Skills backend-atomic-commit

📦

backend-atomic-commit

Name: backend-atomic-commit
Author: DiversioTeam

Content revision r1 High Risk ⚙️ External commands📁 Filesystem access

Prepare Backend Atomic Commits

Backend commits often fail review because formatting, tests, and staged scope drift apart. This skill runs strict local checks, fixes safe issues, and prepares a focused commit summary.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "backend-atomic-commit" from https://skillstore.io/skills/diversioteam-backend-atomic-commit.md and its manifest at https://skillstore.io/api/skills/diversioteam-backend-atomic-commit/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/diversioteam-backend-atomic-commit.md Signed manifest GET /api/skills/diversioteam-backend-atomic-commit/manifest Signed lockfile GET /api/skills/diversioteam-backend-atomic-commit/lockfile

Test it

Using "backend-atomic-commit". A developer asks for pre-commit cleanup on modified Django files.

Expected outcome:

Summary of safe fixes applied to formatting, imports, and type hints.
List of checks that passed, failed, or could not run locally.
Remaining issues grouped by blocking, should-fix, and minor categories.

Using "backend-atomic-commit". A developer asks whether staged backend changes are ready to commit.

Expected outcome:

Atomicity assessment for the staged file set.
Quality gate results for available local tooling.
A proposed human-style commit subject when no blockers remain.

Using "backend-atomic-commit". A team lead asks for review prep on a migration-heavy change.

Expected outcome:

Risk notes for schema changes and rollout order.
Recommended targeted tests for affected Django apps.
Clear next steps before the change is considered commit-ready.

Security Audit

High Risk

v11 • 7/9/2026 Open versioned report

Most static findings are false positives caused by Markdown backticks and references to local tooling. Two shell command substitution examples are confirmed because they expand git output without null-safe argument handling. A semantic prompt-injection risk remains because repository guidance files are described as the source of truth.

Files scanned

484

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

SKILL.md:93-94 SKILL.md:116

Untrusted Repository Instructions Granted Priority

The skill says local AGENTS.md and CLAUDE.md are the source of truth and tells the agent to read them before acting. Repository-controlled instruction files can contain prompt injection and should not override higher-priority instructions.

The wording grants authority to files that may come from the target repository. This is a clear prompt-injection exposure, although the skill does not include an explicit malicious override phrase.

Capability review items (2)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

SKILL.md:172

Shell command substitution

.bin/ty check $(git diff --cached --name-only --diff-filter=ACMR | grep '\.py$')

The documented command expands git output directly into a shell command. Repository-controlled filenames can be split or interpreted as options, so null-safe argument handling is needed.

Medium

SKILL.md:175

Shell command substitution

.bin/ty check $(git diff --name-only --diff-filter=ACMR | grep '\.py$')

The documented command expands git output directly into a shell command. Repository-controlled filenames can be split or interpreted as options, so null-safe argument handling is needed.

Risk Factors

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/diversioteam-backend-atomic-commit/audits/11?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/diversioteam-backend-atomic-commit/security.svg)](https://skillstore.io/skills/diversioteam-backend-atomic-commit?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/diversioteam-backend-atomic-commit?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/diversioteam-backend-atomic-commit/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/diversioteam-backend-atomic-commit.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

DiversioTeam. (2026). backend-atomic-commit security audit report (audit version 11) [Author version unspecified]. Skillstore. https://skillstore.io/skills/diversioteam-backend-atomic-commit/audits/11

BibTeX citation

@techreport{diversioteam-diversioteam-backend-atomic-commit-2026,
  author = {DiversioTeam},
  title = {backend-atomic-commit security audit report (audit version 11)},
  institution = {Skillstore},
  year = {2026},
  number = {11},
  url = {https://skillstore.io/skills/diversioteam-backend-atomic-commit/audits/11},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "backend-atomic-commit security audit report (audit version 11)"
version: "unspecified"
type: report
authors:
  - name: "DiversioTeam"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/diversioteam-backend-atomic-commit/audits/11"
identifiers:
  - type: other
    value: "skillstore:diversioteam-backend-atomic-commit:audit:11"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Clean a Backend Working Tree

Run formatting, linting, type checks, and safe edits before opening a pull request.

Validate a Focused Commit

Check that staged files represent one logical change and that required gates are green.

Standardize Team Review Prep

Apply consistent backend review expectations across Django projects before handoff.

Try These Prompts

Run Basic Pre-Commit Checks

Use this skill in pre-commit mode. Check my current backend changes, fix safe formatting issues, and summarize any remaining blockers.

Fix Changed Python Files

Run the backend pre-commit workflow on changed Python files. Apply safe Ruff, typing, import, logging, and debug cleanup fixes.

Prepare an Atomic Commit

Use atomic-commit mode for my staged backend changes. Verify atomicity, run available gates, and propose a ticket-prefixed commit message.

Review a Risky Backend Change

Run the strict atomic workflow for these staged Django changes. Pay special attention to migrations, multi-tenant behavior, tests, and security-sensitive logging.

Best Practices

Run the skill from the repository root so local configuration can be detected correctly.
Stage only one logical change before using atomic-commit mode.
Review edits and check results before committing or pushing changes.

Avoid

Using atomic-commit mode on unrelated staged changes.
Skipping failed local checks and treating the commit as ready.
Letting repository guidance override higher-priority safety instructions.

Frequently Asked Questions

Does this skill create commits automatically?

No. It prepares checks and a suggested message, but the user remains responsible for committing.

Which repositories fit this skill best?

It fits Django backend repositories with Ruff, ty, Django checks, pytest, and pre-commit configuration.

Can it work outside a Django project?

It can fall back to lighter Python checks, but many backend-specific checks may not apply.

Does it edit files?

Yes. In pre-commit mode it may apply safe formatting and cleanup edits to changed files.

What happens if local tools are missing?

It should report missing tools and mark affected checks as not run or needing follow-up.

Is this available for Claude, Codex, and Claude Code?

Yes. The skill declares support for Claude, Codex, and Claude Code workflows.

Developer Details

Author

DiversioTeam

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/DiversioTeam/agent-skills-marketplace/tree/main/plugins/backend-atomic-commit/skills/backend-atomic-commit

Ref

3e4b6c31a74a3bd1a291c98cf585d720cb9fbc88

Maintenance freshness

7/18/2026

Usage

7 downloads · 314 views

File structure

📄 SKILL.md