GitHub Actions Workflow Rules Agent Skill

Create, edit, audit, and speed up GitHub Actions workflows using Bret Fisher's opinionated DevOps rules.

Context cost
18.9k tokensestimated from the bundle, loaded when it triggers
Bundle
8 files · 96.1 kB3 scripts among them — read before you run
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Create, edit, audit, and speed up GitHub Actions workflows using Bret Fisher's opinionated DevOps rules. Use it when the user asks to create a workflow or CI/CD pipeline, edit or add a job to an existing `.github/workflows/*` file (even a one-line change), review or harden a workflow for security, speed up slow CI, publish a container image from CI, automate releases, or mentions GHA, action pinning, or findings from gasa, zizmor, poutine, pinact, or actionlint, even if they don't say "GitHub Actions".

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

devopsgithub
Filed under

Cloud & DevOps

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md13.0 kB · preview
--- name: github-actions-workflow-pro ---
6# GitHub Actions Workflow Rules
7
8Apply these defaults proactively to every workflow you touch, unless the repository has a clear conflicting convention or the user asks for a different tradeoff. The rules exist because a workflow runs arbitrary code with a token: security is built in from the first line, and speed is what keeps a workflow maintained.
9
10## Working Style
11
121. Inspect existing workflow files before editing so new changes match the repository's naming, trigger, and secret conventions.
132. Prefer the smallest correct change, and fix insecure or wasteful patterns in the code you are already touching.
143. Facts are yours to find (an action's SHA, its required permissions, whether a tool supports OIDC). Decisions are the user's (adding a manual trigger, choosing a registry, creating an environment): put each one to them and wait.
154. Use placeholders for secret names, environment names, package names, and cloud roles the repo does not reveal, and list every placeholder when you hand back.
16
17## Building a workflow
18
19- Infer from the repo: the runtime version from its version file (.nvmrc, .python-version, go.mod) or engines, the lint and test commands from its scripts.
20- Reusable workflows are named call-*.yaml or reusable-*.yaml.
21- Pin each third-party uses: with pinact, one -i '<action>' per action. An action you add: write @v<major> and run scripts/scan.sh pinact run --update --min-age 7 -i '<action>' <file>, because new code takes the newest release at least 7 days old. An action already on a tag (@v4): run scripts/scan.sh pinact run --min-age 7 -i '<action>' <file> without --update, because --update jumps to the newest major (v4 to v7) and a major bump is the user's decision; name a newer major as a question in the hand-back. The scope matters: a whole-file --update bumps lines that were already pinned, which the user did not ask for. An action already on a tag in a file you are editing gets pinned too, whatever "keep everything else" covers: the tag is the one line an attacker can move, so pin it and name it in the hand-back (see **pinned** below).
22- For a Docker build workflow, or a lint workflow in a repo with no linter of its own, offer a reusable workflow before writing a bespoke one and ask whether the user already has one: Bret's are <https://github.com/BretFisher/docker-build-workflow> and <https://github.com/BretFisher/super-linter-workflow>. A repo that already defines npm run lint or equivalent runs that.
23
24## Auditing an existing workflow
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md2,024 words
Files8
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈140
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
18,710
on trigger
The instruction body and 7 supporting files, read only when the skill fires.
9.4%
of a 200k window
Ten skills this size would take about 94% of the window before you open a file.
050k100k150k200k context window

18.9k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

8 files, 96.1 kB on disk. Mostly text — the instructions the model reads — with 3 scripts in it that your client would run only if the instructions tell it to.

  • SKILL.md13.0 kB
  • references/audit.md34.2 kB
  • references/parallel-steps.md5.8 kB
  • references/security.md16.7 kB
  • references/speed.md5.7 kB
  • scripts/run-stats.py15.7 kB
  • scripts/scan.sh2.4 kB
  • scripts/validate.sh2.6 kB
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 3 scripts beside the text, so the bundle is 8 files you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# GitHub Actions Workflow Rules · 18.9k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/github-actions-workflow-rules/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/github-actions-workflow-rules" ] && { [ ! -e .claude/skills/github-actions-workflow-rules ] || { mv .claude/skills/github-actions-workflow-rules "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/github-actions-workflow-rules" .claude/skills/ && echo "Installed .claude/skills/github-actions-workflow-rules"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add bretfisher/github-actions-workflow-rules

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/github-actions-workflow-rules/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/github-actions-workflow-rules/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/github-actions-workflow-rules" ] && { [ ! -e ~/.claude/skills/github-actions-workflow-rules ] || { mv ~/.claude/skills/github-actions-workflow-rules "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/github-actions-workflow-rules" ~/.claude/skills/ && echo "Installed ~/.claude/skills/github-actions-workflow-rules" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/github-actions-workflow-rules/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as github-actions-workflow-pro in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, github-actions-workflow-rules.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencebretfisher/github-actions-workflow-rules

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill