conflicts
Resolve git merge conflicts by analyzing change intent across branches. Use when the user asks to resolve merge conflicts, sync a branch, merge branches, or when a git merge produces conflicts.
64
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/conflicts/skills/conflicts/SKILL.mdQuality
Discovery
89%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 solid skill description with an explicit 'Use when...' clause covering multiple natural trigger scenarios and a clear niche around git merge conflicts. The main weakness is that the 'what' portion could be more specific about the concrete actions performed beyond 'analyzing change intent' — listing specific resolution strategies would strengthen it.
Suggestions
Add more specific concrete actions to the capability portion, e.g., 'analyze conflicting hunks, choose resolution strategies, edit conflict markers, and stage resolved files'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (git merge conflicts) and one action (resolve/analyzing change intent), but doesn't list multiple concrete actions like 'accept theirs/ours, edit conflict markers, stage resolved files'. | 2 / 3 |
Completeness | Clearly answers both 'what' (resolve git merge conflicts by analyzing change intent across branches) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'resolve merge conflicts', 'sync a branch', 'merge branches', 'git merge produces conflicts' — these cover the common ways users would phrase such requests. | 3 / 3 |
Distinctiveness Conflict Risk | The description is narrowly scoped to git merge conflicts specifically, with distinct triggers like 'merge conflicts', 'sync a branch', and 'merge branches' that are unlikely to overlap with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with a clear multi-step workflow and thoughtful conflict resolution decision framework. Its main weaknesses are moderate verbosity (explaining concepts Claude already knows, like change categorization) and limited actionability—it describes what to do conceptually but lacks complete executable command sequences for actually manipulating conflict markers in files. The output format templates and safety constraints are strong additions.
Suggestions
Remove the 'Role' section entirely and trim change categorization explanations—Claude already understands these concepts. Focus tokens on the decision framework and constraints.
Add concrete, executable examples showing how to actually resolve a conflict marker in a file (e.g., using sed, file editing, or showing the exact sequence of read-file → edit → stage commands).
Consider extracting the output format templates and the detailed decision framework criteria into a referenced CONFLICT_RESOLUTION_GUIDE.md to keep the main skill leaner.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity. The 'Role' section is redundant (Claude doesn't need to be told it's an agent), and some categorizations (e.g., explaining what 'intentional modifications' vs 'incidental changes' are) over-explain concepts Claude already understands. The decision framework criteria could be tighter. | 2 / 3 |
Actionability | The workflow provides a clear sequence of steps with some concrete commands (git fetch, git merge), but most guidance is descriptive rather than executable. There are no complete code/command sequences showing exact git commands for the full workflow, and the conflict resolution logic is conceptual rather than providing specific tool-use patterns (e.g., how to actually edit conflict markers in files). | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced (Steps 1-5) with explicit decision points, validation checkpoints (analyze before merging, review before committing), and an abort escape hatch (git merge --abort). The conflict resolution decision framework provides clear criteria for each path, and the constraint about staging and prompting for review before committing serves as a final validation step. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and headers, but it's a fairly long monolithic document with no references to supporting files. The output format templates and the detailed decision framework could potentially be split into referenced files. However, given no bundle files exist, the inline approach is acceptable but not optimal. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- mattermost/mattermost-ai-marketplace
- Commit
349d5ed
- Reviewed
Table of Contents
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.