CtrlK
BlogDocsLog inGet started
Tessl Logo

setup-serena-mcp

Guide for setup Serena MCP server for semantic code retrieval and editing capabilities

38

Quality

36%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/mcp/skills/setup-serena-mcp/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

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 framework for setting up Serena MCP server but relies too heavily on external documentation rather than providing concrete, executable guidance inline. The workflow has a good overall structure with the restart message being a strong point, but lacks explicit error recovery paths and has some redundancy between steps 4 and 6. The CLAUDE.md content template is well-crafted and actionable.

Suggestions

Inline the key setup commands (e.g., `uv --version` for prerequisite check, `serena project create --index` for initialization) rather than deferring entirely to external URLs that may change

Add explicit error recovery steps: what to do if `uv` is not installed, if Serena tools are still inaccessible after restart, or if indexing fails

Merge Step 6 into Step 4 to eliminate redundancy — both cover project initialization

Replace the four external URL loads in Step 3 with a concise summary of the essential setup information, referencing URLs only as fallback for edge cases

DimensionReasoningScore

Conciseness

The skill is moderately efficient but includes some unnecessary verbosity. Step 3 delegates entirely to external URLs rather than summarizing key points, and Step 6 is redundant with Step 4. The CLAUDE.md content block is appropriately detailed, but the overall structure could be tightened.

2 / 3

Actionability

The skill provides a structured process but lacks concrete executable commands for most steps. It relies heavily on loading external documentation (Step 3) rather than providing specific commands inline. Key actions like 'Check prerequisites' and 'Guide user to run project initialization commands' are vague rather than specifying exact commands (e.g., `uv --version`, `serena project create --index`).

2 / 3

Workflow Clarity

The multi-step process is sequenced and includes some validation (test connection, restart instructions), but validation checkpoints are incomplete. Step 4 mixes setup and testing without clear error recovery paths. The restart message is well-defined, but there's no explicit feedback loop for what to do if prerequisites fail or if Serena tools remain inaccessible after restart.

2 / 3

Progressive Disclosure

The skill references external documentation URLs for detailed setup, which is reasonable progressive disclosure. However, there are no bundle files to support the skill, and the external URLs could become stale. Step 6 overlaps significantly with Step 4, creating confusion about where project initialization actually lives. The structure is adequate but not cleanly layered.

2 / 3

Total

8

/

12

Passed

Description

22%

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 too vague and reads more like a document title than a functional skill description. It lacks concrete actions, natural trigger terms users would say, and has no explicit 'Use when...' guidance. The mention of 'Serena MCP server' provides some distinctiveness but is insufficient to make this a well-functioning skill description.

Suggestions

Add a 'Use when...' clause specifying triggers, e.g., 'Use when the user wants to set up or configure Serena MCP server, or needs help with semantic code navigation and editing tools.'

List specific concrete actions the skill covers, e.g., 'Configures Serena MCP server, sets up semantic code indexing, enables symbol search, code navigation, and refactoring capabilities.'

Include natural keywords users might say, such as 'Serena setup', 'code search', 'symbol lookup', 'MCP configuration', 'code indexing'.

DimensionReasoningScore

Specificity

The description says 'setup Serena MCP server for semantic code retrieval and editing capabilities' which is vague. It mentions 'semantic code retrieval and editing' but doesn't list concrete actions like 'search functions by name', 'refactor code blocks', or 'navigate symbol definitions'.

1 / 3

Completeness

The description weakly addresses 'what' (setup guide for Serena MCP server) but completely lacks a 'when' clause. There is no explicit trigger guidance like 'Use when...' to tell Claude when to select this skill.

1 / 3

Trigger Term Quality

Contains some relevant keywords like 'Serena', 'MCP server', 'semantic code retrieval', and 'editing', but misses common user-facing terms. Users might say 'code search', 'find references', 'code navigation', or 'Serena setup' — the description partially covers this but lacks natural variation.

2 / 3

Distinctiveness Conflict Risk

The mention of 'Serena MCP server' provides some distinctiveness as it's a specific tool, but 'semantic code retrieval and editing' is broad enough to overlap with other code search or editing skills.

2 / 3

Total

6

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
NeoLabHQ/context-engineering-kit
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.