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

Apex Github Operations

ASecurity

**WORKFLOW SKILL** — Full GitHub contribution lifecycle: branches, conventional commits, issues, PRs, Actions, releases. gh CLI-first with MCP fallback. WHEN: "commit", "push", "open PR", "create branch", "create issue", "cut release", "GitHub operation". DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code, architecture decisions. INVOKES: gh CLI (primary), GitHub MCP (fallback).

216 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentsgoexpressazureterraformgitapi

Works with

cliapimcp

Security Analysis

A100/100

Pro scans all 8 files and shows the line behind each finding

Scanned 9/24/2026

$npx -y skills add jonathan-vella/apex --skill apex-github-operations --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Apex Github Operations?

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

Security grade badge for Apex Github Operations
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jonathan-vella-apex-github-operations/badge)](https://www.skillsdirectory.com/skills/jonathan-vella-apex-github-operations)

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: apex-github-operations
user-invocable: true
disable-model-invocation: false
argument-hint: "GitHub operation and repository or branch scope"
description: '**WORKFLOW SKILL** — Full GitHub contribution lifecycle: branches, conventional commits, issues, PRs, Actions, releases. gh CLI-first with MCP fallback. WHEN: "commit", "push", "open PR", "create branch", "create issue", "cut release", "GitHub operation". DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code, architecture decisions. INVOKES: gh CLI (primary), GitHub MCP (fallback).'
license: MIT
metadata:
  author: apex
  version: "3.0"
  category: github
---

# GitHub Operations

Full contribution lifecycle — from branch creation to PR merge.
`gh` CLI preferred (always available in this dev container); MCP tools as
fallback for operations with no `gh` equivalent (rich PR review thread
management, bulk GraphQL queries).

## Steps

```text
1. Create branch (naming convention) →
2. Make changes →
3. Commit (conventional commits) →
4. Push (pre-push hooks validate branch + scope) →
5. Create PR (gh CLI) →
6. Review + Merge
```

## Rules

1. **Identify the operation** (issue, PR, search, Actions, release, etc.)
2. **Use `gh` CLI by default** — always available in this dev container; the more stable primitive
3. **Fall back to MCP only** when `gh` cannot satisfy the operation (rich PR review threads, bulk GraphQL, Copilot review requests)
4. **Validate branch name before any commit or PR** — `git rev-parse --abbrev-ref HEAD`; if invalid, stop and rename via `git branch -m`
5. **Conventional Commits are mandatory** — enforced by commitlint
6. **Devcontainer**: do not run `gh auth` unless explicitly asked to troubleshoot authentication.
  Use configured CLI credentials; never request tokens through chat or switch identity implicitly.
7. **Never skip hooks** (`--no-verify`) unless the user explicitly asks

## Branch Naming Quick Reference

| Type          | Prefixes                                                                             | File Scope                 |
| ------------- | ------------------------------------------------------------------------------------ | -------------------------- |
| Domain-scoped | `docs/`, `agents/`, `skills/`, `infra/`, `scripts/`, `instructions/`                 | Restricted to domain paths |
| Cross-cutting | `feat/`, `fix/`, `chore/`, `ci/`, `refactor/`, `perf/`, `test/`, `build/`, `revert/` | Any files                  |

For scope tables, validation commands, and enforcement layers, read
[`references/branch-strategy.md`](references/branch-strategy.md).

## Conventional Commits Quick Reference

Format: `<type>[optional scope]: <description>`.

Types: `feat`, `fix`, `docs`, `refactor`, `perf`, `test`, `build`, `ci`,
`chore`, `revert`.

Scopes: `agents`, `skills`, `instructions`, `bicep`, `terraform`, `mcp`,
`docs`, `scripts`.

For staging, breaking changes, and safety protocol, read
[`references/commit-conventions.md`](references/commit-conventions.md).

## Issues & Pull Requests

`gh issue ...` and `gh pr ...` are the default for both. MCP tools are
available as a fallback for operations the CLI does not cover well (rich
PR review threads, Copilot review requests, bulk GraphQL).

> **Default merge method**: `squash` unless the user specifies otherwise.

For tool tables, creation pre-flight checks, and the gh-vs-MCP decision
lattice, read [`references/issues-and-prs.md`](references/issues-and-prs.md).
For PR lifecycle states, auto-labels, and auto-merge conditions, read
[`references/smart-pr-flow.md`](references/smart-pr-flow.md).

## CLI Commands

For complete `gh` CLI commands covering repos, Actions, releases, secrets,
API, and auth, read
[`references/detailed-commands.md`](references/detailed-commands.md).

> **IMPORTANT**: `gh api -f` does not support object values. Use multiple
> `-f` flags with hierarchical keys and string values instead.

### Global Flags

| Flag                | Description                |
| ------------------- | -------------------------- |
| `--repo OWNER/REPO` | Target specific repository |
| `--json FIELDS`     | Output JSON with fields    |
| `--jq EXPRESSION`   | Filter JSON output         |
| `--web`             | Open in browser            |
| `--paginate`        | Fetch all pages            |

## Smart PR Flow Quick Reference

| Condition                   | Label Applied        |
| --------------------------- | -------------------- |
| CI passes                   | `infraops-ci-pass`   |
| CI fails                    | `infraops-needs-fix` |
| Review approved             | `infraops-reviewed`  |
| Auto-merge (all gates pass) | PR merged via MCP    |

Full state machine, watchdog pattern, and auto-merge gates in
[`references/smart-pr-flow.md`](references/smart-pr-flow.md).

## Reference Index

Operational procedures: [commit/push/PR](references/git-commit.md) and
[sensei-free PR](references/merge-sensei-free-pr.md). The manual Host entrypoint
is [apex-host-git-commit](../apex-host-git-commit/SKILL.md); it requires explicit
owner/model selection and does not change the Local slash name.

| Reference          | File                               | Content                                             |
| ------------------ | ---------------------------------- | --------------------------------------------------- |
| Branch Strategy    | `references/branch-strategy.md`    | Naming convention, scope tables, enforcement layers |
| Commit Conventions | `references/commit-conventions.md` | Format, types, staging workflow, safety protocol    |
| Issues & PRs       | `references/issues-and-prs.md`     | gh-vs-MCP decision lattice, tool tables, pre-flight |
| Smart PR Flow      | `references/smart-pr-flow.md`      | PR lifecycle states, auto-labels, auto-merge        |
| CLI Commands       | `references/detailed-commands.md`  | Repos, Actions, Releases, Secrets, API, Auth        |

Attribution

jonathan-vellajonathan-vella
View sourceSee grades on GitHubMore from jonathan-vella →
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 →