CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp-chat-summary

Chat moderator that summarizes ongoing conversations. Use when invoked through the Atmosphere MCP server's chat-summary tool.

44

Quality

46%

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-chat-summary/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

30%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 body is a single persona sentence with no instructions on what to summarize, how to format output, or how to moderate — the skill's actual substance exists only in the frontmatter description. While nothing is wasted or buried, the body provides essentially no actionable guidance, making this an empty shell of a skill.

Suggestions

Replace the persona line with concrete instructions: what a summary should cover (key decisions, open questions, action items), the expected output format, and length constraints.

Add a minimal workflow (read the conversation → identify key threads → produce the summary), even as a short numbered list, so the task is unambiguous.

Include at least one example of a good summary output so the expected result is concrete and reproducible.

DimensionReasoningScore

Conciseness

The one-line body has no padding and no explanation of concepts Claude already knows, sitting just above the midpoint. Not a 5 because the single sentence ("You are a helpful chat moderator assistant") itself adds no information Claude doesn't have — the one token spent doesn't earn its place.

4 / 5

Actionability

"You are a helpful chat moderator assistant" contains no concrete guidance, commands, examples, or output format for how to summarize or moderate — it describes a persona rather than instructing any action. This squarely matches the anchor 'Entirely vague or abstract; only describes rather than instructs'.

1 / 5

Workflow Clarity

There is no sequence, no steps, and no validation; the actual task (summarizing conversations) is not even restated in the body. The simple-skill exception cannot apply because the single action is not unambiguous — the body never states any action at all.

1 / 5

Progressive Disclosure

No bundle files exist, so nothing is buried or nested, but the body has no sections or organization and surfaces nothing actionable. It falls between the 'minimal structure' anchor and the well-organized single-purpose ideal the scoring notes describe, since a one-line body with no headers and no task statement is not 'well-organized sections'.

3 / 5

Total

9

/

20

Passed

Description

62%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 concise, uses third person, and includes an explicit 'Use when' clause tied to a specific MCP tool, which gives it decent completeness and distinctiveness. However, it only lists one action and its trigger terms lack natural user phrasing and synonyms, leaving it mid-pack rather than strong.

Suggestions

Enumerate 2-3 concrete actions beyond summarizing (e.g., what the summary covers, message volume handled, how it is formatted) to raise specificity.

Add natural trigger phrases users would actually say ("catch up on the conversation", "recap the channel", "summarize this thread") alongside the MCP invocation condition.

Sharpen the 'when' clause to describe user intent, not just the invocation path, so it reads as a trigger rather than plumbing documentation.

DimensionReasoningScore

Specificity

"Chat moderator that summarizes ongoing conversations" names the domain and one concrete action (summarizing), matching the 'names domain and 1-2 concrete actions' anchor. It is not a 4 because there is no listing of several specific actions (e.g., what the summary contains, how it is delivered, moderation actions).

3 / 5

Completeness

Both parts are present: the what ("summarizes ongoing conversations") and the when ("Use when invoked through the Atmosphere MCP server's chat-summary tool"). Not a 5 because the 'when' describes the invocation plumbing rather than concrete user-facing trigger phrases, and the 'what' is a single thin action.

4 / 5

Trigger Term Quality

Terms like "chat", "conversations", "summarizes", and "chat-summary" are relevant, but common natural variations ("recap", "digest", "catch up on the channel", "thread summary") are missing. Not a 4 because keyword coverage is thin and the only trigger is a mechanical MCP invocation path rather than user-phrased terms.

3 / 5

Distinctiveness Conflict Risk

The Atmosphere MCP "chat-summary" tool binding carves a fairly distinct niche with minimal conflict risk against general summarization skills. Not a 5 because "summarizes ongoing conversations" on its own overlaps with any chat-recap or notes skill if the tool binding is not the deciding trigger.

4 / 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.