CtrlK
BlogDocsLog inGet started
Tessl Logo

fix-merge-conflicts

Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution

57

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./cursor-team-kit/skills/fix-merge-conflicts/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 lean, well-structured, and clearly sequenced for a simple skill, but it lacks specific executable commands and an explicit validation feedback loop for what is effectively a batch operation across multiple conflicting files.

Suggestions

Add an explicit validation feedback loop after step 5 (e.g., 'If compile/lint/tests fail, fix the resolution and re-run until green before staging').

Provide concrete commands for key steps, such as the exact lockfile regeneration command per package manager and how to detect conflicts via `git status` / `grep -rn '<<<<<<<'`.

DimensionReasoningScore

Conciseness

The body is lean and efficient with no padding or explanation of concepts Claude already knows; every section (Trigger, Workflow, Guardrails, Output) earns its place, matching the 'lean and efficient' anchor.

5 / 5

Actionability

Steps are concrete actions ('Detect all conflicting files from git status', 'Regenerate lockfiles with package manager tools') but lack specific executable commands, fitting the 'some concrete guidance but incomplete' anchor rather than the copy-paste-ready 4.

3 / 5

Workflow Clarity

A clear 6-step sequence is present with a validation step ('Run compile, lint, and relevant tests'), but there is no explicit validate→fix→retry feedback loop; since conflict resolution is a batch operation touching multiple files, the missing feedback loop caps this at 3.

3 / 5

Progressive Disclosure

At under 50 lines with no need for external references, the well-organized sections (Trigger, Workflow, Guardrails, Output) satisfy the simple-skill exception that allows a 5 with just well-organized structure.

5 / 5

Total

16

/

20

Passed

Description

58%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 concise and names a clear, distinct niche with several concrete actions, but it omits an explicit 'Use when...' trigger clause and lacks keyword variations, capping completeness and trigger term quality at 3.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when a branch has unresolved merge conflicts or git status shows conflict markers').

Include natural keyword variations users might say, such as 'git conflicts', 'conflict markers', or 'rebase conflicts', alongside 'merge conflicts'.

DimensionReasoningScore

Specificity

Lists several specific actions — 'Resolve merge conflicts non-interactively', 'validate build and tests', and 'finalize conflict resolution' — with only minor coverage gaps, fitting the 'several specific actions' anchor better than the 1-2 action anchor at 3.

4 / 5

Completeness

The 'what' is clear (resolve, validate, finalize), but there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

'merge conflicts' is a relevant keyword a user would naturally say, but common variations and synonyms like 'git conflicts', 'conflict markers', or 'rebase conflicts' are missing, so it sits at the 'some relevant keywords' anchor rather than the 4.

3 / 5

Distinctiveness Conflict Risk

Non-interactive merge conflict resolution is a clear niche with minimal conflict risk; it could only overlap with closely related git skills, fitting the 'mostly distinct' anchor rather than the broad 3.

4 / 5

Total

14

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cursor/plugins
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.