skills/merge-conflict-resolver/SKILL.md
Resolve git merge, rebase, and cherry-pick conflicts interactively. Use this skill whenever the user mentions merge conflicts, conflict markers, failed merges, rebase conflicts, or asks to resolve conflicts in their repository. Also trigger when the user says things like "fix my merge", "I have conflicts", "help me rebase", or "resolve the conflicts". Even if they don't say "merge conflict" explicitly, if context suggests they're dealing with conflicting changes in git, use this skill.
npx skillsauth add moliboy5000/.claude merge-conflict-resolverInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Resolve git merge conflicts by analyzing both sides, recommending a resolution, and letting the user make the final call.
The user has one or more files with unresolved git conflicts — whether from git merge, git rebase, git cherry-pick, or git stash pop. They want help understanding what happened and choosing the right resolution.
Run these commands to build context:
git status
This tells you which files are in conflict (look for "both modified", "both added", "deleted by us/them", etc.) and what operation is in progress (merge, rebase, cherry-pick).
If it's a merge:
git log --oneline --graph -10
If it's a rebase or cherry-pick, also check:
git rebase --show-current-patch 2>/dev/null || true
Summarize the situation to the user briefly: what operation caused the conflicts, how many files are affected, and which branches/commits are involved.
For each conflicted file, read it and locate the conflict markers:
<<<<<<< HEAD (or <<<<<<< ours) — the current branch's version======= — separator>>>>>>> branch-name (or >>>>>>> theirs) — the incoming branch's versionFor each conflict hunk, understand what both sides are doing. Use git history for additional context when the intent isn't obvious:
git log --oneline -5 -- <file>
git log --oneline -5 MERGE_HEAD -- <file> 2>/dev/null || true
This helps you understand why each side made its changes, which is critical for a good recommendation.
For each conflict hunk, present the user with:
Your recommendation should be one of:
Always show the exact code you're proposing as the resolution so the user can evaluate it.
Present conflicts one file at a time. If there are many files, group trivial conflicts (e.g., import ordering, whitespace) separately from substantive ones.
Only after the user approves (or modifies) your recommendation for each conflict:
grep -n "^<<<<<<< \|^=======$\|^>>>>>>> " <file>
git add <file>
Repeat for each conflicted file.
After all files are resolved and staged, tell the user what to do next based on the operation:
git commit (git will use the default merge commit message) or I can do it for you."git rebase --continue to proceed, or I can do it for you." (Note: there may be more conflicts in subsequent rebase steps.)git cherry-pick --continue to finish, or I can do it for you."Do not automatically commit or continue — let the user decide.
<<<<<<<. Real conflict markers start at column 0 and follow the exact pattern.tools
MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. NEVER call `generate_diagram` directly without loading this skill first. Trigger whenever the user asks to create, generate, draw, render, sketch, or build a diagram — flowchart, architecture diagram, sequence diagram, ERD or entity-relationship diagram, state diagram or state machine, gantt chart, or timeline. Also trigger when the user mentions Mermaid syntax or wants a system architecture, decision tree, dependency graph, API call flow, auth handshake, schema, or pipeline visualized in FigJam. Routes to type-specific guidance, sets universal Mermaid constraints, and tells you when to use a different diagram type or skip the tool entirely (mindmaps, pie charts, class diagrams, etc.).
development
DEFAULT PIPELINE for all tasks requiring execution. You (Claude) are the strategic orchestrator. Codex agents are your implementation army - hyper-focused coding specialists. Trigger on ANY task involving code, file modifications, codebase research, multi-step work, or implementation. This is NOT optional - Codex agents are the default for all execution work. Only skip if the user explicitly asks you to do something yourself.
development
This skill should be used when the user asks to analyze a UI screen recording and map interaction states into Figma. Trigger for requests such as "put video frames in Figma", "extract states from my recording", "map interactions from video to Figma", "analyze this screen recording", "create a storyboard from my video", "deconstruct this interaction in Figma", "annotate the UI states in my recording", or "pull the key moments from this video into Figma". Also trigger when the user references a video file (.mp4, .mov, .webm, .avi) together with Figma, design review, interaction analysis, prototypes, or UI states. The skill extracts key visual moments from a video, infers interaction triggers, and builds an annotated Figma Design storyboard using native Figma annotations and uploaded screenshot assets.
development
Generate a FigJam project plan board from a PRD plus codebase context. Interactive flow: research → propose sections → per-section deep research → per-section content + block-shape proposal → create FigJam → skeleton → fill → diagrams → wrap. Each content block (section, nested section, intro callout, table, multi-column text, sticky column, diagram section, metadata strip) has its own subskill reference file. Use when the user asks for 'project plan in FigJam', 'interactive project plan', '/generate-project-plan', or provides a PRD and wants per-section confirmation on content + rendering.