Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Dxcommit

ASecurity

Stage, commit, and push a coherent checkpoint whenever work reaches a useful history boundary.

5 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsbashgit

Works with

claude code

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add mitchellfyi/dex --skill dxcommit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dxcommit?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Dxcommit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mitchellfyi-dxcommit/badge)](https://www.skillsdirectory.com/skills/mitchellfyi-dxcommit)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: "dxcommit"
description: "Stage, commit, and push a coherent checkpoint whenever work reaches a useful history boundary."
---

# Skill: dxcommit

Stage, commit, and push coherent checkpoints following the repo's commit
discipline.

## When to Use

- Throughout implementation, review, and verification whenever the current
  changes form a small, coherent checkpoint
- After a focused check, even when broader or final verification is still
  pending or currently failing
- When a local commit exists but has not reached the remote branch

## Steps

### 1. Understand the Changes

```bash
git status
git diff --stat
```

Review what has changed and identify logical groupings for atomic commits. If
the working tree is clean, check whether the current branch has an unpushed
branch-specific commit from an earlier failed push. Continue to the push check
when it does. Otherwise stop: do not publish a newly created branch merely to
establish upstream tracking, and do not create an empty commit.

Do not run or wait for the full verification pipeline merely to make the
changes committable. Run a useful focused check when practical, preserve its
actual result in the status report, and commit the coherent checkpoint whether
that check passed, failed, or remains pending. Final verification gates PR
handoff, not the existence of working-history commits.

### 2. Stage, Commit, and Push Each Group

Read the commit format guide from the Dex prompts directory (`prompts/commit-format.md`) for the full format specification.

For each logical group, finish all four steps before starting the next group:

1. **Stage specific files** — never use `git add -A` or `git add .`:
   ```bash
   git add path/to/file1 path/to/file2
   ```

2. **Check for forbidden and sensitive files** — verify none are staged:
   ```bash
   git diff --cached --name-only
   ```

3. **Write a conventional commit message** following the format in `prompts/commit-format.md`. Include the Dex `Co-Authored-By` trailer and no Claude attribution:
   ```
   Co-Authored-By: Dex <noreply@dexcode.ai>
   ```
   Do not include `Generated with Claude Code`, `Co-Authored-By: Claude ...`, or any similar Claude Code footer.

4. **Push immediately.** The first real commit on a new local branch establishes
   its upstream; every later commit pushes to that upstream before another
   commit is created:

   ```bash
   current_branch=$(git branch --show-current)
   upstream=$(git rev-parse --abbrev-ref --symbolic-full-name @{u} 2>/dev/null || true)
   if [[ -z "$upstream" || "$upstream" != "origin/${current_branch}" ]]; then
     git push -u origin HEAD
   else
     git push
   fi
   ```

   Verify the push succeeded before staging the next logical group. If it fails
   because the remote diverged, investigate; do not force-push without user
   approval.

### 3. Final Sync Check

Confirm the working tree is clean, the current branch contains at least one
branch-specific commit, and local HEAD matches `origin/<current-branch>`. A
newly created branch with no branch-specific commits stays local.

Do not confuse this sync check with final verification. It proves that the
checkpoint was recorded and pushed, not that the branch is ready for a PR.

Attribution

mitchellfyimitchellfyi
View sourceMore from mitchellfyi →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →