git-conflict-resolver

Resolve git conflicts (rebase, merge, cherry-pick, revert) using mergiraf, deterministic category handling, explicit intent inference, validation, and semantic-conflict auditing. Use when git status shows unmerged paths or an operation is paused with conflicts. Also decomposes an oversized PR or branch into smaller stacked PRs along functional/structural boundaries.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a dense, highly actionable procedural skill with strong validation feedback loops and well-signaled progressive disclosure to real reference files. Its main weakness is conciseness and a couple of navigation gaps (a referenced constitution.md absent from the bundle, and several bundled references not surfaced from the body).

Suggestions

Provide or relocate constitution.md so the referenced '${CLAUDE_SKILL_DIR}/constitution.md' path resolves within the bundle, or inline the three constitutional rules and drop the external reference.

Surface the existing references history-mining.md, intent-inference.md, mergiraf-integration.md, and semantic-conflicts.md from the relevant procedure steps so all bundled material is navigable one level deep.

Tighten the per-file Decision Record and HALT/Summary templates (e.g., consolidate into a single references/records.md) to reduce body length while keeping the core procedure lean.

Dimension	Reasoning	Score
Conciseness	The procedure is lean and assumes Claude's competence with executable commands and minimal prose, but at ~385 lines the body carries dense procedural detail and template blocks that could be trimmed or partly externalized.	4 / 5
Actionability	Every step provides copy-paste-ready executable scripts with concrete flags and JSON output (conflict-status.sh, categorize-conflicts.sh, mergiraf solve, meta-route.sh, validate-and-reprompt.sh), fully covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced six-step procedure with explicit validation checkpoints (validate -> reprompt -> re-invoke, semantic-audit gate), abort-recommendation heuristics, a HALT schema, and a documented feedback loop back to Step 1.	5 / 5
Progressive Disclosure	The body is an overview pointing to one-level-deep, clearly signaled references (design-rationale.md, meta-resolver.md, pr-decomposition.md, recurring-conflicts.md — all real files), but constitution.md is referenced without an existing bundle file and several provided references (history-mining.md, intent-inference.md, mergiraf-integration.md, semantic-conflicts.md) are not surfaced from the body for navigation.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete, third-person, and comprehensively covers capabilities, triggers, and scope boundaries. It cleanly answers both 'what' and 'when' with minimal padding and explicit anti-triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — resolve, validate, semantic-conflict audit, decompose — naming mergiraf and deterministic category handling, with comprehensive coverage of rebase/merge/cherry-pick/revert plus stacked-PR decomposition.	5 / 5
Completeness	Explicitly answers both what ('Resolve git conflicts...using mergiraf...validation, and semantic-conflict auditing') and when ('Use when git status shows unmerged paths or an operation is paused with conflicts').	5 / 5
Trigger Term Quality	Description and when_to_use give comprehensive natural phrases ('unmerged paths', 'rebase paused', 'merge conflict', 'split this PR', 'PR too big to review') that users would actually say, with synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Clear niche (git conflict resolution + PR decomposition) with narrow, distinct triggers and explicit exclusions ('Do not use for...force-push recovery, or general PR review'), minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Raudbjorn/conflict-of-interest
Path: SKILL.md
Commit: 945f5be

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.