CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-ops-cicd-github

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

48

1.00x

Quality

18%

Does it follow best practices?

Impact

100%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

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

Evaluation results

100%

Node.js API Service CI Pipeline Setup

Node.js CI workflow with caching and versioning

Criteria
Without context
With context

checkout action version

100%

100%

setup-node action version

100%

100%

npm ci usage

100%

100%

dependency caching

100%

100%

ubuntu-latest runner

100%

100%

push trigger on main

100%

100%

pull_request trigger

100%

100%

no hardcoded secrets

100%

100%

Node.js version specified

100%

100%

test step present

100%

100%

pipeline-notes produced

100%

100%

Without context: $0.1702 · 45s · 12 turns · 19 in / 2,037 out tokens

With context: $0.4057 · 1m 14s · 23 turns · 285 in / 3,928 out tokens

100%

Cross-Version Compatibility Testing for a Python Library

Multi-environment matrix testing pipeline

Criteria
Without context
With context

matrix strategy used

100%

100%

all 4 versions covered

100%

100%

checkout action version

100%

100%

ubuntu-latest runner

100%

100%

dependency caching

100%

100%

push trigger

100%

100%

pull_request trigger

100%

100%

parallel jobs

100%

100%

no hardcoded secrets

100%

100%

ci-design.md produced

100%

100%

workflow file location

100%

100%

pytest run step

100%

100%

Without context: $0.3104 · 1m 23s · 20 turns · 27 in / 4,224 out tokens

With context: $0.3845 · 1m 21s · 22 turns · 139 in / 4,474 out tokens

100%

Production Deployment Pipeline for a Containerised Web Application

Secure deployment workflow with secret management

Criteria
Without context
With context

no hardcoded secrets

100%

100%

secrets syntax used

100%

100%

minimal GITHUB_TOKEN permissions

100%

100%

environment protection

100%

100%

checkout action version

100%

100%

ubuntu-latest runner

100%

100%

push trigger on main

100%

100%

build before deploy

100%

100%

security-notes produced

100%

100%

workflow file location

100%

100%

docker build step

100%

100%

Without context: $0.3201 · 1m 49s · 14 turns · 19 in / 6,127 out tokens

With context: $0.3976 · 1m 30s · 22 turns · 281 in / 4,938 out tokens

Repository
ruvnet/claude-flow
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.