CtrlK
BlogDocsLog inGet started
Tessl Logo

ably-automation

Automate Ably tasks via Rube MCP (Composio). Always search tools first for current schemas.

68

4.57x
Quality

53%

Does it follow best practices?

Impact

96%

4.57x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./composio-skills/ably-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

93%

93%

Ably Onboarding Automation Workflow

Core workflow pattern and session management

Criteria
Without context
With context

Search tools first

0%

53%

Search with use case query

0%

100%

Manage connections step

0%

100%

Active status verification

0%

100%

Auth link handling

0%

100%

Session ID generated

0%

100%

Session ID reused

0%

100%

Memory parameter present

0%

100%

No hardcoded tool slugs

0%

100%

Correct tool execution call

0%

100%

Without context: $0.3451 · 1m 40s · 16 turns · 21 in / 6,362 out tokens

With context: $0.4868 · 2m 7s · 22 turns · 281 in / 7,393 out tokens

96%

73%

Ably Channel Cleanup After Service Sunset

Bulk operations via RUBE_REMOTE_WORKBENCH

Criteria
Without context
With context

RUBE_REMOTE_WORKBENCH for bulk

0%

100%

Search tools first

0%

100%

Connection verified

0%

100%

Pagination handled

100%

100%

Session ID consistent

30%

100%

Memory parameter present

0%

66%

No hardcoded slugs

0%

100%

Schema-compliant arguments

25%

100%

Without context: $0.5978 · 3m 1s · 28 turns · 31 in / 10,307 out tokens

With context: $0.6827 · 3m 20s · 22 turns · 185 in / 12,775 out tokens

100%

59%

Ably Presence Monitoring Integration

Schema discovery via RUBE_GET_TOOL_SCHEMAS

Criteria
Without context
With context

RUBE_GET_TOOL_SCHEMAS for schemaRef

40%

100%

Search tools first

58%

100%

Use-case specific search query

87%

100%

Connection check step

0%

100%

Pagination instructions

93%

100%

Memory parameter

0%

100%

Session ID management

0%

100%

No hardcoded tool slugs

37%

100%

Schema compliance note

40%

100%

Without context: $0.2981 · 1m 40s · 16 turns · 21 in / 5,411 out tokens

With context: $0.2400 · 1m 10s · 12 turns · 48 in / 3,310 out tokens

Repository
ComposioHQ/awesome-claude-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.