CtrlK
BlogDocsLog inGet started
Tessl Logo

codex-git

Git-aware development workflows with Codex CLI including intelligent commits, PR automation, branch management, and diff application. Use for git operations, PR reviews, or automated git workflows.

56

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/codex-git/SKILL.md

The canonical home for this skill is codex-git in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

46%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.

The body is highly actionable with concrete commands but is excessively long, repetitive, and monolithic with no progressive disclosure. Destructive git workflows lack the validation checkpoints the rubric requires, capping workflow clarity.

Suggestions

Split the body into reference files (e.g. references/cicd.md, references/config.md, references/advanced-workflows.md) and keep SKILL.md as a concise overview with clearly signaled one-level links, cutting the repeated codex exec boilerplate.

Add explicit validation/verification checkpoints to destructive and batch workflows — e.g. after history rewrites or release pushes, require running tests and confirming results before proceeding, with a fix-and-retry feedback loop.

Trim redundant sections and restatements (such as repeated 'codex exec --dangerously-bypass-approvals-and-sandbox' blocks and obvious claims like 'Codex generates high-quality commit messages') to respect the context budget.

DimensionReasoningScore

Conciseness

The ~680-line body is noticeably verbose, repeating the same 'codex exec --dangerously-bypass-approvals-and-sandbox' invocation dozens of times with minor prompt variations, plus padded restatements like 'Codex generates high-quality commit messages' that add little. Not anchor 1 because it does not lecture on concepts Claude already knows; not 3 because the repetition constitutes clear padding rather than isolated over-explanation.

2 / 5

Actionability

Most examples are concrete, copy-paste-ready commands (codex exec, git stash, gh pr view, bash functions), covering common cases well. It falls short of 5 because many examples embed natural-language prompts rather than fully specified executable logic, leaving minor gaps.

4 / 5

Workflow Clarity

Multi-step workflows (develop_feature, create_hotfix, checkpoint_refactoring) are sequenced with numbered steps, but numerous destructive/batch operations (history cleanup, amend, fixup, release push) lack explicit validation checkpoints. Per the rubric's destructive-operations cap, workflow clarity cannot exceed 3 here.

3 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ absent) and the entire 680-line body is inlined with zero references to separate files; content that clearly belongs elsewhere (CI/CD YAML, the config.toml reference, advanced workflows) is all monolithically inlined. Section headers provide some structure, keeping it from anchor 1, but progressive disclosure is effectively absent.

2 / 5

Total

11

/

20

Passed

Description

83%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 well-constructed description that clearly states both capabilities and explicit trigger conditions in third person. It is specific and largely distinct, with only minor gaps in keyword synonyms and slight overlap with related codex skills.

DimensionReasoningScore

Specificity

Names the domain and lists four concrete actions — 'intelligent commits, PR automation, branch management, and diff application' — giving strong coverage with only minor gaps, matching the 'several specific actions' anchor rather than the fully comprehensive 5.

4 / 5

Completeness

It explicitly answers both 'what' (git-aware workflows with the four named capabilities) and 'when' (an explicit 'Use for git operations, PR reviews, or automated git workflows' trigger clause), matching the anchor for clearly answering both with concrete triggers.

5 / 5

Trigger Term Quality

The 'Use for git operations, PR reviews, or automated git workflows' clause supplies natural terms a user would say, but it omits common synonyms like 'commits', 'pull request', and 'merge', so it sits at good-but-not-comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The 'Codex CLI' + git niche is largely distinct, but 'PR reviews' overlaps with the sibling codex-review skill referenced in the body, giving minor overlap risk with a closely related skill rather than the minimal-risk 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (684 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.