Atlas / Skills / mattzimak / claude-code-handbook

claude-code-handbookSAFE

skills/mattzimak/claude-code-handbook

A founder's handbook for Claude Code - the skills, hooks, prompts and workflows I actually run across three companies. 136 entries, each says why it earned its place.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
—
Hosts
6 documented
License
CC-BY-4.0
Stars
0
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

164 entries · last verified 2026-10-10 · 164 links checked · 0 dead

One founder's handbook for running a company on Claude Code: the skills I install, the setups I copied, the rules I keep, and the people worth learning from. It is not a directory of everything that exists - if something is here, it earned its place in real work. Suggest a link by opening an issue (see CONTRIBUTING.md).

Descriptions are my own notes where I wrote one. Where I only saved a link, the description is the repository's or the post's own summary. Ratings like (Matt: 8/10) are my personal scores.

Contents

  • Start here
  • Learn
  • Agent teams and subagents
  • Prompting
  • Skills
  • General
  • Token burn & models
  • Webdesign taste skills
  • Webdesign dev skills
  • Webdesign MCP & UI elements
  • Project management
  • Development
  • Research
  • Image & Video Editing
  • Marketing - Content & Writing
  • Marketing - Ads & SEO
  • Installed on my machine
  • Collections
  • Field notes
  • General best practices
  • Plan vs bypass mode
  • Effort
  • Prompting basics
  • Structure
  • CLAUDE.md
  • Security and passwords
  • Context
  • Hooks
  • Personal assistant
  • Tools and memory
  • n8n with Claude Code
  • Other useful lists
  • How this list is built
  • License

Start he

Read from source at commit 6098ff0d0218OBSERVED · 2026-10-10
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
codexmentioned
copilotmentioned
cursormentioned
openclawmentioned
windsurfmentioned
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (3)

MEDIUMInventory / provenance · skill.no_skill_md · CWE-1104
Why it matters. no SKILL.md at the audited path
Fix. a skill without its instruction file cannot be reviewed as one
LOWInventory / provenance · inv.hidden_file · CWE-1104
.gitleaks.toml
.gitleaks.toml
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
README.md:141
- [Caveman](https://github.com/JuliusBrussee/caveman) - Cuts 65% of token usage by instructing Claude to respond in compressed, caveman-style shorthand - ideal for long sessions where context budget m
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine

Gates applied: no_behavioural_pass.

Audited 2026-10-10 · audit v0.4.1 · source sha 6098ff0d0218full audit observations/trust-audit/skill/mattzimak__claude-code-handbook.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-106098ff0d0218SAFEB89first audit
05

Questions

What does the claude-code-handbook skill do?

A founder's handbook for Claude Code - the skills, hooks, prompts and workflows I actually run across three companies. 136 entries, each says why it earned its place.

Is claude-code-handbook safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can claude-code-handbook access on my machine?

The audit observed that it reaches the network. Each of those is consistent with what it says it does. Secrets in the source: none found.

Which assistants does claude-code-handbook work with?

Its documentation mentions claude-code, codex, copilot, cursor, openclaw and windsurf. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (6098ff0d0218), read on 2026-10-10. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement