More screenshots
Works with the AI Agents you already use
Merge Conflict Rescue
Resolve merge conflicts in a safe order: protect behaviour, resolve mechanically first, then by hand.
$5
Merge Conflict Rescue
Example session with this skill installed
Apply the skill to a small test input and produce its core output. The script finds conflict markers only; a marker-free merge can still be behaviourally broken, which is why the silent-conflict sweep is mandatory.
- Read your context and instructions
- Compiled the merge conflict rescue
A feature branch lived for three weeks and came back with 47 conflicted files, and the team had been avoiding it for a further week. The rescue started with a backup branch and a freeze, then an inventory that classified 31 conflicts as formatting and import order, 11 as same-line edits, and 5 as semantic. The formatter cleared the 31 in an hour. Reading both sides of the 11 same-line edits revealed two cases where accepting one side would have reverted a bug fix, which a wholesale accept would have missed. The 5 semantic conflicts went to behaviour owners, with decisions recorded. The full test suite then caught one silent conflict, duplicated validation logic, that the diff had not shown. The merge landed the next day, and the cause note, a three-week branch with no intermediate merges, led to a weekly merge rule that prevented a repeat.
Script demo (verified): running python3 scripts/conflict_scan.py on a test file with one conflict printed 1 conflict block, one each of the three main markers, and has_conflicts true.
This is a worked example produced by applying the skill, not a claim about a live customer outcome.
Connects securely to your tools. The creator never sees your data.
About this skill
A rescue workflow for messy merges: stop the bleeding, classify conflicts by type, resolve mechanical conflicts first, handle semantic conflicts with tests, and verify the result before anyone else builds on it. The skill provides a step-by-step protocol with decision points, a decision table, a fill-in template, a checklist, and a scoring rubric, plus a runnable script (conflict_scan.py) that scans files for conflict markers and reports counts by file and marker type. It focuses on finding the bottleneck first and fixing in an order backed by evidence, rather than applying generic advice.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
It cannot resolve semantic conflicts automatically; where two changes mean different things, a human must decide. It assumes a backup of the pre-merge state exists or can be made.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 23 days ago