git-conflict-resolve

Quick Summary

Goal: Resolve git merge/cherry-pick/rebase conflicts with backup, analysis, and structured reporting.

Workflow:

1. Backup — Create safety backup of current state
2. Analyze — Identify conflict types and affected files
3. Resolve — Apply resolution strategy per conflict
4. Report — Generate conflict resolution report

Key Rules:

• Always create backup before resolving conflicts
• Prefer preserving both sides' intent over arbitrary choice
• Generate resolution report for audit trail

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Purpose

Systematically resolve git conflicts (merge, cherry-pick, rebase) with:

1. Backup of all conflicted files before resolution
2. Per-file conflict analysis with root cause explanation
3. Resolution with documented rationale
4. Comprehensive report generation

Variables

OPERATION: auto-detect (cherry-pick, merge, rebase) from git state REPORTPATH: plans/reports/conflict-resolution-{date}-{operation}-{source}.md BACKUPPATH: .ai/workspace/conflict-backups-{date}/

Workflow

Step 1: Detect conflict state

# Detect operation type
git status  # Check for "cherry-pick in progress", "merge in progress", etc.

# List all conflicted files
git diff --name-only --diff-filter=U  # Unmerged files (both modified)
git status --short | grep "^DU\|^UD\|^UU\|^AA\|^DD"  # All conflict types

Classify each conflict:

• DU (Deleted by us): File exists on source but not on target branch
• UD (Deleted by them): File exists on target but deleted by source
• UU (Both modified): Both branches modified the same file
• AA (Both added): Both branches added a file at the same path
• DD (Both deleted): Both branches deleted the file

Step 2: Create backup files

MANDATORY before any resolution.

mkdir -p {BACKUP_PATH}

# For each conflicted file, copy WITH conflict markers preserved
cp <conflicted-file> {BACKUP_PATH}/<filename>.conflict

Create a TaskCreate item for each conflicted file PLUS report and review tasks.

Step 3: Analyze each conflict (per file)

For each conflicted file, perform this analysis:

3a. Understand the conflict type

• DU/UD (deleted by one side): Check if the file was introduced in a commit not present on the target branch. Read the file content from the source commit to understand what it provides.
• UU (both modified): Read the conflict markers. Identify what each side changed and why.

3b. Read both versions

# For UU conflicts: read the file with conflict markers
# Look for <<<<<<< HEAD / ======= / >>>>>>> markers

# For DU conflicts: get the source version
git show <source-commit>:<file-path>

# Optionally extract clean versions
git show HEAD:<file-path> > {BACKUP_PATH}/<filename>.ours
git show <source-commit>:<file-path> > {BACKUP_PATH}/<filename>.theirs

3c. Analyze dependencies

• Check callers: Do other files reference methods/classes in this file? Are caller names compatible?
• Check constructor/DI: Does the resolution require new dependencies?
• Check cross-file consistency: Will the resolution break other files?

3d. Determine resolution strategy

Step 4: Resolve each conflict

Apply the determined strategy:

# Accept theirs (source version)
git checkout --theirs <file> && git add <file>

# Keep ours (target version)
git checkout --ours <file> && git add <file>

# Manual merge: Edit the file to remove conflict markers, then:
git add <file>

For manual merges:

1. Remove <<<<<<< HEAD, =======, >>>>>>> <commit> markers
2. Keep the correct content from each side
3. Verify no leftover conflict markers: git diff --check

Step 5: Verify resolution

# Check no unmerged files remain
git diff --name-only --diff-filter=U

# Check no leftover conflict markers
git diff --check

# Review overall status
git status

Step 6: Complete the operation

# For cherry-pick
git cherry-pick --continue --no-edit

# For merge
git commit  # (merge commit is auto-prepared)

# For rebase
git rebase --continue

Step 7: Generate report

Create a comprehensive report at {REPORT_PATH} with:

1. Header: Date, source commit/branch, target branch, result commit
2. Summary: Total conflicts, categories, overall risk
3. Per-file details:

- File path - Conflict type (DU/UU/etc.) - Root cause (why the conflict occurred) - Resolution chosen (accept theirs/keep ours/manual merge) - Rationale (why this resolution was chosen) - Risk level (Low/Medium/High)

1. Summary table: All files with conflict type, resolution, risk
2. Root cause analysis: Common patterns across conflicts
3. Recommendations: Follow-up actions, build verification, etc.

Step 8: Final review

• Verify report is complete and accurate
• Check that all backup files exist
• Confirm build passes (if applicable)
• Flag any Medium/High risk resolutions for user attention

Resolution Decision Framework

When to "Accept Theirs" (source version)

• File is NEW (DU) and required by the feature being cherry-picked/merged
• File contains schema/config additions needed by new entities
• Source has strictly more content (e.g., empty class → populated class)

When to "Keep Ours" (target version)

• Source modifies methods that don't exist on target (added by uncommitted prerequisite)
• Source renames methods/types that target callers still reference by old names
• Changes are not required for the feature being brought in

When to "Manual Merge"

• Both sides have legitimate changes that need to coexist
• Schema files where both add new entries (keep both)
• Config files where both add new sections

Risk Assessment

Notes

• Always create backup files BEFORE any resolution
• Understand the root cause first, then resolve — never force-resolve blind. — why: a guessed resolution silently drops or duplicates legitimate changes
• For complex conflicts (>3 conflict regions in one file), extract both clean versions for side-by-side analysis
• Check for prerequisite commits: if a cherry-pick modifies files from prior commits not on target, note this in the report
• Use git diff <commit>^..<commit> -- <file> to see the actual diff of a specific commit (not the full file state)

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

Prerequisites: MUST ATTENTION READ before executing:

<!-- SYNC:ai-mistake-prevention -->

AI Mistake Prevention — Failure modes to avoid on every task:

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting.
Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing.
Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first.
Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done.
Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect.
Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard.
Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk.
Assert the outcome your system owns, not the intermediate state your infrastructure owns. When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure.
Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

<!-- /SYNC:ai-mistake-prevention -->

<!-- SYNC:critical-thinking-mindset -->

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.
Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

<!-- /SYNC:critical-thinking-mindset -->

<!-- SYNC:understand-code-first -->

Understand Code First — HARD-GATE: Do NOT write, plan, or fix until you READ existing code.

1. Search 3+ similar patterns (grep/glob) — cite file:line evidence
2. Read existing files in target area — understand structure, base classes, conventions
3. Run python .claude/scripts/code_graph trace <file> --direction both --json when .code-graph/graph.db exists
4. Map dependencies via connections or callers_of — know what depends on your target
5. Write investigation to .ai/workspace/analysis/ for non-trivial tasks (3+ files)
6. Re-read analysis file before implementing — never work from memory alone. — why: long context drifts from the file; the file is ground truth
7. NEVER invent new patterns when existing ones work — match exactly or document deviation. — why: divergent patterns fragment the codebase and slow every future reader

BLOCKED until: - [ ] Read target files - [ ] Grep 3+ patterns - [ ] Graph trace (if graph.db exists) - [ ] Assumptions verified with evidence

<!-- /SYNC:understand-code-first -->

<!-- SYNC:understand-code-first:reminder -->

• MANDATORY IMPORTANT MUST ATTENTION search 3+ existing patterns and read code BEFORE any modification. Run graph trace when graph.db exists.

<!-- /SYNC:understand-code-first:reminder -->

<!-- SYNC:evidence-based-reasoning:reminder -->

• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim. Confidence >80% to act, <60% = do NOT recommend.

<!-- /SYNC:evidence-based-reasoning:reminder -->

<!-- SYNC:critical-thinking-mindset:reminder -->

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

<!-- /SYNC:critical-thinking-mindset:reminder -->

<!-- SYNC:ai-mistake-prevention:reminder -->

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

<!-- /SYNC:ai-mistake-prevention:reminder -->

<!-- SYNC:project-protocol-overlay -->

Project Protocol Overlay — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the Target column of the project's skill-protocol index (docs/project-reference/skill-protocols-reference.md by default; a referenceDocs entry in docs/project-config.json overrides the path), taking the most specific matching tier ONLY — exact name > glob > *. That precedence orders overlays against EACH OTHER, never against this skill. Read ONLY the matched bodies, resolved as <protocols-dir>/<Name>.md; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: .claude/skills/project-skill-protocol/references/registry.md.

Overlays are ADDITIVE ONLY: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently.

<!-- /SYNC:project-protocol-overlay -->

<!-- SYNC:project-protocol-overlay:reminder -->

MUST ATTENTION resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > *, which ranks overlays against each other, NEVER against this skill), read only matched bodies at <protocols-dir>/<Name>.md; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user.

<!-- /SYNC:project-protocol-overlay:reminder -->

Closing Reminders

IMPORTANT MUST ATTENTION Goal: Resolve git merge/cherry-pick/rebase conflicts with backup, analysis, and structured reporting.

Protocols in force (concise digest of the SYNC/shared blocks this skill carries):

• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
• Critical Thinking: critical + sequential thinking, traced proof, confidence >80% to act.
• Understand Code First: search 3+ patterns and read code before any modification.

• MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
• MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
• MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.