Generates a fully structured, project-specific CLAUDE.md by scanning the repo for signal files (package.json, Makefile, .github/workflows/, .env.example, etc.), inferring stack, commands…

MITAuto-check passedAgent Workflows

Install Md Starter

skills CLI
$ npx skills add Infrasity-Labs/dev-gtm-claude-skills --skill md-starter -a claude-code

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

GitHub CLI
$ gh skill install Infrasity-Labs/dev-gtm-claude-skills md-starter --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/Infrasity-Labs/dev-gtm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/notion-skills/claude-md-starter .claude/skills/md-starter && 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
md-starter
GitHub stars
136
Token cost
~2k tokens
SKILL.md length
877 words
Files
4 (incl. references)
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

Generates a fully structured, project-specific CLAUDE.md by scanning the repo for signal files (package.json, Makefile, .github/workflows/, .env.example, etc.), inferring stack, commands…

  • Works in 6 steps: Read the existing file → Complete Nodes 2–4 to produce the… → Compare section by section — for each of… → …
  • The user says create a CLAUDE.md
  • SKILL.md covers Invocation Triggers, Workflow (6 Nodes), Node 1 — Detect and Node 2 — Scan, plus 7 more sections
  • Calls npm

What it does

Md Starter is an agent skill from Infrasity-Labs/dev-gtm-claude-skills. Generates a fully structured, project-specific CLAUDE.md by scanning the repo for signal files (package.json, Makefile, .github/workflows/, .env.example, etc.), inferring stack, commands, architecture, and conventions, then asking at most 3 targeted questions for what cannot be inferred. Use whenever the user says 'create a CLAUDE.md', 'my CLAUDE.md is blank', 'generate project context', 'initialize CLAUDE.md', 'set up Claude context for this repo', 'fill in my CLAUDE.md', or any variation where someone needs…

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/claude-md-template.md`, `references/scan-signals.md` and `references/validation-checklist.md`).

It sits in Agent Workflows, covering Agent instruction files and Project scaffolding. It works with GitHub Actions, npm and Notion. The repository describes itself as: Open-source Claude skills for GEO, AI discoverability, and developer GTM workflows. Built for developer-focused companies that want their documentation to be found, parsed, and… The licence is MIT.

When your agent uses it

  • The user says create a CLAUDE.md
  • My CLAUDE.md is blank
  • Generate project context
  • Initialize CLAUDE.md

Example prompts

  • “create a CLAUDE.md”
  • “my CLAUDE.md is blank”
  • “generate project context”
  • “/md-starter”

Requirements

  • Python 3
  • Docker

Workflow steps

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

  1. Read the existing file
  2. Complete Nodes 2–4 to produce the generated version
  3. Compare section by section — for each of the 8 required sections, classify as
  4. Present a diff summary table
  5. Offer three options
  6. Write the chosen merge result.

What it can do on your machine

Read from SKILL.md and the folder at commit 02cfefb. 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

    Shell commands in SKILL.md call:

    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use npm, 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 no API keys, tokens, secrets or passwords.

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

Context cost

Md Starter loads about 2k tokens when it runs, and up to ~6.3k if it reads all its reference files. Until then it costs about 164 tokens; SKILL.md has 877 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~164
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.3k

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

The full file from Infrasity-Labs/dev-gtm-claude-skills at commit 02cfefb, republished under its MIT licence (© Infrasity-Labs). 877 words, ~2,034 tokens.

Download SKILL.mdSave it as .claude/skills/md-starter/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
md-starter
description
Generates a fully structured, project-specific CLAUDE.md by scanning the repo for signal files (package.json, Makefile, .github/workflows/, .env.example, etc.), inferring stack, commands, architecture, and conventions, then asking at most 3 targeted questions for what cannot be inferred. Use whenever the user says 'create a CLAUDE.md', 'my CLAUDE.md is blank', 'generate project context', 'initialize CLAUDE.md', 'set up Claude context for this repo', 'fill in my CLAUDE.md', or any variation where someone needs their project context documented for Claude. If a CLAUDE.md already exists with content, runs a diff-and-merge flow before writing.
user-invokable
true
metadata.category
utility
metadata.version
1.0.0

Claude.md Starter — Project Context Generator

Scans the repo, infers the tech stack and conventions, asks at most 3 targeted questions, and writes a populated CLAUDE.md that gives Claude full project context from session one.

Invocation Triggers

Explicit:

  • "create a CLAUDE.md"
  • "my CLAUDE.md is blank"
  • "generate project context"
  • "initialize CLAUDE.md"
  • "set up Claude context for this repo"
  • "fill in my CLAUDE.md"
  • "run the claude-md-starter skill"

Implicit:

  • User pastes a near-empty CLAUDE.md and asks Claude to populate it
  • User keeps re-explaining the same project context at the start of sessions

Run immediately when triggered — no upfront questions before scanning.

Workflow (6 Nodes)

NodeRole
1 — DetectCheck if CLAUDE.md exists and measure content length
2 — ScanRead signal files from the project root (see references/scan-signals.md)
3 — InferDraft all sections that can be derived from scanned signals
4 — Grill-meAsk at most 3 questions for what cannot be inferred
5 — GenerateWrite the full CLAUDE.md using the template in references/claude-md-template.md
6 — ValidateConfirm required sections are present and non-placeholder

Node 1 — Detect

Check for CLAUDE.md at the project root.

If not found: Proceed directly to Node 2.

If found and has ≤ 200 characters: Treat as blank — proceed to Node 2.

If found and has > 200 characters: Run the diff-and-merge flow before writing:

  1. Read the existing file

  2. Complete Nodes 2–4 to produce the generated version

  3. Compare section by section — for each of the 8 required sections, classify as:

    • NEW — exists in generated, absent or empty in existing
    • ENHANCED — both versions have content; generated version adds more
    • SAME — both versions have equivalent content
    • CONFLICT — both versions have different non-empty content
  4. Present a diff summary table:

Section              | Existing | Generated | Action
---------------------|----------|-----------|-------
Project Overview     | present  | enhanced  | +additions available
Tech Stack           | absent   | new       | will add
Commands             | present  | enhanced  | +2 commands found
Architecture         | absent   | new       | will add
Code Conventions     | present  | same      | no change
Testing              | absent   | new       | will add
What NOT To Do       | absent   | new       | will add
Environment Setup    | absent   | new       | will add
  1. Offer three options:

    • A (Recommended) — Keep existing content + add new and enhanced sections only (safe, additive)
    • B — Full replace with generated version
    • C — Review each conflicting section individually before writing
  2. Write the chosen merge result.

Node 2 — Scan

Read signal files using the catalog in references/scan-signals.md. For each file found, extract the fields it reveals. Missing files are skipped silently.

Run all reads in parallel where possible:

  1. package.json — framework, scripts, package manager, dependencies
  2. pyproject.toml / requirements.txt / setup.py — Python stack
  3. Cargo.toml / go.mod / pom.xml / build.gradle — language
  4. Makefile / justfile — named commands
  5. .github/workflows/*.yml — CI/CD steps, deploy targets
  6. Dockerfile / docker-compose.yml — runtime environment, services
  7. .eslintrc.* / .prettierrc.* / eslint.config.* — JS/TS code style
  8. ruff.toml / .flake8 / mypy.ini — Python lint/type config
  9. jest.config.* / vitest.config.* / pytest.ini / conftest.py — test framework
  10. tsconfig.json — TypeScript settings
  11. .env.example / .env.sample — required environment variables
  12. README.md (first 40 lines only) — project description
  13. Top-level directory listing — architecture pattern
  14. .gitignore — build artifacts and generated files

Node 3 — Infer

Using scanned data, populate as many sections as possible before asking questions:

  • Project Overview → from README.md first paragraph; fall back to package.json description field
  • Tech Stack → from language files + framework dependencies
  • Commands → from package.json scripts, Makefile targets, workflow run steps
  • Architecture → from top-level directory structure
  • Code Conventions → from eslint/prettier/ruff config values
  • Testing → from test config files and test directory location
  • What NOT To Do → from .gitignore build outputs, workflow branch protection, lock files
  • Environment Setup → from .env.example variable names and docker-compose services
Show full SKILL.md (360 more words)Show less

Node 4 — Grill-Me Intake

Ask only for what cannot be inferred. Maximum 3 questions. Skip any question whose answer is already clear from scanned files.

Present all applicable questions together in one message — never ask them across multiple turns:

Quick questions to finish your CLAUDE.md (answer whichever apply):

  1. What does this project do in one sentence? (skip if README was found)
  2. Are there any files, directories, or systems that should never be touched or auto-modified by Claude?
  3. Any team conventions not captured in your lint config? (naming patterns, PR size, commit format, review process)

Node 5 — Generate

Produce the CLAUDE.md using the exact section structure from references/claude-md-template.md.

Critical rules:

  • Every populated section must have real content — no [TODO: add your X here] placeholders
  • If a section cannot be filled at all, omit it entirely rather than writing a placeholder
  • Commands must be exact and runnable (npm run dev, not "run the dev server")
  • What NOT To Do must have at least 2 entries
  • Write in imperative, direct style ("Run tests with...", "Never edit files in...")
  • No heading levels deeper than H2 within sections

Node 6 — Validate

Before writing, verify against references/validation-checklist.md:

  • All populated sections have real content (no placeholders)
  • Commands section has ≥ 2 runnable commands
  • What NOT To Do has ≥ 2 entries
  • No unreplaced placeholder text remains
  • If existing CLAUDE.md had > 200 characters, diff-and-merge flow was completed

If Commands or What NOT To Do would fail: ask one final targeted question before writing.

Output

Write the file to CLAUDE.md at the project root. After writing, print a one-line confirmation:

✓ CLAUDE.md written — X sections populated from repo scan, Y from your answers.

If in diff-and-merge mode, also print which sections were added vs. left unchanged.

Anti-Patterns To Reject

  • Generating CLAUDE.md without running the scan first
  • Asking more than 3 intake questions
  • Writing placeholder sections ("add your commands here")
  • Overwriting an existing populated CLAUDE.md without running the diff-and-merge flow
  • Writing generic boilerplate not specific to the scanned project
  • Including commands that weren't found in signal files and weren't confirmed by the user

References

  • references/scan-signals.md — full catalog of signal files and what each reveals
  • references/claude-md-template.md — canonical CLAUDE.md section structure and style rules
  • references/validation-checklist.md — required fields and quality gates before writing

Version: 1.0.0

© Infrasity-Labs, 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 3 other files (references) in notion-skills/claude-md-starter of Infrasity-Labs/dev-gtm-claude-skills.

  • SKILL.md
  • references/claude-md-template.md
  • references/scan-signals.md
  • references/validation-checklist.md

Open the folder on GitHubat commit 02cfefb

Compare with similar skills

Md Starter 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.

Md Starter compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Md Starter this skillInfrasity-Labs/dev-gtm-claude-skills136—~2kAutomated safety check: PassMIT
Harness Initk1ein-chen/Harness-Starter119—~995Automated safety check: NotesMIT
Agent Prompts Warmupiamtouchskyer/memex143—~1kAutomated safety check: PassMIT
MCP Server Trello Releasedelorenj/mcp-server-trello445—~3.5kAutomated safety check: PassMIT
Ad HooksCorridorTech/PoseCap224—~2.4kAutomated safety check: NotesApache-2.0
Ad HooksCorridorTech/PoseCap224—~1.7kAutomated safety check: PassApache-2.0

Similar skills

  • Harness Init

    k1ein-chen/Harness-Starter

    Initialize this project with the Harness Engineering starter template.

    119 GitHub stars~995 tokensUpdated 17 days ago
    Agent WorkflowsAuto-check: notes
  • Agent Prompts Warmup

    iamtouchskyer/memex

    Audit and sync agent instruction files across all coding agent formats.

    143 GitHub stars~1k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • MCP Server Trello Release

    delorenj/mcp-server-trello

    Canonical build → release → tag → publish procedure for the @delorenj/mcp-server-trello repo.

    445 GitHub stars~3.5k tokensUpdated 17 days ago
    DevelopmentAuto-check passed
  • Ad Hooks

    CorridorTech/PoseCap

    Scaffold deterministic quality gates per WORKFLOW.md §11 — pre-commit (lint, format, secret-scan), pre-push (build, unit, integration).

    224 GitHub stars~2.4k tokensUpdated 4 days ago
    Testing & QAAuto-check: notes
  • Ad Hooks

    CorridorTech/PoseCap

    Scaffold deterministic quality gates per WORKFLOW.md §11 — pre-commit (lint, format, secret-scan), pre-push (build, unit, integration).

    224 GitHub stars~1.7k tokensUpdated 4 days ago
    Testing & QAAuto-check passed
  • OpenCode Plugin Creator

    Devin-AXIS/iPolloWork

    Scaffolds an OpenCode plugin for iPolloWork with the right async factory shape, zod-based tool definitions and hook registration, and explains where to place and register it.

    6.8k GitHub starsUsed in 1 repo~1.3k tokens
    Agent WorkflowsAuto-check passed

More from Infrasity-Labs/dev-gtm-claude-skills

All 26 skills in this repo
  • Brief Outline Generator

    Infrasity-Labs/dev-gtm-claude-skills

    Generates a fully structured SEO content outline (not a finished brief) and exports it as a formatted .docx Word document.

    136 GitHub stars~4k tokensUpdated 3 mo ago
    Auto-check passed
  • Content Brief

    Infrasity-Labs/dev-gtm-claude-skills

    Generates a fully structured SEO content brief for a target keyword and optionally pushes it to a Notion database.

    136 GitHub stars~2.8k tokensUpdated 3 mo ago
    Auto-check passed
  • API Docs Quality Report

    Infrasity-Labs/dev-gtm-claude-skills

    Audits any API documentation site by crawling every endpoint page and scoring each one across 5 checks: description quality, OpenAPI spec presence, body param descriptions, response codes, and…

    136 GitHub stars~2.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Docs Auditor

    Infrasity-Labs/dev-gtm-claude-skills

    Audits any developer documentation site across 33 checks in 7 categories and produces a scored report (out of 100) with Pass / Warn / Fail status per check.

    136 GitHub stars~3k tokensUpdated 3 mo ago
    Auto-check passed
  • Growth Report

    Infrasity-Labs/dev-gtm-claude-skills

    Generates a 3-month SEO performance HTML report for any domain using DataForSEO data.

    136 GitHub stars~4k tokensUpdated 3 mo ago
    Auto-check passed
  • Inbox

    Infrasity-Labs/dev-gtm-claude-skills

    Email triage system that handles both one-time setup and recurring triage in a single skill.

    136 GitHub stars~4.8k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Md Starter

What does Md Starter do?

Generates a fully structured, project-specific CLAUDE.md by scanning the repo for signal files (package.json, Makefile, .github/workflows/, .env.example, etc.), inferring stack, commands…. Md Starter is an agent skill from Infrasity-Labs/dev-gtm-claude-skills.), inferring stack, commands, architecture, and conventions, then asking at most 3 targeted questions for what cannot be inferred.

When should I use Md Starter?

Md Starter fits situations like: the user says create a CLAUDE.md; my CLAUDE.md is blank; generate project context; initialize CLAUDE.md.

How do I install Md Starter in Claude Code?

Run `npx skills add Infrasity-Labs/dev-gtm-claude-skills --skill md-starter -a claude-code`. Or copy the skill folder (notion-skills/claude-md-starter in Infrasity-Labs/dev-gtm-claude-skills) into .claude/skills/md-starter in your project. Claude Code loads it when a task matches its description.

How do I install Md Starter in Codex?

Run `npx skills add Infrasity-Labs/dev-gtm-claude-skills --skill md-starter -a codex`. Or copy the skill folder (notion-skills/claude-md-starter in Infrasity-Labs/dev-gtm-claude-skills) into .agents/skills/md-starter in your project. Codex loads it when a task matches its description.

Can I use Md Starter 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 Infrasity-Labs/dev-gtm-claude-skills --skill md-starter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/md-starter, .gemini/skills/md-starter, .github/skills/md-starter and .opencode/skills/md-starter in your project.

What does Md Starter need to run?

Going by SKILL.md and its folder, Md Starter needs the command-line tools its instructions call (npm). Our summary lists: Python 3; Docker.

Does Md Starter access the network?

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

Is Md Starter 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 Md Starter use?

Md Starter is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Md Starter use?

About 2k tokens (SKILL.md is roughly 8.1k 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 4.2k tokens, read only when the agent opens those files.

What are the alternatives to Md Starter?

Skills that share tags, products or a category with Md Starter: Harness Init (k1ein-chen/Harness-Starter, 119 stars), Agent Prompts Warmup (iamtouchskyer/memex, 143 stars), MCP Server Trello Release (delorenj/mcp-server-trello, 445 stars) and Ad Hooks (CorridorTech/PoseCap, 224 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Md Starter?

Infrasity-Labs (a GitHub user) maintains it in Infrasity-Labs/dev-gtm-claude-skills, which has 136 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on June 28, 2026.

Source: Infrasity-Labs/dev-gtm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.