agent-ops-cicd-github

Agent skill for ops-cicd-github - invoke with $agent-ops-cicd-github

1.00x

Quality

—

Does it follow best practices?

Impact

100%

1.00x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

22%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body mixes a large embedded YAML configuration dump with a reasonably lean but high-level markdown guide. It offers one concrete workflow example but no sequenced process, validation checkpoints, or external reference structure, and much of the content is configuration bloat.

Suggestions

Remove or move the embedded YAML config block out of the body; keep SKILL.md as a lean overview of what to build and when.

Add a concrete, sequenced workflow with validation checkpoints (e.g. lint with actionlint -> dry-run -> deploy) since the skill covers production deployments.

Replace abstract best-practice bullets with specific, actionable guidance (exact commands, reusable composite-action patterns, concrete permission snippets).

Dimension	Reasoning	Score
Conciseness	The body is dominated by an embedded ~115-line YAML config dump (capabilities, constraints, hooks, examples) that is padded mechanical configuration rather than instruction, and while the trailing markdown is lean, the overall body explains/dumps content Claude does not need, matching the verbose/padded anchor; it is not level 2 because the bulk is unnecessary context.	1 / 3
Actionability	A complete, copy-paste-ready GitHub Actions workflow YAML example is provided, but the surrounding guidance ('Use workflow reusability', 'Implement proper secret management') is abstract bullet advice without concrete commands or specifics, matching the some-concrete-guidance-but-incomplete anchor rather than fully-executable level 3.	2 / 3
Workflow Clarity	There is no sequenced multi-step process — only numbered responsibilities and bulleted best practices — and no validation/verification checkpoints despite the skill covering destructive batch operations like production deployments, matching the steps-missing/no-validation anchor and triggering the cap-at-2 rule which this falls below.	1 / 3
Progressive Disclosure	The markdown is organized into clear sections (responsibilities, best practices, patterns, security) with no broken or deeply-nested references, but the body is well over 50 lines and the large YAML config block is inline content that should be split out or removed, matching the some-structure-but-inline-content anchor rather than a clean overview.	2 / 3
	Total	6 / 12 Passed

Description

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 frontmatter description is an auto-generated placeholder that names a domain slug and an invocation token but describes no concrete capabilities or usage triggers. It fails to tell Claude what the skill does or when to invoke it.

Suggestions

Replace the placeholder with concrete third-person actions, e.g. 'Creates and optimizes GitHub Actions CI/CD workflows, job matrices, caching, and deployment pipelines.'

Add an explicit 'Use when...' trigger clause citing natural terms users say, such as 'Use when the user asks about GitHub Actions, CI/CD pipelines, workflow files in .github/workflows, or deployment automation.'

Drop the 'invoke with $agent-ops-cicd-github' token from the description; invocation syntax is not a capability and adds no trigger value.

Dimension	Reasoning	Score
Specificity	The description only states 'Agent skill for ops-cicd-github' and 'invoke with $agent-ops-cicd-github', naming a domain slug but no concrete actions (no verbs like create, build, or deploy); this matches the vague/abstract anchor and falls short of the level-2 anchor which requires naming some actions.	1 / 3
Completeness	It weakly hints at 'what' via the slug but states no capabilities, and there is no 'Use when...' or equivalent trigger guidance for 'when'; both halves are weak/missing, matching the level-1 anchor and the guideline that a missing 'Use when...' clause caps completeness at 2 at most.	1 / 3
Trigger Term Quality	The only terms are the internal slug 'ops-cicd-github' and the invocation token '$agent-ops-cicd-github' — technical identifiers rather than natural phrases a user would say (e.g. 'github actions', 'ci/cd pipeline'), matching the no-natural-keywords anchor.	1 / 3
Distinctiveness Conflict Risk	The slug 'ops-cicd-github' points at a fairly distinct niche, lowering conflict risk, but the description itself is generic in form ('Agent skill for X') with no distinct trigger phrasing, matching the somewhat-specific-but-overlapping anchor rather than the clearly-distinct level 3.	2 / 3
	Total	5 / 12 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: ruvnet/claude-flow
Commit: 03d4f84

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.