CtrlK
BlogDocsLog inGet started
Tessl Logo

circleci-automation

Automate CircleCI tasks via Rube MCP (Composio): trigger pipelines, monitor workflows/jobs, retrieve artifacts and test metadata. Always search tools first for current schemas.

76

1.44x
Quality

65%

Does it follow best practices?

Impact

100%

1.44x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.trae/skills/circleci-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

41%

CircleCI Automation Integration Guide

CircleCI connection setup and pipeline trigger workflow

Criteria
Without context
With context

RUBE_SEARCH_TOOLS first

0%

100%

RUBE_MANAGE_CONNECTIONS usage

0%

100%

ACTIVE status check

30%

100%

GitHub project_slug format

100%

100%

Bitbucket project_slug format

100%

100%

Branch/tag mutual exclusion

100%

100%

CIRCLECI_TRIGGER_PIPELINE call

100%

100%

Pipeline ID returned asynchronously

100%

100%

Case-sensitivity awareness

100%

100%

Correct tool sequence documented

0%

100%

100%

25%

CI/CD Pipeline Status Monitor

Pipeline hierarchy traversal, pagination, and rate limiting

Criteria
Without context
With context

CIRCLECI_LIST_PIPELINES_FOR_PROJECT

100%

100%

CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID

100%

100%

CIRCLECI_GET_JOB_DETAILS for jobs

0%

100%

Pipeline IDs as UUIDs

100%

100%

Job numbers as integers

0%

100%

Pagination: reads next_page_token

100%

100%

Pagination: passes page_token

100%

100%

Pagination loop termination

100%

100%

Rate limiting / backoff

30%

100%

GitHub project_slug format

100%

100%

Workflow states in output

100%

100%

100%

26%

CI Failure Investigator

Job details, artifact retrieval, and test metadata investigation

Criteria
Without context
With context

CIRCLECI_GET_JOB_DETAILS before test metadata

100%

100%

CIRCLECI_GET_JOB_DETAILS before artifacts

100%

100%

CIRCLECI_GET_TEST_METADATA tool

0%

100%

CIRCLECI_GET_JOB_ARTIFACTS tool

0%

100%

Job number as integer

100%

100%

Failed test 'message' field

100%

100%

JUnit XML requirement noted

0%

100%

Artifact auth headers noted

100%

100%

Test metadata fields used

100%

100%

Correct project_slug format

100%

100%

Job completion check

71%

100%

Repository
Lingjie-chen/MT5
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.