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.
77
96%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description that clearly communicates both purpose and trigger conditions. It excels at specificity and completeness with an explicit 'Trigger when...' clause and concrete action verbs. The main weakness is that its trigger terms overlap heavily with general coding tasks, which could cause it to fire alongside or instead of other coding-related skills.
Suggestions
Consider narrowing the trigger clause or adding a differentiator like 'Use this skill *before* other coding skills to load team conventions' to clarify its role relative to other code-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'writing, modifying, or reviewing code', 'add a feature, refactor, fix a bug, write tests, or review a change', and specifies the mechanism of reading rules from a specific MCP workspace path. | 3 / 3 |
Completeness | Clearly answers both 'what' (apply shared coding rules before writing/modifying/reviewing code, reads rules from MCP workspace) and 'when' (explicit 'Trigger when...' clause listing specific scenarios). | 3 / 3 |
Trigger Term Quality | Includes highly natural trigger terms users would actually say: 'add a feature', 'refactor', 'fix a bug', 'write tests', 'review a change'. These cover the most common coding task requests comprehensively. | 3 / 3 |
Distinctiveness Conflict Risk | The triggers overlap significantly with general coding skills since 'add a feature', 'fix a bug', 'write tests' are common to many coding-related skills. The distinguishing factor is the team-rules/MCP workspace aspect, but the broad coding triggers could cause conflicts with other code-focused skills. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, well-crafted skill. It's concise yet complete, providing exact tool names, file paths, and a clear workflow without over-explaining. The quick reference table adds high-density value, and the rules of engagement section handles edge cases (conflicts, missing rules, read-only constraints) cleanly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No unnecessary explanations of what MCP is or how workspaces work. The quick reference table is dense and useful. The read-only constraint is stated once, concisely. | 3 / 3 |
Actionability | Provides the exact MCP tool call name (`mcp__team-rules__file_list`), specific parameters (`path: "/rules"`, `depth: 2`), concrete file paths to read for each situation, and explicit instructions on citing rules. Claude knows exactly what to do. | 3 / 3 |
Workflow Clarity | The 4-step workflow is clearly sequenced (list → read → cite → apply). Conflict handling is explicitly addressed (surface and ask). The constraint about not writing is a clear guardrail. For a non-destructive read-then-apply workflow, validation checkpoints aren't critical, and the conflict-resolution step serves as an adequate checkpoint. | 3 / 3 |
Progressive Disclosure | For a skill of this size and scope, the content is well-organized into logical sections (workflow, rules of engagement, quick reference table) without being monolithic. No bundle files are needed since the skill references external rule files via MCP at runtime, which is the appropriate design. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- redis/agent-filesystem
- Commit
ef5c9a4
- Reviewed
Table of Contents
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.