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.

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 ./skills/circleci-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 skill provides a reasonable overview of CircleCI automation via Rube MCP with clear workflow sequences and useful pitfall documentation. However, it suffers from significant content repetition (project slug format, ID types explained multiple times), lacks concrete executable examples showing actual MCP call syntax, and could benefit from consolidating duplicated information. The 'When to Use' section at the end adds no value.

Suggestions

Consolidate repeated information: project_slug format, ID type distinctions, and pitfalls are each stated 2-3 times across sections. Define them once in a reference section and remove duplicates.

Add at least one concrete MCP call example showing the actual invocation syntax with realistic arguments and a sample response, so Claude knows the exact format to use.

Remove the vacuous 'When to Use' section at the bottom, which adds no information beyond restating the description.

Consider adding a brief error-handling pattern (e.g., what to do on 404 from bad project_slug, or how to retry on 429) as a reusable pattern rather than just listing it as a pitfall.

DimensionReasoningScore

Conciseness

The skill has significant repetition — project_slug format is explained three times (in individual workflows, Common Patterns, and Known Pitfalls), ID format distinctions are repeated multiple times, and pitfalls sections overlap heavily with the Known Pitfalls section. The 'When to Use' footer is vacuous. However, the core content is relevant and not explaining concepts Claude already knows.

3 / 5

Actionability

The skill provides tool names, parameter names, and sequences, but no actual executable code or MCP call examples with concrete arguments. Everything is described at a high level — 'Call CIRCLECI_TRIGGER_PIPELINE' — without showing the actual invocation syntax, request format, or response structure. The guidance is specific enough to follow but lacks copy-paste ready examples.

3 / 5

Workflow Clarity

Workflows are clearly sequenced with labeled steps (Required/Optional/Prerequisite), and the pipeline->workflow->job hierarchy is well explained. However, there are no explicit validation/error-recovery feedback loops — e.g., what to do if a pipeline trigger fails, or how to handle a workflow stuck in 'on_hold' state. Since these aren't destructive operations, the missing feedback loops don't cap the score at 3.

4 / 5

Progressive Disclosure

All content is inlined in a single file with no bundle files or references to external documentation. The file is ~150 lines with substantial repetition that could be consolidated. The Quick Reference table is helpful, but the repeated pitfalls sections and Common Patterns section largely duplicate content from the individual workflow sections, suggesting the content could be better organized.

3 / 5

Total

13

/

20

Passed

Description

70%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 effectively communicates specific CircleCI automation capabilities and names the integration mechanism (Rube MCP/Composio), making it highly distinctive. However, it lacks an explicit 'Use when...' clause that would help Claude know when to select this skill, and could benefit from additional trigger terms covering common user phrasings around CI/CD.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks about CircleCI builds, CI/CD pipelines, build status, or deployment workflows'

Include common synonyms and variations users might say: 'CI/CD', 'build', 'deploy', 'continuous integration', 'circle ci'

DimensionReasoningScore

Specificity

Lists several specific actions: trigger pipelines, monitor workflows/jobs, retrieve artifacts and test metadata. These are concrete actions, though coverage could be slightly more comprehensive (e.g., listing configuration, environment variables, etc.).

4 / 5

Completeness

Has a clear 'what' (automate CircleCI tasks via Rube MCP with specific actions listed) but lacks an explicit 'when' clause. The instruction to 'always search tools first' is operational guidance, not a trigger condition. No 'Use when...' clause is present, which caps this at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes good natural keywords like 'CircleCI', 'pipelines', 'workflows', 'jobs', 'artifacts', 'test metadata'. Missing some variations users might say like 'CI/CD', 'build status', 'deployment', or 'circle ci' (space-separated).

4 / 5

Distinctiveness Conflict Risk

Very distinct niche: CircleCI automation via a specific MCP tool (Rube/Composio). The combination of the platform (CircleCI), the integration method (Rube MCP/Composio), and specific CI/CD actions makes this highly unlikely to conflict with other skills.

5 / 5

Total

16

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.