Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Github Actions Update Actions

ASecurity

Use when updating every outdated GitHub Action across one repository or a fleet, one researched change at a time.

3 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsbashgit

Works with

claude code

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 9/19/2026

$npx -y skills add tony/skills --skill github-actions-update-actions --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Github Actions Update Actions?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Github Actions Update Actions
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tony-github-actions-update-actions/badge)](https://www.skillsdirectory.com/skills/tony-github-actions-update-actions)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: github-actions-update-actions
description: >-
  Use when updating every outdated GitHub Action across one repository or a
  fleet, one researched change at a time.
disable-model-invocation: true
allowed-tools: ["Bash", "Read", "Grep", "Glob", "Edit", "WebSearch", "WebFetch", "Task", "AskUserQuestion"]
metadata:
  argument-hint: "[--root <dir>] [--owner <name>...] [--repo <path|slug>...] [--audit-only] [--pr] [--no-push]"
  source: "plugins/github-actions/skills/update-actions/SKILL.md"
---

# Update All GitHub Actions

Audit every `uses:` pin across the repositories in scope, then bring
the out-of-date ones current — one commit per repository and action,
each justified against the vendor's own release notes.

Use the `github-actions-bumping-github-actions` skill for
the phase structure. It reads the same two references this command
does, so the audit and the single-action path cannot drift:
`references/action-pinning.md` and
`references/dependabot-closeout.md`.

For a single named action, use the `github-actions-update-action` skill instead.

User arguments: $ARGUMENTS

## Context

Repository — run this command and read the output:

```bash
git remote get-url origin 2>/dev/null || echo "(not a git repository)"
```

Default branch — run this command and read the output:

```bash
git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null || echo "(unknown)"
```

Pins on this branch — run this command and read the output:

```bash
git grep -hoE 'uses:[[:space:]]*[^[:space:]]+' "$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null || echo HEAD)" -- '.github/workflows/*' '.github/actions/*' 2>/dev/null | sed -E 's/uses:[[:space:]]*//' | sort | uniq -c | sort -rn || echo "(no workflows found)"
```

Open dependabot pull requests here — run this command and read the output:

```bash
gh pr list --author app/dependabot --state open --limit 50 --json number,title --jq '.[] | "#\(.number) \(.title)"' 2>/dev/null || echo "(none, or gh unavailable)"
```

## Procedure

Follow the skill's phases. This command supplies the scope and the
fan-out.

### 1. Scope

Default scope is the current repository. `--root` audits every git
repository beneath a directory; `--owner` keeps only those whose remote
belongs to the given accounts or organisations; `--repo` names
individual ones. Exclude forks — check the fork flag, not the owner
name — and say which were excluded.

### 2. Inventory and verify

Run the skill's inventory and verification phases across the whole
scope before touching anything. Every target tag is confirmed to exist
first; a dangling ref written fleet-wide is the expensive failure this
sequencing prevents.

### 3. Research, one chain per distinct upgrade

Group the work by upgrade chain rather than by repository — twenty
repositories moving `actions/checkout` from the same major share one
piece of research. Dispatch a subagent per chain where the host
supports it. Validate every release URL before it reaches a commit
message.

### 4. Orchestration plan

Present the plan the skill defines and wait for approval. With
`--audit-only`, stop here and report; nothing is written.

### 5. Commit and push

One commit per repository and action. Work through repositories one at
a time, pushing as each completes, so an interrupted run resumes
cleanly. Repositories parked on a feature branch get a throwaway
worktree based on the remote default branch.

### 6. Verify and close out

Watch CI per repository. Attribute failures before blaming the bumps.
Close every dependabot pull request whose action was bumped, citing the
commit that superseded it; close as obsolete any whose action no longer
appears in a workflow.

## Rules

- No version string is written before its tag is confirmed to exist.
- One commit per repository and action — never bundle actions.
- Commit messages never cite dependabot; the pull request cites the
  commit.
- A fleet-wide claim is verified per repository before it enters that
  repository's commit body.
- Report unrelated breakage; fix it only when a bump caused it.
- Forks and upstream projects are out of scope.

## Output

Open with a one-line hero (`✓ N commits across M repos` or
`⚠ Audit only: N pins out of date`), then exactly these sections:

1. `## Audit` — every action in scope with its current pins and the
   latest version, and what was excluded as fork, upstream, or already
   current.
2. `## Upgrades` — one entry per distinct chain: what changed, release
   links, and which repositories the breaking changes reach.
3. `## Commits` — per repository, the commits made and whether they
   were pushed.
4. `## Close-out` — CI results, dependabot pull requests closed with
   the commit each cited, and any failure shown to predate the bumps.
5. `## Drift` — repositories with no dependabot configuration, and
   actions pinned to a moving branch.

End with an `ask-user-choice` panel offering next steps (for example:
add dependabot configuration to the repos lacking it, pin the moving
branches, stop here) — skip the panel only in plan mode.


## Portability notes

- `ask-user-choice` — present the listed options and wait for the user to pick one. Hosts with a structured multiple-choice tool (Claude Code's `AskUserQuestion`) should use it; otherwise print a numbered list and wait for a numbered reply. Never proceed on an assumed answer.
- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.
- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.

Attribution

tonytony
View sourceSee grades on GitHubMore from tony →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →