub organization) maintains it in buildfastwithai/gen-ai-experiments, which has 785 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 22, 2026.

Source: buildfastwithai/gen-ai-experiments on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.