circleci-cli

Operate and troubleshoot CircleCI using the CircleCI CLI. Use when users ask to authenticate CLI access, inspect pipeline/workflow/job status, validate configuration locally, rerun pipelines/jobs, trigger pipelines, or gather actionable diagnostics from CLI outputs.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%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-organized, token-efficient skill body with a sound read-first workflow and good guardrails around CLI version differences. Its main weakness is actionability: it names subcommands but never provides a complete example invocation, and the workflow lacks explicit error-recovery loops for the mutating steps.

Suggestions

Add one or two complete example commands for the most common operations (e.g., 'circleci pipeline list <project-slug>' and a rerun command with real arguments) so guidance is copy-paste ready.

Add an explicit feedback loop for the mutating steps, e.g., 'if validation fails, report the error, fix the config, and re-run validation before rerunning the pipeline'.

Tighten the Overview and Guardrails sections, which partially restate the Workflow and the Installed CLI Compatibility section.

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanation of concepts Claude already knows, but the Overview sentence 'Prioritize safe, read-first diagnostics, then run targeted mutating commands only after confirming scope' restates the Workflow section, and Guardrails overlaps slightly with Installed CLI Compatibility, so a little trimming is possible.	4 / 5
Actionability	Real subcommands are named ('circleci help', 'circleci pipeline list\|create\|run', 'circleci trigger ...') but no complete executable command with arguments (project slug, flags, example invocations) appears anywhere, so guidance stays at the pattern level rather than copy-paste ready.	3 / 5
Workflow Clarity	The five-step read-first sequence is clear with pre-mutation checkpoints (verify auth first, extract failing scope before rerun, validate config before edits), but there is no explicit error-recovery feedback loop (e.g., what to do when validation or a rerun fails), which the top anchor requires.	4 / 5
Progressive Disclosure	The skill is a short, single-purpose overview (~55 lines) with no bundle files and no need for external references; sections are well-organized and self-contained, which the simple-skill exception scores as full marks.	5 / 5
	Total	16 / 20 Passed

Description

92%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 strong description: third-person voice, comprehensive concrete capabilities, and an explicit 'Use when...' trigger clause. The only weakness is modest synonym coverage — users saying 'build' or 'CI' rather than 'pipeline'/'job' would not match as naturally.

Suggestions

Add common user synonyms such as 'builds', 'build failures', or 'CI' to the 'Use when...' clause so the description triggers for users who use those terms instead of 'pipeline'/'job'.

Dimension	Reasoning	Score
Specificity	The description lists six concrete capabilities ('authenticate CLI access', 'inspect pipeline/workflow/job status', 'validate configuration locally', 'rerun pipelines/jobs', 'trigger pipelines', 'gather actionable diagnostics'), giving comprehensive coverage of the skill's actions with no significant gaps.	5 / 5
Completeness	It explicitly answers what the skill does ('Operate and troubleshoot CircleCI using the CircleCI CLI') and when to use it via a concrete 'Use when users ask to...' clause enumerating specific triggers, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Natural terms like 'CircleCI', 'pipeline', 'workflow', 'job status', 'rerun', 'trigger', and 'validate configuration' are present, but common user phrasings such as 'CI', 'build', 'build failed', or 'flaky tests' are missing, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The CircleCI CLI niche is explicitly and repeatedly named, and all triggers are CircleCI-specific operations, so overlap with other skills is minimal.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/circleci/skills/cli/SKILL.md
Commit: 5fd93af

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.