Project Onboarding Guide from Knowledge Graph
Egonex-AI/Understand-Anything
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.
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.
$ npx skills add buildfastwithai/gen-ai-experiments --skill eazyr -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install buildfastwithai/gen-ai-experiments eazyr --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/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/eazyr-main .claude/skills/eazyr && 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 "eazyr" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/apps/eazyr-main into .claude/skills/eazyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eazyr", 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/buildfastwithai/gen-ai-experiments/tree/main/apps/eazyr-mainType 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 buildfastwithai/gen-ai-experiments --skill eazyr -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install buildfastwithai/gen-ai-experiments eazyr --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .agents/skills && cp -r skills-src/apps/eazyr-main .agents/skills/eazyr && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "eazyr" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/apps/eazyr-main into .agents/skills/eazyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eazyr", 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 buildfastwithai/gen-ai-experiments --skill eazyr -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install buildfastwithai/gen-ai-experiments eazyr --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/apps/eazyr-main .cursor/skills/eazyr && 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 "eazyr" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/apps/eazyr-main into .cursor/skills/eazyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eazyr", 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/buildfastwithai/gen-ai-experiments.git --path apps/eazyr-main--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 buildfastwithai/gen-ai-experiments --skill eazyr -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install buildfastwithai/gen-ai-experiments eazyr --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/apps/eazyr-main .gemini/skills/eazyr && 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 "eazyr" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/apps/eazyr-main into .gemini/skills/eazyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eazyr", 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 buildfastwithai/gen-ai-experiments eazyrInstalls 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 buildfastwithai/gen-ai-experiments --skill eazyr -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .github/skills && cp -r skills-src/apps/eazyr-main .github/skills/eazyr && 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 "eazyr" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/apps/eazyr-main into .github/skills/eazyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eazyr", 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 buildfastwithai/gen-ai-experiments --skill eazyr -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install buildfastwithai/gen-ai-experiments eazyr --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/apps/eazyr-main .opencode/skills/eazyr && 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 "eazyr" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/apps/eazyr-main into .opencode/skills/eazyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eazyr", 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.
eazyrCreates 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.
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.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 7b62043. It shows what the files ask for, not the result of running them.
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.
Ships script files (PowerShell, Shell and JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
npxbashFrom the folder's file list and the shell code blocks in SKILL.md.
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.
Names these keys or tokens, usually read from environment variables:
STRIPE_SECRET_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
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.
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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
er copy a real value out of an existing `.env`; use a placeholderAutomated 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.
The full file from buildfastwithai/gen-ai-experiments at commit 7b62043, republished under its MIT licence (© buildfastwithai). 688 words, ~1,363 tokens.
.claude/skills/eazyr/SKILL.md (or your agent's skills folder). This skill also uses 23 other files; get the full folder from GitHub.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:
| Artifact | Purpose |
|---|---|
QUICKSTART.md | The shortest correct path from clone to "it works" |
scripts/doctor.sh + scripts/doctor.ps1 | Runnable checks that fail loudly before setup wastes an hour |
.env.example | Every variable the app reads, documented, with safe defaults |
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.
npx eazyr scan --jsonReturns: 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:
npx eazyr scanThe 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.
npx eazyr init # add --force to overwrite, --dry-run to previewWrites 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.
This is the part only you can do. Work through the generated files and:
TODO. The generator emits one wherever it couldn't determine a fact.sources: ["src/config.ts:14"], open that line and write
what the variable actually does. "Stripe API key" beats a repeated variable name.STRIPE_SECRET_KEY → "Create a test-mode key at
dashboard.stripe.com/apikeys". The generator cannot know this; a reader is stuck without it..github/workflows/ is the setup that provably works. If it does something
the quickstart doesn't, the quickstart is wrong.references/quickstart.md has the section-by-section spec, references/doctor.md the
check conventions, references/detect.md the manual detection table.
npx eazyr doctor # runs the derived checks against this machine, writes nothing
bash scripts/doctor.sh # and confirm the committed script agreesThen run the install and start commands if you can. Best effort, in this order:
doctor passes, and fails informatively when you unset a required variable.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.
Unrecognised stack, or a repo too unusual to detect? Fall back to the manual workflow — the artifacts are still the goal:
assets/doctor.sh and assets/doctor.ps1 into scripts/, and edit only the
CHECKS block — the runner is complete.QUICKSTART.md from assets/QUICKSTART.template.md.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.
references/detect.md — manual stack detection, per ecosystemreferences/quickstart.md — QUICKSTART.md section specreferences/doctor.md — check catalog and script conventionsassets/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
SKILL.md and 23 other files (references, assets) in apps/eazyr-main of buildfastwithai/gen-ai-experiments.
Open the folder on GitHubat commit 7b62043
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Eazyr Repo Onboarding Kit this skillbuildfastwithai/gen-ai-experiments | 785 | — | ~1.4k | Automated safety check: Notes | MIT | |
| Project Onboarding Guide from Knowledge GraphEgonex-AI/Understand-Anything | 86k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Deepwiki Rssopaco/deepwiki-rs | 3.1k | — | ~748 | Automated safety check: Pass | MIT | |
| Acquire Codebase Knowledgegithub/awesome-copilot | 40k | 1 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Codex Proxy RS Development Guidezyycn/codex-proxy-rs | 766 | — | ~618 | Automated safety check: Pass | Apache-2.0 | |
| Githits Codegithits-com/githits-cli | 114 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 |
Egonex-AI/Understand-Anything
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.
sopaco/deepwiki-rs
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation.
github/awesome-copilot
Maps an unfamiliar codebase into seven evidence-backed documents in docs/codebase/, using a scan script and templates, for onboarding or architecture write-ups.
zyycn/codex-proxy-rs
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.
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…
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.
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.
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.
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.
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…
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.
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.
Categories
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.