agent-repo-architect

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

4.94x

Quality

28%

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

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured and offers concrete MCP/GitHub tool usage, but it is padded with a duplicate config block and placeholders, contains corrupted file paths that break executability, and lacks validation checkpoints for its batch operations.

Suggestions

Fix the corrupted paths (replace "$" with "/") and replace bracket placeholders like "[Architecture documentation]" with real content or remove them so examples are executable.

Remove the duplicate second YAML frontmatter/config block (lines 6–44) that restates name, tools, and hooks already in the real frontmatter.

Add explicit validation/verification steps after batch operations such as cross-repo file pushes and branch creation (e.g., confirm pushes succeeded, validate CI workflow syntax before committing).

Dimension	Reasoning	Score
Conciseness	The body includes a redundant duplicate YAML config block, repeated long code sections, and bracket placeholders ("[Architecture documentation]") that add tokens without value, though it is not pure concept-explanation fluff.	2 / 3
Actionability	Concrete MCP tool-call syntax and GitHub operations are provided, but file paths are corrupted with "$" in place of "/" (e.g. ".claude$commands$github$github-modes.md", "actions$checkout@v3") and template contents are placeholders, so examples are not fully executable.	2 / 3
Workflow Clarity	Usage patterns and the batch-operations section give a sequenced TodoWrite checklist, but batch/destructive operations (pushing files to multiple repos, creating branches) lack any validation or verification checkpoints.	2 / 3
Progressive Disclosure	The skill has recognizable sections (Purpose, Capabilities, Usage Patterns, Best Practices) but everything is inlined in one ~350-line document with no bundle files or one-level-deep references to split out detail.	2 / 3
	Total	8 / 12 Passed

Description

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 a generic template that identifies the skill but fails to describe its capabilities or state when it should be used. It reads as boilerplate rather than a meaningful trigger description.

Suggestions

Replace the boilerplate with concrete capabilities, e.g. "Optimizes repository structure, manages multi-repo templates, and coordinates cross-repo workflows with ruv-swarm."

Add an explicit trigger clause: "Use when restructuring repositories, standardizing templates across repos, or coordinating multi-repo architecture."

Drop the "invoke with $agent-repo-architect" meta-instruction in favor of natural user-facing trigger terms like "repository structure", "multi-repo", or "architecture optimization".

Dimension	Reasoning	Score
Specificity	The description only states "Agent skill for repo-architect" — it identifies the skill but names no concrete actions or capabilities, matching the vague/abstract anchor.	1 / 3
Completeness	It conveys neither a concrete "what does this do" nor any "when should Claude use it" guidance — only the skill's identity, so both halves are missing or very weak.	1 / 3
Trigger Term Quality	"invoke with $agent-repo-architect" is an invocation hint, not natural keywords a user would say when needing this skill; no capability trigger terms are present.	1 / 3
Distinctiveness Conflict Risk	"repo-architect" points at a specific domain, but the generic "Agent skill for X" template could overlap with many agent skills; no distinct triggers lift it to 3.	2 / 3
	Total	5 / 12 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: 26c35b5

Reviewed: about 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.