Standard workflow for pulling updates from main or other branches on multi-contributor projects (including Flows apps) without silently discarding work. Guides fetching/merging, requires listing merge conflicts explicitly, analyzing ours vs theirs using conversation history and repo context, presenting prioritized recommendations, and obtaining user answers before editing conflict markers or completing the merge. Triggers: pull main, merge main, merge origin, rebase, merge conflict, unmerged paths, both modified, integrate branch, sync with main, git merge abort, resolve conflicts, UU status, theirs vs ours, feat branch update.
73
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines a specific workflow for git merge conflict resolution. It excels in listing concrete actions (fetching, analyzing conflicts, presenting recommendations, requiring user approval), provides extensive natural trigger terms, and carves out a distinct niche. The description is comprehensive without being padded, and uses appropriate third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: fetching/merging, listing merge conflicts explicitly, analyzing ours vs theirs, presenting prioritized recommendations, obtaining user answers before editing conflict markers or completing the merge. Very detailed workflow steps. | 3 / 3 |
Completeness | Clearly answers both 'what' (workflow for pulling updates, guiding fetch/merge, analyzing conflicts, presenting recommendations) and 'when' (explicit triggers list covering many natural user phrases). The triggers section serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'pull main', 'merge main', 'merge conflict', 'rebase', 'resolve conflicts', 'unmerged paths', 'both modified', 'sync with main', 'git merge abort', 'UU status', 'theirs vs ours'. These cover both casual and technical variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on git merge conflict resolution workflows with explicit mention of conflict markers, ours vs theirs analysis, and multi-contributor projects. Unlikely to conflict with general git or coding skills due to the very specific merge conflict focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides clear, actionable guidance for a complex multi-step process. The workflow is well-sequenced with explicit validation checkpoints and user confirmation gates, which is critical for a potentially destructive operation like merge conflict resolution. Minor verbosity in the Goals and Anti-patterns sections prevents a perfect conciseness score, but overall the content earns its token budget.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic Git concepts, but some sections are slightly verbose — e.g., the Goals section and Anti-patterns section restate things already implied by the workflow. The priority classification scheme (P0–P3) is useful but could be more compact. | 2 / 3 |
Actionability | Provides concrete Git commands (git fetch, git merge origin/main, git show :2:path, git checkout --conflict=merge), specific classification frameworks (orthogonal/overlapping/corruption risk), a clear priority scheme, and explicit user interaction patterns. The guidance is specific enough to follow without ambiguity. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit validation checkpoints: pause at conflicts (step 2), analyze before editing (step 3), require user confirmation before resolving (step 4), and verify no conflict markers remain after resolution. The feedback loop (present recommendations → get user approval → apply → verify) is well-defined, and the abort path is covered. | 3 / 3 |
Progressive Disclosure | The skill is well-structured with clear sections (Goals, Hard rules, Workflow steps, Anti-patterns, Quick reference) and references a separate reference.md for optional command snippets and templates. Content is appropriately split — the main file covers the workflow and decision framework while deferring supplementary material. Note: reference.md is not provided in the bundle, but the reference is one-level deep and clearly signaled. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
d6af887
Table of Contents
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.