CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-ops-cicd-github

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

40

1.00x
Quality

7%

Does it follow best practices?

Impact

100%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-ops-cicd-github/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

14%Scale 1-3

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

This skill is dominated by an extremely large YAML frontmatter block that contains configuration metadata, hooks, and examples that don't translate into actionable guidance for Claude. The body content is a shallow list of generic best practices Claude already knows, with only one concrete workflow example. It lacks a clear step-by-step process, validation checkpoints, and any progressive disclosure structure.

Suggestions

Remove or drastically reduce the YAML frontmatter to essential metadata only, and move the actual instructional content into the body with clear structure and actionable steps.

Add a concrete multi-step workflow for creating a CI/CD pipeline (e.g., 1. Detect project type, 2. Generate workflow file, 3. Validate YAML syntax, 4. Verify with dry-run) with explicit validation checkpoints.

Replace generic best-practice bullet points ('implement proper secret management') with specific, executable examples showing how to implement each practice in a GitHub Actions workflow.

Add references to supporting files for advanced topics (e.g., matrix strategies, composite actions, deployment patterns) to implement progressive disclosure rather than listing everything superficially.

DimensionReasoningScore

Conciseness

The vast majority of the file is YAML frontmatter configuration that is not actionable skill content—it's metadata bloat. The actual body content is brief but consists largely of vague bullet-point lists of responsibilities and best practices that Claude already knows (e.g., 'never hardcode secrets', 'use appropriate runners'). Very little earns its token cost.

1 / 3

Actionability

There is one concrete, executable YAML workflow example which provides some actionable guidance. However, the rest of the content is vague direction ('implement proper secret management', 'use workflow reusability with composite actions') without concrete commands, specific configurations, or copy-paste ready examples for those topics.

2 / 3

Workflow Clarity

There is no clear multi-step workflow for creating or modifying CI/CD pipelines. The content lists responsibilities and best practices but never sequences them into a process. There are no validation checkpoints or feedback loops for what could be destructive operations (modifying production deployment workflows).

1 / 3

Progressive Disclosure

The content is a monolithic mix of massive YAML frontmatter and a flat body with no references to supporting files. There is no bundle, no navigation structure, and no separation of overview from detailed reference material. The frontmatter itself contains content (hooks, examples) that bloats the file without clear organization.

1 / 3

Total

5

/

12

Passed

Description

0%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is essentially a placeholder that provides no useful information about the skill's capabilities, use cases, or trigger conditions. It only names the skill and provides an invocation command, making it impossible for Claude to determine when to select this skill from a list of available options. This is one of the weakest possible descriptions.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Manages GitHub Actions CI/CD pipelines, configures workflows, monitors build status, and troubleshoots deployment failures.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about GitHub Actions, CI/CD pipelines, deployment workflows, build failures, or continuous integration/deployment configuration.'

Remove the invocation instruction ('invoke with $agent-ops-cicd-github') from the description and replace it with capability and trigger information that helps Claude select the right skill.

DimensionReasoningScore

Specificity

The description contains no concrete actions whatsoever. It only states it is an 'agent skill' and provides an invocation command, with no indication of what the skill actually does.

1 / 3

Completeness

The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance.

1 / 3

Trigger Term Quality

The only potentially relevant terms are 'ops', 'cicd', and 'github', which are embedded in a hyphenated identifier rather than presented as natural keywords a user would say. There are no natural trigger terms like 'pipeline', 'deploy', 'CI/CD', 'GitHub Actions', 'workflow', etc.

1 / 3

Distinctiveness Conflict Risk

The description is so vague that it provides no clear niche. Without knowing what the skill does, it could conflict with any ops, CI/CD, or GitHub-related skill, and Claude would have no basis for choosing it over alternatives.

1 / 3

Total

4

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/claude-flow
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.