Initialise a git repository with optional agent commit instructions and .gitignore. Use when users say "here be git", "init git", "initialise git", or otherwise indicate they want to set up version control in the current directory.
Install with Tessl CLI
npx tessl i github:intellectronica/agent-skills --skill here-be-git84
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
Node.js git setup with agent commit instructions
AGENTS.md heading
50%
100%
All four commit rules
70%
100%
To be absolutely clear section
0%
100%
AGENTS.md committed
50%
100%
node_modules/ ignored
100%
100%
dist/ ignored
100%
100%
.env ignored
100%
100%
*.log ignored
100%
100%
.gitignore committed
100%
100%
Atomic separate commits
100%
100%
Without context: $0.3560 · 1m 16s · 18 turns · 19 in / 4,226 out tokens
With context: $0.4806 · 1m 26s · 26 turns · 74 in / 4,521 out tokens
Append commit instructions to existing AGENTS.md
Original content preserved
100%
100%
Original deployment section preserved
100%
100%
Commit instructions appended
100%
100%
AGENTS.md mandatory heading
0%
100%
All four commit rules
46%
100%
To be absolutely clear section
0%
100%
AGENTS.md committed
100%
100%
Commit message quality
100%
100%
Without context: $0.1949 · 48s · 9 turns · 10 in / 2,536 out tokens
With context: $0.4903 · 1m 33s · 26 turns · 395 in / 5,001 out tokens
Python gitignore with custom patterns
__pycache__/ ignored
100%
100%
*.pyc ignored
100%
100%
venv ignored
100%
100%
.env ignored
100%
100%
*.egg-info/ ignored
100%
100%
data/ ignored
100%
100%
*.pkl ignored
100%
100%
secrets.json ignored
100%
100%
.gitignore committed
100%
100%
Without context: $0.2115 · 43s · 11 turns · 12 in / 2,591 out tokens
With context: $0.4212 · 1m 15s · 21 turns · 21 in / 4,617 out tokens
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.