CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp-analyze-topic

Expert analyst persona used by the MCP analyze-topic tool to produce structured topic analyses. Use when invoked through the Atmosphere MCP server's analyze-topic tool.

46

Quality

49%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./modules/skills/src/main/resources/META-INF/skills/mcp-analyze-topic/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

37%Weight 40%Scale 1-5

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

The SKILL.md body is a single generic persona sentence that provides no actionable guidance: it neither defines what a "structured topic analysis" looks like (sections, format, output schema) nor gives any workflow, examples, or persona detail beyond "expert analyst". The description promises structured analyses the body never equips Claude to deliver.

Suggestions

Specify the output structure for a topic analysis (e.g., required sections like overview, key entities, sub-topics, open questions, and citations) so the 'structured' claim in the description is backed by a concrete template.

Add the persona substance the skill claims: the analytical lens to apply, depth/tone expectations, and how to handle sparse or ambiguous source material.

If fuller guidance exists elsewhere (prompt templates, example analyses), move it into a reference file and link it from SKILL.md so the body serves as a real overview rather than a placeholder.

DimensionReasoningScore

Conciseness

The body is a single sentence ("You are an expert analyst.") with zero padding and zero over-explanation of concepts Claude already knows. It fully matches the "lean and efficient; assumes Claude's competence" anchor — though the missing substance is captured under actionability, not here.

5 / 5

Actionability

The entire body is "You are an expert analyst." — no concrete guidance, no code or commands, no specification of the analysis structure, format, or steps. This matches the lowest anchor ("entirely vague or abstract ... only describes rather than instructs") and is arguably weaker since it barely even describes.

1 / 5

Workflow Clarity

No sequence of steps exists for producing a "structured topic analysis"; there is no workflow at all to evaluate. The simple-skill exception does not apply because the single action is ambiguous — nothing defines what steps or checkpoints the analysis involves.

1 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/) and nothing is inlined that belongs elsewhere, so there are no nesting or navigation failures. However, the body has no sections or organization at all, and an MCP tool this thin provides no pointer to where a fuller persona or analysis template would live, so it sits between "no structure issues" and "minimal structure".

3 / 5

Total

10

/

20

Passed

Description

61%Weight 40%Scale 1-5

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 well-scoped, appropriately brief MCP-tool description with an explicit "Use when..." trigger clause and essentially zero conflict risk. Its main weakness is that the capability statement ("produce structured topic analyses") stays at the level of the domain without naming any concrete actions or output components.

DimensionReasoningScore

Specificity

The description names the domain ("the MCP analyze-topic tool" and "structured topic analyses") but the only action is the generic "produce structured topic analyses" with no concrete analysis actions enumerated. It does not reach anchor 3 because no specific 1-2 concrete actions (e.g., what the analysis contains or how it is structured) are stated.

2 / 5

Completeness

Both parts are present: the "what" ("Expert analyst persona ... to produce structured topic analyses") and an explicit "when" ("Use when invoked through the Atmosphere MCP server's analyze-topic tool"). Not 5 because the "what" is high-level — it never says what a structured topic analysis actually includes.

4 / 5

Trigger Term Quality

Relevant keywords like "analyze-topic", "topic analyses", and "Atmosphere MCP server" are present and the invocation trigger is named exactly, but there are no natural variations or synonyms users/model-callers might use. Not 4 because coverage is limited to the exact tool name with no broader natural phrasing.

3 / 5

Distinctiveness Conflict Risk

The trigger is tightly bound to a single named tool ("the Atmosphere MCP server's analyze-topic tool"), giving it a clear niche with minimal conflict risk against other skills. It clearly matches the top anchor rather than anchor 4's "minor overlap risk".

5 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
Atmosphere/atmosphere
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.