CtrlK
BlogDocsLog inGet started
Tessl Logo

omnichannel-chat

General-purpose AI assistant that answers naturally over web chat and external messaging platforms (Telegram, Slack, Discord, WhatsApp, Messenger). One agent, every channel.

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./samples/spring-boot-channels-chat/src/main/resources/META-INF/skills/omnichannel-chat/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 appropriately concise and well-structured for a simple persona skill, with clear organization and no token waste. Its main weakness is actionability: it directs Claude to adapt to each platform's message limit without supplying those limits, leaving a key detail unspecified.

Suggestions

Add the concrete per-platform message/length limits (or a small table) so 'adapt response length to each platform's message limit' is directly executable.

Optionally include one short before/after example showing a long answer reformatted for a messaging channel to make the formatting guidance concrete.

DimensionReasoningScore

Conciseness

The body is lean and efficient — short persona directive, brief paragraph, and two tight bulleted lists — with no padding or explanation of concepts Claude already knows, matching anchor 5.

5 / 5

Actionability

Gives some concrete guidance ('short paragraphs and minimal markdown') but is incomplete: 'adapt response length to each platform's message limit' is stated without the actual per-platform limits, leaving key details missing per anchor 3.

3 / 5

Workflow Clarity

As a simple single-purpose skill the core action (answer consistently, format per platform) is fairly clear and well-organized, though it stops short of being fully unambiguous because platform-specific limits are not defined.

4 / 5

Progressive Disclosure

Under 50 lines with no external references needed and well-organized sections (persona, Skills, Channels), so per the simple-skill guideline progressive disclosure scores 5 on structure alone.

5 / 5

Total

17

/

20

Passed

Description

48%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 clearly states the domain and lists concrete platforms, but relies on a single generic action verb and lacks an explicit 'Use when...' trigger clause, capping completeness. It is reasonably distinct but would benefit from explicit trigger guidance and more concrete capabilities.

Suggestions

Add an explicit 'Use when...' clause naming the natural trigger phrases (e.g., 'Use when the user asks to send, reply, or answer messages on Telegram, Slack, Discord, WhatsApp, or Messenger').

Replace the single generic verb 'answers naturally' with several concrete actions (e.g., 'answers questions, sends replies, and maintains persona across web chat and messaging platforms').

Include common phrasal variations and the web-chat trigger term more explicitly to raise trigger-term coverage.

DimensionReasoningScore

Specificity

Names the multi-channel domain and enumerates five platforms, but the only action is the generic verb 'answers naturally' — minimal/generic rather than multiple concrete actions, matching anchor 2.

2 / 5

Completeness

Has a clear 'what' (answers over web chat and named messaging platforms) but no 'Use when...' trigger clause, so per guideline completeness is capped at 3 with 'when' only weakly implied.

3 / 5

Trigger Term Quality

Includes natural platform names (Telegram, Slack, Discord, WhatsApp, Messenger) and 'web chat' that users would say, but misses common phrasal variations like 'send a message to Slack', fitting anchor 3.

3 / 5

Distinctiveness Conflict Risk

Enumerating five specific messaging platforms gives a mostly-distinct niche with only minor overlap risk against other channel-integration skills, though 'general-purpose AI assistant' framing is broad.

4 / 5

Total

12

/

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.