Name: git-pushing
Rating: 64.8 (1 reviews)
Author: administrakt0r

git-pushing

Stage all changes, create a conventional commit, and push to the remote branch. Use when explicitly asks to push changes ("push this", "commit and push"), mentions saving work to remote ("save to github", "push to remote"), or completes a feature and wants to share it.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/git-pushing/SKILL.md

The canonical home for this skill is git-pushing in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

64%Scale 1-5

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

This is a concise, focused skill that delegates the core workflow to a script, keeping the SKILL.md lean. Its main weaknesses are the lack of validation/error-handling steps for a destructive operation (pushing to remote) and no visibility into what the referenced script actually does, which limits troubleshooting ability. The trigger phrase list adds some unnecessary bulk.

Suggestions

Add validation checkpoints: verify current branch, review staged changes before pushing, and confirm push succeeded (e.g., check exit code or remote status).

Add a brief summary of what smart_commit.sh does internally (or reference a README in the scripts directory) so Claude can troubleshoot failures.

Include error recovery guidance: what to do if push is rejected (e.g., pull --rebase first) or if the script fails.

Dimension	Reasoning	Score
Conciseness	Mostly efficient. The 'When to Use' section listing trigger phrases is slightly verbose since this is contextual information that could be trimmed, but overall the content is lean and doesn't over-explain concepts Claude already knows.	4 / 5
Actionability	Provides concrete, executable bash commands with both default and custom message usage. However, it delegates all logic to an external script without showing what the script does internally, which means Claude can't troubleshoot or adapt if the script fails.	4 / 5
Workflow Clarity	The workflow is essentially 'run this script,' which is simple but lacks any validation or error handling steps. Since git push is a potentially destructive operation (pushing to remote), the absence of any verification steps (e.g., check branch, review staged changes, confirm push succeeded) caps this at 3 per the rubric guidelines.	3 / 5
Progressive Disclosure	References an external script at a specific path (skills/git-pushing/scripts/smart_commit.sh), but no bundle files are provided to verify the script exists. The skill is short enough that it doesn't need external documentation files, but the lack of any insight into what the script does (or a reference to its source) is a minor gap.	3 / 5
	Total	14 / 20 Passed

Description

91%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.

This is a strong skill description that clearly communicates the three-step workflow (stage, commit, push) and provides excellent trigger guidance with natural user phrases. The 'Use when' clause is well-constructed with multiple realistic scenarios. Minor improvements could include mentioning 'git' explicitly as a trigger term and specifying what 'conventional commit' entails.

Dimension	Reasoning	Score
Specificity	Lists three specific actions: 'stage all changes', 'create a conventional commit', and 'push to the remote branch'. These are concrete and actionable, though it could mention additional details like branch selection or commit message formatting.	4 / 5
Completeness	Clearly answers both 'what' (stage, commit, push) and 'when' with an explicit 'Use when' clause containing multiple concrete trigger scenarios. The trigger phrases cover different user intents comprehensively.	5 / 5
Trigger Term Quality	Excellent coverage of natural trigger phrases users would actually say: 'push this', 'commit and push', 'save to github', 'push to remote', 'share it'. These are realistic, varied, and include common synonyms and phrasings.	5 / 5
Distinctiveness Conflict Risk	Fairly distinct with its focus on the full stage-commit-push workflow and conventional commits. Minor overlap risk with a skill that only generates commit messages (like the rubric's example), but the push-to-remote aspect and specific trigger terms help differentiate it.	4 / 5
	Total	18 / 20 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/git-pushing/SKILL.md
Commit: 7520423

Reviewed: ~7 hours ago

Table of Contents

Discovery Implementation Validation

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.