Name: agent-repo-architect
Rating: 54.8 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-repo-architect

Agent skill for repo-architect - invoke with $agent-repo-architect

4.94x

Quality

31%

Does it follow best practices?

Impact

94%

4.94x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-repo-architect/SKILL.md

The canonical home for this skill is agent-repo-architect in ruvnet/claude-flow

Quality

Content

35%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 provides a broad tour of repository-architecture capabilities with MCP call examples, but suffers from placeholder content, broken path syntax, and generic padding. Batch/destructive operations lack validation checkpoints, and nothing is split into reference files.

Suggestions

Replace placeholder strings ('[Architecture documentation]') and fix path separators ('$' → '/') so the code blocks are copy-paste executable.

Add validation feedback loops to batch operations — e.g. after push_files, verify the commit landed and re-run on failure before proceeding.

Trim the generic 'Best Practices' and 'Monitoring' bullets that restate what Claude already knows, or move detailed architecture patterns into a referenced ARCHITECTURE.md to shorten SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~400-line body is noticeably verbose, padding with generic best-practice bullets Claude already knows ('Consistent directory organization', 'Clear separation of concerns') and placeholder-laden code, matching 'noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	Code examples use non-executable placeholders ('[GitHub modes template]', '[Architecture documentation]') and broken path syntax with '$' instead of '/' (e.g. '.claude$commands$github$github-modes.md'), giving high-level MCP calls but missing the specifics to actually execute, fitting 'minimal concrete guidance; missing the specific steps'.	2 / 5
Workflow Clarity	Steps are roughly sequenced (init swarm, analyze, search, orchestrate, push, track via TodoWrite), but the batch/destructive cross-repo operations lack any validation checkpoints or error-recovery feedback loops, so per the rubric cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	The skill is a single monolithic file with no bundle files (references/scripts/assets absent) and no one-level-deep references; sections are headed but content that could live in separate files (architecture patterns, best practices) is inlined, fitting 'some structure but could be better organized'.	3 / 5
	Total	10 / 20 Passed

Description

28%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 frontmatter description is circular and meta — it describes how to invoke the skill rather than what it does or when to use it. It lacks concrete capabilities and any 'Use when...' trigger guidance, capping completeness low.

Suggestions

Replace the description with concrete actions, e.g. 'Analyzes repository structure, creates standardized project templates, and synchronizes files across multiple repos.'

Add an explicit trigger clause such as 'Use when optimizing repo layout, setting up multi-repo templates, or coordinating cross-repository structure changes.'

Drop the 'invoke with $agent-repo-architect' meta instruction from the description; invocation is handled elsewhere, not in the capability summary.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for repo-architect - invoke with $agent-repo-architect' names the domain (repo-architect) but lists no concrete actions, only how to invoke it, matching the 'names domain but actions are minimal or generic' anchor.	2 / 5
Completeness	It offers only a vague 'what' (an agent skill for repo-architect) and no 'when' guidance — the 'invoke with' clause is an invocation instruction, not a use-case trigger, matching 'has a vague what and no when'.	2 / 5
Trigger Term Quality	It contains only the manufactured skill name 'repo-architect' and the invocation token; no natural phrases a user would actually say when needing repository-architecture help, fitting 'one or two generic keywords; missing the natural phrases users say'.	2 / 5
Distinctiveness Conflict Risk	The name 'repo-architect' gives it a somewhat specific niche, but the description itself is generic enough that it could overlap with other repo/structure skills, fitting 'somewhat specific but could still overlap'.	3 / 5
	Total	9 / 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: ruvnet/ruflo
Path: .agents/skills/agent-repo-architect/SKILL.md
Commit: fa13ee4

Reviewed: about 8 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.