merge

Merge the winning agent's branch into base, archive losers, and clean up worktrees. Use when the user runs /hub:merge or asks to land the winning AgentHub result and tidy the session.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

78%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 concise, actionable merge workflow with clear sequencing and a pre-merge validation checkpoint, scoring well on token efficiency and actionability. Its main weaknesses are a missing post-merge verification loop and a referenced script file that is not present in the bundle.

Suggestions

Add a post-merge verification step (e.g., 'git log --oneline -1 {base_branch}' or confirm each archive tag exists) so the destructive batch operation has a validate-after-execution feedback loop.

Either ship scripts/session_manager.py in a scripts/ bundle directory or remove/replace the inline references to it with concrete inline commands, since the referenced path is currently a dead link.

Specify how placeholders like {base_branch} and {session-id} are resolved (e.g., read from a state file or the most recent /hub:eval output) so the commands are copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no explanation of what git merge or git tag is, every section is action-oriented, and the ~88 lines are almost entirely commands and short directives with no padding.	5 / 5
Actionability	It provides concrete, executable git/python commands with real flags (--no-ff, -m, --cleanup, --update) for nearly every step, but placeholders like {base_branch}, {session-id}, and {skill_path} require substitution that is not fully specified, leaving minor gaps.	4 / 5
Workflow Clarity	The six steps are clearly sequenced and the Safety section adds an explicit validation checkpoint ('Confirm with user before merging — show the diff summary first') plus an 'Only proceed' guardrail, but it lacks a verify-after-merge feedback loop (e.g., check the merge succeeded or that tags were created) for a destructive/batch operation.	4 / 5
Progressive Disclosure	Structure is clean with well-labeled sections and a single one-level reference (scripts/session_manager.py), but the referenced file does not exist in any bundle directory, so navigation signals to detailed material are not actually backed by real files.	3 / 5
	Total	16 / 20 Passed

Description

83%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 well-crafted description that explicitly states concrete capabilities and provides a clear 'Use when' trigger tied to a specific command and natural user phrasing. It is third person, concise, and clearly distinguishable from generic skills.

Dimension	Reasoning	Score
Specificity	It names three concrete actions — 'Merge the winning agent's branch into base', 'archive losers', and 'clean up worktrees' — which are specific rather than generic, but the actions are stated as a list without naming the underlying mechanisms (git tags, --no-ff merge), leaving minor coverage gaps.	4 / 5
Completeness	It explicitly answers both 'what' (merge winner, archive losers, clean up worktrees) and 'when' ('Use when the user runs /hub:merge or asks to land the winning AgentHub result and tidy the session') with concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes natural trigger phrases users would actually say — 'when the user runs /hub:merge', 'asks to land the winning AgentHub result' — with good keyword coverage, but it is missing common synonym variations or file/path extensions.	4 / 5
Distinctiveness Conflict Risk	The /hub:merge and AgentHub niche is clearly distinct and tied to a specific command, with only minor overlap risk against general git/merge skills; it is mostly distinct but not perfectly carved out.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: engineering/agenthub/skills/merge/SKILL.md
Commit: 19392f7

Reviewed: ~6 hours 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.