agent-merge-conflict-arbiter

Neutral arbiter for merge conflicts between two agents.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/autonomous-ai-agents/agent-merge-conflict-arbiter/SKILL.md

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 body is highly actionable and excellently sequenced with explicit validation checkpoints and feedback loops, assuming Claude's competence throughout; the only minor gaps are a few trimmable restatements and the absence of any external reference split.

Suggestions

Tighten the intro paragraph and the Pitfalls' self-favoring entry, which restate the structural-bias point already made in How to Run, to nudge conciseness from 4 to 5.

Consider extracting the hunk-class table and resolution rules into a one-level-deep reference file (e.g., references/hunk-classes.md) so SKILL.md reads as a leaner overview and progressive disclosure can reach 5.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence throughout (no git/merge-conflict primers) and every section earns its place, fitting the score-4 anchor "Efficient; minor instances of over-explanation that could be trimmed" — the intro and Pitfalls restate the bias point a second time.	4 / 5
Actionability	It gives copy-paste-ready commands (e.g., `git merge-base <A> <B>`, `git diff <base>..<side> -- <file>`, `kanban_create(title=..., parents=[...])`), named tools (`patch`, `write_file`, `search_files`), and a concrete hunk-class decision table, matching the score-5 anchor "Fully executable; copy-paste ready code or commands; specific examples cover the common cases."	5 / 5
Workflow Clarity	The five-step procedure (Gather → Classify → Resolve → Verify → Hand back) each carry explicit "Done when" checkpoints, plus a Verify step that runs build/tests with a feedback loop, matching the score-5 anchor "Clear sequence with explicit validation steps; feedback loops for error recovery."	5 / 5
Progressive Disclosure	No bundle files exist, so there are no nested references; the single SKILL.md is well organized into clearly signaled sections (When to Use, Prerequisites, Procedure, Pitfalls, Verification), fitting the score-4 anchor "Good structure; most content is appropriately placed" — it falls short of 5 only because the ~145-line body is monolithic rather than a lean overview pointing to one-level-deep references.	4 / 5
	Total	18 / 20 Passed

Description

48%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 distinct and uses a natural trigger term ("merge conflicts"), but it is thin on concrete actions and entirely omits explicit "when to use" guidance, capping completeness at 3.

Suggestions

Add a concrete list of actions the skill performs (e.g., "classifies conflicted hunks, resolves each per both sides' stated intents, runs build/tests, and hands back a per-hunk decision summary") to lift specificity toward 4-5.

Append an explicit trigger clause such as "Use when a parallel multi-agent campaign produces merge conflicts between two agents' branches and neither should self-adjudicate" to satisfy the "what AND when" requirement and raise completeness to 4-5.

Include natural synonyms a user might say ("git merge conflict", "agent branch collision", "reconcile agent branches") to broaden trigger-term coverage from 3 toward 4-5.

Dimension	Reasoning	Score
Specificity	The phrase "Neutral arbiter for merge conflicts between two agents" names a concrete domain but offers only one abstract action ("arbiter"), matching the score-2 anchor "Names the domain but actions are minimal or generic."	2 / 5
Completeness	It states a clear "what" (neutral arbiter for merge conflicts) but provides no "Use when..." trigger guidance, so per the missing-trigger rule completeness is capped at 3 ("Has a clear 'what' but 'when' is missing or only weakly implied").	3 / 5
Trigger Term Quality	"merge conflicts" and "agents" are natural terms a user would say, but the description lacks synonyms or variations, fitting the score-3 anchor "Some relevant keywords but missing common variations or synonyms."	3 / 5
Distinctiveness Conflict Risk	The "between two agents" qualifier carves a clear niche with minimal overlap risk, matching the score-4 anchor "Mostly distinct; minor overlap risk with closely related skills."	4 / 5
	Total	12 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/autonomous-ai-agents/agent-merge-conflict-arbiter/SKILL.md
Commit: 68fa7e9

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.