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 Action

ASecurity

Update one named GitHub Action to its current version — verify the tag exists, research the upgrade, and commit it with release links

3 stars
0 votes
0 copies
0 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-action --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Github Actions Update Action?

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

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

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-action
description: >-
  Update one named GitHub Action to its current version — verify the tag
  exists, research the upgrade, and commit it with release links
disable-model-invocation: true
allowed-tools: ["Bash", "Read", "Grep", "Glob", "Edit", "WebSearch", "WebFetch", "AskUserQuestion"]
metadata:
  argument-hint: "<owner/action> [target version] [--repo <path|slug>...] [--pr] [--no-push]"
  source: "plugins/github-actions/skills/update-action/SKILL.md"
---

# Update One GitHub Action

Take a single action — `actions/checkout`, `astral-sh/setup-uv`,
whatever the user names — from whatever each repository currently pins
to its current version, with one commit per repository explaining the
upgrade.

Read `references/action-pinning.md` first; it
defines how to inventory pins, verify a target tag exists, dereference
annotated tags, and choose the pin shape. Read
`references/dependabot-closeout.md` for the
close-out and CI-attribution rules.

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)"
```

Current pins for all actions 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)"
```

## Procedure

### 1. Identify the action and the scope

The action comes from the argument. Without one, ask via
`ask-user-choice`, offering the out-of-date pins from the context block
above.

Scope defaults to the current repository. `--repo` may be repeated to
name others by path or slug. Exclude forks unless the user insists —
ownership is not the same as authorship.

### 2. Inventory the current pins

Read every `uses:` line naming this action from each repository's
default branch, per the pinning reference. Note the pin shape per
repository: a major float, an exact patch, or a commit SHA with a
version comment.

### 3. Resolve and verify the target

Resolve the latest version, or take the one the user named. Choose the
target that preserves each repository's existing shape, then confirm
the tag exists and gate on exit status. Stop here if it does not
resolve, and report the shapes that are available instead.

### 4. Research the upgrade

Collect every major release between the oldest pin in scope and the
target, each with a verified release URL, plus the breaking changes.
Then check those claims against the actual workflows — the gates
section of the pinning reference lists the recurring ones.

### 5. Commit

One commit per repository. Subject and body follow the project's own
commit conventions from AGENTS.md or CLAUDE.md; the body says what
changed upstream, what it means for that repository, and links every
major release in the span. Never cite a dependabot pull request.

Push unless `--no-push`. With `--pr`, branch and open a pull request
instead of committing to the default branch.

### 6. Verify and close out

Watch CI. Attribute any failure before blaming the bump. Close any
dependabot pull request for this action by citing the commit that
superseded it.

## Rules

- Never write a version string whose tag has not been confirmed to
  exist.
- One commit per repository, for this action only — no bundling with
  unrelated bumps.
- Preserve each repository's pin shape; move a SHA pin's trailing
  version comment along with the SHA.
- A commit body may not carry a claim that is false for the repository
  it lands in.
- Bump the action; report unrelated breakage rather than fixing it.

## Output

Open with a one-line hero (`✓ <action> <old> → <new> across N repos`
or `⚠ Blocked: <reason>`), then exactly these sections:

1. `## Target` — resolved version, evidence the tag exists, and the
   pin shape chosen per repository.
2. `## Upgrade` — what changed between the pins in scope and the
   target, with release links, and which repositories the breaking
   changes actually reach.
3. `## Commits` — one line per repository: commit subject and whether
   it was pushed, or why it was skipped.
4. `## Close-out` — CI result and any dependabot pull requests closed,
   with the commit each cited.

End with an `ask-user-choice` panel offering next steps (for example:
update another action, run the full audit, 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 →