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.

80

1.44x
Quality

71%

Does it follow best practices?

Impact

100%

1.44x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/circleci-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, actionable MCP orchestration guide whose tool sequences, parameters, and pitfalls capture genuinely non-obvious knowledge. Its main weaknesses are redundant repetition of the slug format and pitfalls across sections, and the absence of example call payloads or explicit in-workflow validation loops.

Suggestions

State the project_slug format and the UUID-vs-integer ID distinction once (e.g., in Common Patterns) and remove the repeats from each workflow and the Known Pitfalls section.

Merge the per-workflow Pitfalls with the global Known Pitfalls section, or move the consolidated pitfalls plus the Quick Reference table into a one-level-deep reference file.

Add one example tool call with its key parameters and a truncated expected response (e.g., a trigger-pipeline call returning a pipeline UUID) to make the guidance copy-paste ready.

DimensionReasoningScore

Conciseness

The tool slugs, parameters, and pitfalls are non-obvious knowledge that earns its tokens, but content is duplicated: the project_slug format is explained four times (workflow 1, workflow 2, Common Patterns, Known Pitfalls), job-numbers-are-integers appears twice, and the "Known Pitfalls" section largely restates per-workflow pitfalls, plus a "Powered by Composio" footer. Mostly efficient with noticeable repetition — the score-3 anchor rather than 4, where only minor trimming would be needed.

3 / 5

Actionability

Concrete tool sequences with [Required]/[Optional]/[Prerequisite] labels, exact tool slugs (e.g., CIRCLECI_TRIGGER_PIPELINE), parameter names with formats, a sample UUID, and 429 backoff guidance give mostly executable instruction. Not 5 because no example call payloads or response shapes are shown, leaving minor gaps for an instruction-only skill.

4 / 5

Workflow Clarity

Each workflow is clearly sequenced with prerequisite steps (e.g., "CIRCLECI_GET_JOB_DETAILS - Confirm job completed successfully [Prerequisite]"), and setup includes an explicit checkpoint ("Confirm connection status shows ACTIVE before running any workflows") plus 429 backoff as error recovery. Not 5 because the workflows themselves lack an explicit validate-then-fix-retry loop; these are read/trigger operations, so the destructive/batch cap does not apply.

4 / 5

Progressive Disclosure

No bundle files exist and the body is well-sectioned (prerequisites, five workflows, common patterns, pitfalls, quick-reference table), self-contained at ~175 lines. Good structure with minor organization gaps — the Known Pitfalls and Quick Reference bulk could live in a one-level-deep reference file — matching the score-4 anchor rather than 5.

4 / 5

Total

15

/

20

Passed

Description

75%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.

A highly specific, distinctive description with concrete verb-led capabilities, weakened only by the absence of any explicit "Use when..." trigger guidance and some jargon-heavy phrasing ("test metadata") where natural synonyms are missing. Adding a when-clause and user-facing synonyms would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to trigger or check CircleCI pipelines, builds, or CI/CD jobs, or fetch build artifacts and test results."

Swap the API jargon "test metadata" for the user-facing "test results" and add common synonyms like "build" and "CI status".

Consider naming the main entry points users would mention (e.g., "CircleCI builds/deploys") to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

"trigger pipelines, monitor workflows/jobs, retrieve artifacts and test metadata" lists four concrete actions covering the toolkit's core operations. Comprehensive coverage matching the score-5 anchor; only trivial omissions (e.g., viewing pipeline config) keep it from being arguably fuller, so it is not the level below.

5 / 5

Completeness

The "what" is explicit and concrete, but there is no "Use when..." clause or equivalent trigger guidance; "Always search tools first for current schemas" is an instruction, not a when. Per the judging guideline, a missing when-clause caps completeness at 3; not 2 because the what is fully stated rather than vague.

3 / 5

Trigger Term Quality

"CircleCI", "pipelines", "workflows", "jobs", "artifacts" are terms users naturally say, but "test metadata" is API jargon where users would say "test results", and synonyms like "build" or "CI status" are missing. Good keyword coverage with a few natural terms missing — the score-4 anchor, not 5 (synonym gaps) and not 3 (core vocabulary is well represented).

4 / 5

Distinctiveness Conflict Risk

"CircleCI" plus "Rube MCP (Composio)" carves out a clear niche with distinct triggers, unlikely to fire for GitHub Actions/Jenkins/GitLab skills. Clear niche with minimal conflict risk — the score-5 anchor.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
davepoon/buildwithclaude
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.