ai-context-engineering-for-qa: Skill for Claude Code

.claude/skills/workflow-expert/SKILL.md

workflow-expert is a skill for Claude Code from vlad-ryzhkov/ai-context-engineering-for-qa. It costs 58 tokens per session (4,817 once invoked), scanned A, original, Unlicense.

A skill for reviewing, diagnosing, fixing, securing, and improving GitHub Actions workflows. GitHub Actions is GitHub’s system for automatically running checks and deployment jobs.

In plain words
What is it for?
Use it to audit or modify GitHub Actions files, investigate failed workflows, pin action versions, adjust permissions, or improve workflow speed and structure. It is not intended for Jenkins, GitLab CI, or unrelated YAML files.
Why use it?
It helps identify broken workflow syntax, security weaknesses, outdated actions, and avoidable performance or cost problems. It also stops for user guidance after the same validation failure occurs twice.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is vlad-ryzhkov/ai-context-engineering-for-qa's own configuration. It tells Claude Code how to work on ai-context-engineering-for-qa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-context-engineering-for-qa configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is run: bash .github/scripts/deploy-check.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to vlad-ryzhkov/ai-context-engineering-for-qa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vlad-ryzhkov/ai-context-engineering-for-qa/main/.claude/skills/workflow-expert/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vlad-ryzhkov/ai-context-engineering-for-qa

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for workflow-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/vlad-ryzhkov/ai-context-engineering-for-qa/workflow-expert/github.svg)](https://agentmods.dev/skills/vlad-ryzhkov/ai-context-engineering-for-qa/workflow-expert)
Your own site
<a href="https://agentmods.dev/skills/vlad-ryzhkov/ai-context-engineering-for-qa/workflow-expert"><img src="https://agentmods.dev/badge/skills/vlad-ryzhkov/ai-context-engineering-for-qa/workflow-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for workflow-expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/vlad-ryzhkov/ai-context-engineering-for-qa/workflow-expert"><img src="https://agentmods.dev/badge/skills/vlad-ryzhkov/ai-context-engineering-for-qa/workflow-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,817 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.04817
Opus 5 $0.00029 $0.02409
Sonnet 5 $0.00012 $0.00963
Haiku 4.5 $0.00006 $0.00482

Measured today against content hash 14d78546b12e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

workflow-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/workflow-expert/SKILL.md · 522 lines

How it starts

The opening of the file, as written. The whole thing — 522 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/workflow-expert — GitHub Actions Workflow Expert

SILENT MODE: Execute all analytical and generation phases silently. Do not output intermediate reasoning or conversational filler. Only the final SKILL COMPLETE block (or an explicit ESCALATION if blocked) goes to chat.

Loop Guard: If you encounter the same error or validation failure twice in a row, do NOT attempt a third blind fix. Output an ESCALATION block with the failure details and wait for user instruction.


When to Use

  • User asks to audit, review, or check GitHub Actions workflows for security/performance
  • User reports a broken or failing workflow and needs root-cause analysis
  • User requests a specific change to a workflow (add step, modify trigger, update action)
  • User wants to optimize workflow speed, cost, or architecture
  • User asks to pin action versions, fix deprecated syntax, or harden permissions

When NOT to Use

  • Non-GitHub-Actions CI systems (Jenkins, GitLab CI, CircleCI, Azure Pipelines)
  • Dockerfile optimization without workflow context
  • General YAML editing unrelated to GitHub Actions
  • Kubernetes manifests or Helm charts

Persona & Core Mindset

Principle Description
Security Champion Treat workflow configs as privileged infrastructure code. Every change is a potential attack surface.
Root Cause Driven Never apply band-aid fixes. Trace failures to their origin and fix structurally.
Evidence Based Every finding must reference a specific file, line, and rule. No speculative issues.
Minimal Blast Radius Prefer surgical edits over rewrites. Propagate changes through the call graph.
Zero Trust Inputs All user-controlled context variables (PR titles, issue bodies, branch names) are untrusted.
Deterministic Use <thinking> phase to plan before editing. Never guess action parameters.
Surgical Precision Never rewrite a file for one variable. Find the exact failure line, trace the data chain (caller → called), and change only what solves the problem. No debug echo unless requested.

Read the full file on GitHub · 522 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed · +5 lines 14d78546b12e
  2. 9d ago First seen · 517 lines · 58 tokens per session scan A 8edb69ef768a

Subscribe to this mod's changes

workflow-expert is a skill published in the GitHub repository vlad-ryzhkov/ai-context-engineering-for-qa (6 stars, last pushed today), licensed Unlicense. It adds 58 tokens to every session and 4,817 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.