google-engineer-skills
AGENTS.md5 starsChanged 8 months agoMITView on GitHub
Guidelines for AI agents working in this Google Engineer Skills repository. This is a curated collection of AI agent skills for Google Cloud engineers. Skills are markdown documentation files that teach AI agents how to perform specific tasks. All skills MUST include this frontmatter at the top: python) - Line length: Wrap at 120 characters for readability - British English: Use British spelling (e.g., customise, colour, analyse)
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository15 other files it gives its agents.
- charm-vhsSkill
- cloud-foundation-fabricSkill
- d2Skill
- duckdbSkill
- github-profile-architectSkill
- jqSkill
- opencode-devSkill
- playwright-cliSkill
- skill-crawlerSkill
- skill-registry-syncSkill
- tech-writerSkill
- terminal-ui-engineerSkill
- terraformSkill
- worktrunkSkill
- writingSkill
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 45
All skills MUST include this frontmatter at the top:
- Very specific: line 63
Headers: Use sentence case (# Quick Start not # Quick start)
- Distinctive: line 64
Lists: No colons at start of bullet points
- Very specific: line 66
Code blocks: Always specify language (e.g., `
bash,`python) - Distinctive: line 68
British English: Use British spelling (e.g., customise, colour, analyse)
- Distinctive: line 90
Use type hints for function signatures
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS.md
Guidelines for AI agents working in this Google Engineer Skills repository.
Repository Overview
This is a curated collection of AI agent skills for Google Cloud engineers. Skills are markdown documentation files that teach AI agents how to perform specific tasks.
Directory Structure
skills/
├── <skill-name>/
│ ├── SKILL.md # Main skill documentation (REQUIRED)
│ └── references/ # Additional reference docs (OPTIONAL)
│ └── <topic>.mdBuild Commands
Setup
# Copy mise configuration and install tools
cp mise.toml.example mise.toml && mise upValidation
# Check all skills have required frontmatter
for skill in skills/*/SKILL.md; do
echo "Checking $skill..."
head -20 "$skill" | grep -E "^(name:|description:)" || echo "ERROR: Missing fields in $skill"
done
# Generate banner assets
python scripts/generate_banners.pyCode Style Guidelines
SKILL.md Frontmatter (YAML)
All skills MUST include this frontmatter at the top:
---
name: <skill-name> # Lowercase, hyphenated, matches directory
version: "1.0.0" # Optional but recommended
description: <Action>. Use when you need to <use case> # 1-1024 chars
metadata:
source_url: https://github.com/... # Optional: upstream source
docs_url: https://docs.example.com # Optional: documentation link
related_skills: # Optional: related skills
- skill-name-1
- skill-name-2
---Markdown Style
- Headers: Use sentence case (
# Quick Startnot# Quick start) - Lists: No colons at start of bullet points
- Bullet points: Complete sentences, 1-3 sentences each
- Code blocks: Always specify language (e.g.,
bash,python) - Line length: Wrap at 120 characters for readability
- British English: Use British spelling (e.g., customise, colour, analyse)
Naming Conventions
- Skill names: Lowercase with hyphens (
docker-cli,gcp-deploy) - Directories: Match skill name exactly (
skills/docker-cli/) - Files:
SKILL.md(uppercase),references/(lowercase) - References: lowercase-with-hyphens.md
Content Organization
# Title
## Quick Start # 3-5 most common commands
## Commands # Grouped by category
## Examples # Real-world scenarios
## Tips # Best practices
## Troubleshooting # Common issuesPython Scripts Style
- Use type hints for function signatures
- UTF-8 encoding for file operations
- f-strings for string formatting
- 4-space indentation, 120 char line limit
Example:
def create_banner(filename: str, title: str) -> None:
"""Generate an SVG banner."""
with open(filename, "w", encoding="utf-8") as f:
f.write(content)Testing Skills
# Add skill locally for testing
npx skills add . --skill <skill-name>
npx skills listCommon Tasks
Creating a New Skill
mkdir skills/<skill-name>
touch skills/<skill-name>/SKILL.md
# Add SKILL.md with required frontmatter, test with npx skills add
# Update README.md skills tableAdding References
mkdir -p skills/<skill-name>/references
touch skills/<skill-name>/references/<topic>.md
# Link from SKILL.md: [references/topic.md](references/topic.md)Git Workflow
git diff skills/<skill-name>/SKILL.md
git add skills/<skill-name>/
git commit -m "feat(skill-name): add section on X"Pre-commit Checklist
- YAML frontmatter is valid
- Name matches directory exactly
- Description under 1024 characters
- Quick start commands tested
- Examples are complete
- No markdown syntax errors
- British English spelling used
- Code blocks have language tags
External References
- agentskills.io — Official skill specifications
- vercel-labs/skills — CLI registry
- mise — Tool version manager
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

