CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

70%

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

57%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 command-dense reference that is highly actionable, with complete bash functions and CI examples covering commits, PRs, hotfixes, releases, and bisect. Weaknesses are duplicated safety sections, inlined long-form content that should be split into reference files, and missing validation in several destructive history-rewriting workflows.

Suggestions

Deduplicate the safety material repeated across 'Git Safety Patterns', 'Safety with Automation', and 'Troubleshooting' into a single section, and remove the dated 'Last Updated: December 2025' line.

Add explicit validation/backup steps to destructive workflows — e.g., create a backup branch or run tests before 'Clean up last 5 commits' and before merge-conflict automation.

Move the CI/CD workflow YAML examples, bash automation functions, and TOML config reference into separate files under references/ and link to them from SKILL.md.

DimensionReasoningScore

Conciseness

The body is mostly executable examples without concept-explanation padding, but safety guidance is duplicated across 'Git Safety Patterns', 'Safety with Automation', and 'Troubleshooting', and time-sensitive filler ('Last Updated: December 2025 (GPT-5.2 Release)', 'Created for Claude Code') pads the document. Anchor 3 — mostly efficient but could be tightened.

3 / 5

Actionability

Nearly every section gives copy-paste ready commands and complete bash functions (develop_feature, create_hotfix), YAML CI workflows, and TOML config. Minor gaps keep it below anchor 5: the CI example assumes pr-analysis.json contains a 'summary' field, and flag combinations like '--search --dangerously-bypass-approvals-and-sandbox' are unverified.

4 / 5

Workflow Clarity

Sequences are clearly numbered and several workflows include checkpoints ('Run tests after each checkpoint', 'git apply --check', stash-and-restore-on-failure), but destructive history-rewrite workflows ('Squash WIP commits... Reorder for logical flow', 'Fix last 3 commits') and merge-conflict automation lack validation or backup steps. Per the rubric's cap, destructive/batch workflows without validation cannot score above 3.

3 / 5

Progressive Disclosure

Section headers are well organized, but the ~680-line body inlines large CI/CD workflow YAML, bash automation functions, and a TOML config reference that belong in separate reference files; no bundle files exist. Anchor 3 — some structure but content that should be separate is inline.

3 / 5

Total

13

/

20

Passed

Description

71%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 solid description with an explicit what-plus-when structure, four concrete named capabilities, and natural trigger keywords in third-person voice. Its main weaknesses are a slightly generic when-clause and a trigger phrase set that omits the Codex qualifier, creating overlap risk with generic git/PR skills.

Suggestions

Include the Codex qualifier in the when-clause (e.g., 'Use when the user asks to automate git tasks — commits, PRs, branch management — with Codex CLI') to reduce conflict with generic git and code-review skills.

Add missing natural trigger synonyms such as 'pull request', 'commit messages', and 'merge' to the use-when clause.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'intelligent commits, PR automation, branch management, and diff application' — in third-person voice. Not anchor 5 because coverage has minor gaps (merge/rebase/history workflows detailed in the body are absent from the description); clearly above anchor 3's 1-2 actions.

4 / 5

Completeness

Explicitly answers both what ('Git-aware development workflows with Codex CLI including intelligent commits, PR automation, branch management, and diff application') and when ('Use for git operations, PR reviews, or automated git workflows'). The when-clause is present but slightly generic compared to anchor 5's concrete trigger phrases, so it sits at anchor 4.

4 / 5

Trigger Term Quality

'git operations, PR reviews, or automated git workflows' plus 'commits', 'branch', and 'diff application' are natural phrases users would say. A few common terms are missing (e.g., 'pull request', 'merge', 'commit messages'), matching anchor 4 rather than the comprehensive synonym/extension coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The 'what' names Codex CLI, carving a niche from generic git skills, but the when-clause ('Use for git operations, PR reviews, or automated git workflows') omits the Codex qualifier, so ordinary git or PR-review requests could route here over closely related skills — anchor 3's 'could still overlap with similar skills' is the best fit.

3 / 5

Total

15

/

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.

Validation — 15 / 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

Path

.claude/skills/codex-git/SKILL.md

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.