CtrlK
BlogDocsLog inGet started
Tessl Logo

here-be-git

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.

85

1.20x
Quality

77%

Does it follow best practices?

Impact

100%

1.20x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/here-be-git/skills/SKILL.md

The canonical home for this skill is here-be-git in intellectronica/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A clear, actionable, well-sequenced skill body that mostly respects Claude's competence. The main weakness is verbosity in the commit-instructions template, and exact git commit commands are left implicit.

Suggestions

Tighten the AGENTS.md commit-instructions block: drop the redundant dramatic emphasis (e.g. "CRITICAL, MANDATORY, NO EXCEPTIONS" + "ZERO exceptions" + "Do not defer. Do not batch. Do not skip.") to one concise statement of the rule.

Spell out the commit commands, e.g. `git add AGENTS.md && git commit -m "Add agent commit workflow"`, so the workflow is fully copy-paste ready.

Add a post-commit validation checkpoint such as running `git status` to confirm the working tree is clean before moving on.

DimensionReasoningScore

Conciseness

Mostly efficient, but the AGENTS.md commit-instructions block is padded with emphatic repetition ("CRITICAL, MANDATORY, NO EXCEPTIONS", "ZERO exceptions", "Do not defer. Do not batch. Do not skip.") that could be tightened without losing intent.

3 / 5

Actionability

Provides copy-paste-ready content for AGENTS.md and concrete .gitignore patterns per flavour, plus `git init`; the exact `git add`/`git commit` commands for committing AGENTS.md and .gitignore are implied but not spelled out, a minor gap.

4 / 5

Workflow Clarity

The three-step sequence is clear with user-confirmation checkpoints and a guard for an already-initialised repo; the missing validation step is only a post-commit `git status` check, so it sits at 4 rather than 5.

4 / 5

Progressive Disclosure

Well-organized into Workflow / Steps / Notes with no external references needed; the sizeable inline commit-instructions template could arguably live in a separate reference file, which is the minor gap keeping it below 5.

4 / 5

Total

15

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, concrete actions, explicit trigger phrases, and a clearly bounded niche. The only slack is in specificity and trigger coverage, where a few more concrete capabilities and natural synonyms would push it to the top anchor.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — "Initialise a git repository", "optional agent commit instructions", and ".gitignore" — but stops short of the comprehensive multi-action coverage of a 5.

4 / 5

Completeness

Explicitly answers both what (initialise a git repo with optional commit instructions and .gitignore) and when, with concrete trigger phrases via the "Use when users say..." clause.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say ("here be git", "init git", "initialise git") plus the synonym pair init/initialise and "set up version control"; a few natural variations like "make this a git repo" are missing, keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (git repo setup) with distinctive triggers like "here be git" and "init git", giving it minimal overlap with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
intellectronica/agent-skills
Reviewed

Table of Contents

Is this your skill?

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.