team-rules

Apply the team's shared coding rules before writing, modifying, or reviewing code. Trigger when the user asks to add a feature, refactor, fix a bug, write tests, or review a change. Reads rules live from the team-rules MCP workspace at /rules/*.md.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

100%

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

The body is tight, concrete, and well-structured: it names the exact tool and arguments, gives a clear pre-edit workflow, and includes a quick-reference table, all without padding. It appropriately assumes Claude's intelligence while adding only what Claude wouldn't already know. No changes needed.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no concept-explanation padding; every section (before-editing steps, rules of engagement, quick reference) earns its place and assumes Claude's competence.	3 / 3
Actionability	Provides concrete, copy-ready guidance: the exact MCP tool name 'mcp__team-rules__file_list' with specific args 'path: /rules' and 'depth: 2', plus explicit rule file paths per situation.	3 / 3
Workflow Clarity	A clear 4-step pre-edit sequence with a quick-reference mapping table; for a simple read-only rule-reading task no destructive/batch validation checkpoint is needed, so the unambiguous single-purpose workflow scores 3.	3 / 3
Progressive Disclosure	Well-organized into clear sections with a quick-reference table; under 50 lines with no need for external bundle references, satisfying the simple-skill criterion for full marks.	3 / 3
	Total	12 / 12 Passed

Description

100%

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 exemplary: third-person voice, concrete actions, explicit trigger guidance, and a clearly distinct niche. It answers both what and when without padding. No changes needed.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('writing, modifying, or reviewing code') and trigger tasks ('add a feature, refactor, fix a bug, write tests, or review a change'), matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what ('Apply the team's shared coding rules before writing, modifying, or reviewing code') and when ('Trigger when the user asks to add a feature, refactor, fix a bug, write tests, or review a change').	3 / 3
Trigger Term Quality	Triggers use natural terms users would say ('add a feature, refactor, fix a bug, write tests, review a change') with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	A clear niche (team coding rules via the read-only team-rules MCP workspace) with distinct triggers tied to code-writing tasks, making conflict with other skills unlikely.	3 / 3
	Total	12 / 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: redis/agent-filesystem
Commit: 990b8eb

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.