resolve-conflicts

Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

73%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.

A well-structured, highly actionable workflow: steps are clearly sequenced with validation and feedback loops, and detailed patterns are correctly pushed to references/patterns.md. The main costs are redundancy — the inlined plan template, the Quick Reference Card, and the closing Remember block restate content available elsewhere — plus hardcoded script paths that may not resolve in the installed bundle.

Suggestions

Replace the fully inlined 45-line plan template with a short outline plus a pointer to references/sample-plan.md, which already contains the complete example.

Use bundle-relative script paths (e.g. scripts/handle-deleted-modified.sh) instead of hardcoded ".forge/skills/resolve-conflicts/scripts/..." so the commands work wherever the skill is installed.

Cut the Quick Reference Card table and the closing "Remember" block, both of which restate the Resolution Patterns section and Core Principles verbatim.

Dimension	Reasoning	Score
Conciseness	The body is operationally dense with no explanation of concepts Claude already knows, but contains padded redundancy: the 45-line inlined plan template duplicates references/sample-plan.md, the Quick Reference Card table restates the Resolution Patterns section, and the closing "Remember" block repeats Core Principles. It fits 'mostly efficient but could be tightened' rather than anchor 2, since every section still carries actionable commands rather than filler explanation.	3 / 5
Actionability	Guidance is mostly copy-paste ready (git checkout --ours/--theirs, per-lockfile regeneration commands, validate-conflicts.sh, a fully worked user-interaction example), but script paths are hardcoded to ".forge/skills/resolve-conflicts/scripts/..." rather than bundle-relative paths, and "protoc ..." is a placeholder — minor gaps keeping it below fully executable.	4 / 5
Workflow Clarity	A clear 7-step sequence with explicit validation checkpoints (validate-conflicts.sh marker scan, compile, test suite), a feedback loop for error recovery ("If tests fail... Re-run tests until all pass"), and a checkbox plan/checklist — matching the top anchor including for the destructive/batch operations involved.	5 / 5
Progressive Disclosure	References are real, one level deep, and clearly signaled with named sections ("Read references/patterns.md section 'Import Conflicts'"), and the two scripts exist in the bundle. Not a 5 because the full plan template is inlined in SKILL.md while duplicating references/sample-plan.md, so content that should live only in the reference file is inline.	4 / 5
	Total	16 / 20 Passed

Description

87%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.

A strong description: it explicitly states when to invoke the skill with a natural trigger phrase and enumerates concrete capabilities in third person. Its only weaknesses are mild padding ("Do not attempt to resolve conflicts directly - invoke this skill first" restates the opening instruction) and incomplete coverage of the conflict types the body actually handles.

Suggestions

Trim the redundant second sentence ("Do not attempt to resolve conflicts directly - invoke this skill first") since the opening already mandates immediate invocation.

Add missing capability keywords users would mention, e.g. code-logic and struct/type conflicts, and natural trigger variants like "rebase" or "git conflict".

Dimension	Reasoning	Score
Specificity	"merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis" lists several concrete actions, but omits categories the body covers (code logic, struct/type conflicts, binary files), matching the 'minor gaps in coverage' anchor rather than comprehensive coverage.	4 / 5
Completeness	The when is explicit and concrete ("Use this skill immediately when the user mentions merge conflicts that need to be resolved") and the what is enumerated with specific capability categories, clearly answering both questions with concrete trigger phrases.	5 / 5
Trigger Term Quality	"merge conflicts that need to be resolved" is exactly the natural phrase a user would say, supported by "imports", "lock files", and "configuration files"; however common variations like "rebase", "cherry-pick", or "git conflict" are missing, so a few natural terms are absent.	4 / 5
Distinctiveness Conflict Risk	"merge conflicts" plus "lock files (regeneration)" and "deleted-but-modified files" define a clear niche with distinct triggers that no generic git or file skill would claim, so conflict risk is minimal.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tailcallhq/forgecode
Path: .forge/skills/resolve-conflicts/SKILL.md
Commit: 8eb3e24

Reviewed: 3 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.