CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-ops-cicd-github

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

55

1.00x
Quality

30%

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

The canonical home for this skill is agent-ops-cicd-github in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

32%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.

The body front-loads a large, non-instructional YAML configuration block (with corrupted path separators) before reaching the actual guidance, which is brief and lacks a sequenced workflow. The single workflow example is concrete but syntactically broken, and there are no references or bundle files to offload detail.

Suggestions

Remove or relocate the inlined agent-config YAML block out of the SKILL.md body; keep only the instructional markdown so the file is a lean overview.

Fix the corrupted separators in the workflow example ("actions$checkout@v4" -> "actions/checkout@v4", ".github$workflows" -> ".github/workflows") so it is copy-paste executable.

Add a sequenced pipeline-creation workflow with explicit validation checkpoints (e.g. lint with actionlint, dry-run, then deploy) given the destructive production-deployment scope.

DimensionReasoningScore

Conciseness

The body opens with ~115 lines of inlined agent configuration metadata (triggers, constraints, hooks, integration) that is not instructional and heavily pads the file; the markdown section is reasonable but the config dump is noticeably verbose padding. It is above a 1 because the instruction portion itself is not explaining basic concepts.

2 / 5

Actionability

A concrete GitHub Actions workflow example is provided, but it is corrupted ("actions$checkout@v4", "actions$setup-node@v4" use "$" instead of "/") so it is not directly copy-pasteable; the responsibilities and best-practices lists remain high-level. This matches some concrete but incomplete guidance.

3 / 5

Workflow Clarity

There is no sequenced multi-step process for Claude to follow; the content is unordered lists of responsibilities and best practices with no checkpoints, and the skill touches destructive operations (production deployment workflows) without real validation, which would cap it at 3 anyway. A rough sense of tasks exists but steps and validation are absent.

2 / 5

Progressive Disclosure

No bundle files exist and the large YAML configuration block is inlined directly in the body rather than split out; content that clearly belongs in a separate file is inlined with minimal navigation structure. The markdown section has headers, but the inlined config dump pulls organization down.

2 / 5

Total

9

/

20

Passed

Description

28%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.

The description is an auto-generated placeholder that names the skill's domain but provides no concrete actions, no natural trigger phrases, and no Use-when guidance. It is barely above the vague floor and fails to tell Claude when to invoke it.

Suggestions

Rewrite the description to list concrete actions, e.g. "Creates and optimizes GitHub Actions workflows for build, test, and deployment pipelines."

Add an explicit trigger clause: "Use when the user asks to set up GitHub Actions, CI/CD pipelines, or .github/workflows files."

Include natural trigger terms users would actually say ("github actions", "ci/cd pipeline", "workflow", "deployment") rather than only the slug and invocation syntax.

DimensionReasoningScore

Specificity

The description only names the domain ("ops-cicd-github") with zero concrete actions; it is the auto-generated placeholder "Agent skill for ops-cicd-github - invoke with $agent-ops-cicd-github", which names the domain but gives no actionable verbs. It is above a 1 because it does identify the domain, but lacks any listed actions.

2 / 5

Completeness

It offers only a vague "what" ("Agent skill for ops-cicd-github") and entirely lacks a "when"/Use-when clause, matching the anchor for a vague what with no when; the missing trigger guidance would cap it at 3 even if the what were stronger.

2 / 5

Trigger Term Quality

It contains only the slug "ops-cicd-github" and the invocation syntax "$agent-ops-cicd-github"; none of the natural phrases a user would say ("github actions", "CI/CD pipeline", "workflow") appear, so it sits just above the no-keywords floor.

2 / 5

Distinctiveness Conflict Risk

The slug "ops-cicd-github" scopes it to a GitHub CI/CD niche, but the description text itself is a generic templated placeholder that could still overlap with sibling ops-* skills, so it is only somewhat specific.

3 / 5

Total

9

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
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.