serena

Token-efficient Serena MCP command for structured app development and problem-solving

Quality

25%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/serena/SKILL.md

Quality

Discovery

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 description is very weak across all dimensions. It relies on jargon ('Serena MCP command', 'token-efficient') without explaining what the skill concretely does, uses overly broad terms like 'app development and problem-solving', and lacks any explicit trigger guidance for when Claude should select it.

Suggestions

Add a 'Use when...' clause specifying explicit triggers, e.g., 'Use when the user asks to build an app using Serena, or mentions Serena MCP workflows.'

Replace vague phrases like 'structured app development and problem-solving' with concrete actions, e.g., 'Scaffolds project structures, generates boilerplate code, and debugs application issues using Serena MCP commands.'

Include natural keywords users might say, such as 'scaffold', 'project setup', 'Serena', 'build app', or specific file types and frameworks supported.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'structured app development and problem-solving' without listing any concrete actions. It does not specify what the skill actually does beyond mentioning 'Serena MCP command' which is jargon.	1 / 3
Completeness	The description weakly addresses 'what' (something about app development with Serena MCP) and completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	The terms 'Serena MCP command' and 'token-efficient' are technical jargon unlikely to be used by users naturally. 'App development' and 'problem-solving' are overly generic and don't provide useful trigger terms.	1 / 3
Distinctiveness Conflict Risk	'App development and problem-solving' is extremely broad and would conflict with virtually any coding or development skill. The mention of 'Serena MCP' adds some specificity but is not explained enough to create a clear niche.	1 / 3
	Total	4 / 12 Passed

Implementation

50%

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

This skill provides a reasonable overview of a Serena MCP development workflow with clear section organization and useful quick-reference tables. However, it lacks concrete executable examples (actual MCP tool invocations with parameters and expected outputs), validation/feedback loops in its workflows, and the problem-specific templates read more like abstract checklists than actionable guides. The slash commands appear to be a custom convention without showing what actually happens under the hood.

Suggestions

Add concrete, executable examples showing actual MCP tool invocations with parameters and expected outputs (e.g., show a real `mcp__serena__search_for_pattern` call with arguments and what the response looks like)

Add validation checkpoints and error recovery steps to the problem-specific templates (e.g., in Debug Pattern: 'If root cause hypothesis is invalidated, return to step 3 with new evidence')

Replace or supplement the abstract template steps with concrete examples showing a real problem being solved end-to-end using the described workflow

Clarify whether the `/serena` slash commands are actual executable commands or conceptual patterns—if conceptual, reframe them as workflow descriptions rather than CLI syntax

Dimension	Reasoning	Score
Conciseness	The content is reasonably structured but includes some unnecessary elements like explaining what each pattern's thought count is multiple times, and the cross-command integration table adds little actionable value. The 'Best Practices' section is somewhat generic.	2 / 3
Actionability	The skill provides tool names and CLI-style commands, but the commands appear to be pseudo-commands (slash commands) rather than executable code. The 'Problem-Specific Templates' are abstract checklists rather than concrete executable steps. There's no actual code showing how to invoke these MCP tools or what their parameters/outputs look like.	2 / 3
Workflow Clarity	The problem-specific templates provide numbered steps for multi-step processes, but they lack validation checkpoints, error recovery steps, and feedback loops. For example, the Debug Pattern lists steps but doesn't specify what to do if hypothesis validation fails or how to verify a fix works.	2 / 3
Progressive Disclosure	The content is organized into clear sections with headers and tables, which is good. However, everything is inline in a single file with no references to deeper documentation. The templates could benefit from linking to detailed guides, and the tool descriptions are shallow without pointing to fuller references.	2 / 3
	Total	8 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: sc30gsw/claude-code-customes
Commit: 7aff694

Reviewed: 7 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.