CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-assistant

Streaming chat assistant with conversation memory. Use as a general-purpose assistant for multi-turn conversations where streaming output and context retention matter.

44

Quality

47%

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/ai-assistant/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%

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

The body is lean and well-organized but offers no executable guidance, only a description of general capabilities. It reads more like a prompt preamble than a skill body, which drags actionability to the lowest anchor despite good conciseness and structure.

Suggestions

Add concrete, actionable guidance instead of capability lists, e.g., specific instructions on how to handle streaming breaks or when to summarize retained context.

Turn the Guardrails into enforceable rules with thresholds (e.g., 'If a response would exceed 500 words, ask the user before continuing') rather than soft admonitions.

Provide at least one concrete example of expected behavior (a sample short exchange) so the skill instructs rather than merely describes.

DimensionReasoningScore

Conciseness

The body is short, assumes Claude's competence as a chat assistant, and contains no padded explanations of concepts Claude already knows; every line earns its place.

3 / 3

Actionability

The body only describes capabilities in vague terms ('Answer general knowledge questions', 'Explain technical concepts') with no concrete, executable guidance or examples, matching the 'describes rather than instructs' anchor.

1 / 3

Workflow Clarity

For a simple single-purpose assistant there is no multi-step process, and per the simple-skills note clarity can score higher, but the 'Guardrails' are listed without any sequencing or concrete behavior, leaving the workflow implicit rather than crisp.

2 / 3

Progressive Disclosure

The skill is under 50 lines with no need for external references; content is organized into clear headed sections (Skills, Guardrails), which satisfies the simple-skill criterion for a top progressive-disclosure score.

3 / 3

Total

9

/

12

Passed

Description

42%

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 grammatically clean and third-person but describes a very general chat assistant with only a soft trigger clause. It caps at 2 for completeness and scores poorly on distinctiveness because 'general-purpose assistant' is broad enough to collide with most other skills.

Suggestions

Replace 'Use as a general-purpose assistant' with concrete trigger phrasing such as 'Use when the user wants a streaming chat that retains context across turns' to make the 'when' clause explicit.

List specific concrete actions (e.g., 'streams responses token-by-token, retains N turns of context, summarizes prior turns') to raise specificity from vague capability naming to enumerated actions.

Narrow the niche (e.g., streaming-only multi-turn chat) and add distinctive trigger terms ('streaming chat', 'conversation memory', 'multi-turn') so it is less likely to trigger for unrelated assistant skills.

DimensionReasoningScore

Specificity

The description names a domain (streaming chat with conversation memory) and a couple of behaviors (multi-turn conversations, context retention) but does not enumerate multiple concrete actions the way the score-3 anchor requires.

2 / 3

Completeness

It states what the skill does, and the 'Use as a general-purpose assistant for...' clause gives a trigger, but that trigger is broad rather than an explicit 'when the user says X' clause, so per the guideline a missing sharp 'when...' trigger caps completeness at 2.

2 / 3

Trigger Term Quality

It includes some natural terms a user might say ('multi-turn conversations', 'streaming output') but misses common phrasings like 'chat', 'remember what I said', or 'keep talking', so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

'General-purpose assistant for multi-turn conversations' is extremely broad and would overlap with many other assistant-style skills, making conflicts likely.

1 / 3

Total

7

/

12

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.

Validation14 / 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.