Codex and agent skills for repeatable work
Skills, commands, and rules that map well to Codex-style repeatable agent workflows across engineering, docs, deployment, and review.
Skills, commands, and rules that map well to Codex-style repeatable agent workflows across engineering, docs, deployment, and review.
Compared at a glance
The top 5 picks side by side on trust, install, platform support, and disclosed notes — full rationale for each below.
2 trust signals differ across this comparison (Package trust, Source provenance).
Next steps differ across picks — use the actions in the table below to copy install commands and source links per resource.
| Field | Expert automation-orchestration capability pack for designing safe, low-noise recurring Codex workflows with clear runbooks. Open dossier | Use the built-in /hooks menu to inspect Claude Code hooks and configure them in settings.json so shell commands run deterministically at lifecycle events like PreToolUse, PostToolUse, and Stop. Open dossier | Build intelligent CI/CD pipelines with GitHub Actions, AI-assisted workflow generation, automated testing, and deployment orchestration. Open dossier | Ship smart contracts on Base with secure deployment, verification, environment management, and production-readiness checklists. Open dossier | Expert code-review capability pack for deterministic PR audits, risk-ranked findings, and low-noise fix planning without SaaS lock-in. Open dossier |
|---|---|---|---|---|---|
| Next stepsDiffers | |||||
| Trust | |||||
| Review status | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed |
| Package trustDiffers | Package verified2026-04-11 | Package not verified | Package verified2025-10-16 | Package verified2026-04-10 | Package verified2026-04-11 |
| Source provenanceDiffers | No submission link | Source-backed | No submission link | No submission link | No submission link |
| Submitter | — | — | — | — | — |
| Install risk | Low risk | Review first | Low risk | Low risk | Low risk |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | — | — | — | — | |
| Category | skills | commands | skills | skills | skills |
| Source | First-party | Source-backed | First-party | First-party | First-party |
| Author | JSONbored | JSONbored | JSONbored | JSONbored | JSONbored |
| Added | 2026-04-11 | 2025-10-25 | 2025-10-16 | 2026-04-10 | 2026-04-11 |
| Platforms | |||||
| Harness | |||||
| Source repo | — | — | — | — | — |
| Safety notes | ✓Designs and runs automation workflows that can execute commands and trigger external actions; review each automation's permissions and triggers before enabling it. | ✓Hooks execute shell commands automatically with your user permissions whenever their event fires. A misconfigured or malicious hook can run destructive commands (file deletion, network calls, credential access) without further confirmation. PreToolUse hooks can allow or deny tool calls and PostToolUse hooks run after tools succeed; review hook commands before committing them to a shared .claude/settings.json so teammates do not inherit unexpected execution. Prefer `.claude/settings.json` for reviewed, team-shared hooks and `.claude/settings.local.json` for personal, gitignored hooks; use `disableAllHooks` to turn off user/project hooks when running untrusted code. | ✓Setup downloads and unzips a package, and generated workflows run build/test/deploy commands in CI with repository permissions; review workflow YAML and least-privilege the GITHUB_TOKEN before merging. | ✓Do not deploy or transact from generated contract code without independent review, tests, and a dry run; smart contract mistakes can be irreversible. Use local forks or testnets before mainnet and keep deployment wallets and RPC credentials least-privileged. | ✓Installs from a downloaded package and may run local commands or scaffold files as part of the workflow; review the package and any generated changes before applying. |
| Privacy notes | ✓Inputs can include source files, prompts, logs, account metadata, repository details, and operational context that may be sent to the configured AI model. Redact secrets, customer data, private URLs, credentials, and proprietary implementation details before sharing prompts, reports, or generated artifacts. | ✓Command and HTTP hooks receive event JSON on stdin including `session_id`, `transcript_path`, `cwd`, and tool input (such as file paths and Bash commands); a hook that forwards this data over the network can expose local file contents, paths, or command arguments to third parties. HTTP hooks can include headers with interpolated environment variables (restricted by `allowedEnvVars`); avoid embedding secrets in hook configuration that is committed to a repository. | ✓CI workflows read repository code and use secrets (API keys, deploy credentials, model keys); store them in GitHub Actions secrets, never in workflow files or logs, and review what third-party actions can access. | ✓Prompts and reports can include contract source, audit findings, addresses, deployment config, and transaction context. Never paste private keys, seed phrases, unreleased exploit details, customer wallet data, or privileged RPC credentials into prompts. | ✓Operates on your local project files and any context you share in the session; review what you expose before sharing — nothing is sent beyond the model unless a step calls an external service. |
| Prerequisites |
| — none listed |
|
|
|
| Install | | — | | | |
| Config | — | — | — | — | — |
| Citations | |||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
- 01
Codex Automations Orchestrator Capability Pack Skill
Plan and operate recurring agent automations with deterministic prompts, guardrails, and output contracts.
Level:expertType:capability-packVerified:validatedAdded 3mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutCodex Automations Orchestrator Capability Pack Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 02
Configure Claude Code Hooks with /hooks
Wire shell commands to PreToolUse, PostToolUse, Stop, and other events via the /hooks menu or settings.json.
Invocation:/hooksAdded 8mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutConfigure Claude Code Hooks with /hooks is included because it has safety notes present, privacy notes present, source-backed source posture.
Reach for insteadIf this will touch credentials, local files, or production systems, inspect the upstream source first.
- 03
GitHub Actions AI-Powered CI/CD Automation Skill
Build intelligent CI/CD pipelines with GitHub Actions, AI-assisted workflow generation, automated testing, and deployment orchestration.
Level:advancedType:generalVerified:draftAdded 9mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutGitHub Actions AI-Powered CI/CD Automation Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 04
Base L2 Smart Contract Launchpad Skill
Practical launch workflow for Base contracts from local build to verified deployment and post-launch operations.
Level:advancedType:generalVerified:draftAdded 3mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutBase L2 Smart Contract Launchpad Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 05
Code Review Automation Capability Pack Skill
Run a local, repeatable PR review loop with severity scoring, false-positive control, and fix-ready output.
Level:expertType:capability-packVerified:validatedAdded 3mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutCode Review Automation Capability Pack Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 06
Codex Plugin Creator Capability Pack Skill
Design and ship Codex plugins with clean manifests, bounded permissions, and reusable packaging standards.
Level:expertType:capability-packVerified:validatedAdded 3mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutCodex Plugin Creator Capability Pack Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 07
Google Workspace Gemini Automation Skill
Build practical Gemini + Workspace automations with safeguards, auditability, and business-ready output quality.
Level:advancedType:generalVerified:draftAdded 3mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutGoogle Workspace Gemini Automation Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 08
n8n Production Security Capability Pack Skill
Deep n8n production security skill for safe AI workflows, credential protection, and incident-ready operations.
Level:expertType:capability-packVerified:validatedAdded 3mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutn8n Production Security Capability Pack Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 09
Windsurf AI-Native Collaborative Development Skill
Master collaborative AI-assisted development with Windsurf IDE's Cascade AI, multi-file context awareness, and Flow patterns for team wor...
Level:advancedType:generalVerified:draftAdded 9mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutWindsurf AI-Native Collaborative Development Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 10
Create Claude Code Subagents with /agents
Use the built-in /agents command (or a .claude/agents Markdown file) to define specialized subagents with their own system prompt, tool restrictions, and model.
Invocation:/agentsAdded 8mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutCreate Claude Code Subagents with /agents is included because it has safety notes present, privacy notes present, source-backed source posture.
Reach for insteadIf this will touch credentials, local files, or production systems, inspect the upstream source first.
- 11
TDD Workflow Custom Command for Claude Code
A custom .claude/commands/tdd-workflow.md recipe that drives a red-green-refactor loop in Claude Code. Not a built-in command.
Invocation:Create .claude/commands/tdd-workflow.md, then run: /tdd-workflow add a slugify() helperAdded 8mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutTDD Workflow Custom Command for Claude Code is included because it has safety notes present, privacy notes present, source-backed source posture.
Reach for insteadIf this will touch credentials, local files, or production systems, inspect the upstream source first.
- 12
Docker Compose Production Blueprints Skill
Opinionated Docker Compose patterns for reliable production deployments and maintainable operations.
Level:advancedType:generalVerified:draftAdded 3mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutDocker Compose Production Blueprints Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 13
Playwright E2E Testing Automation Skill
Playwright auto-waits for elements before acting, isolates every test context, and targets Chromium, Firefox, and WebKit from a single cross-platform API...
Level:advancedType:generalVerified:draftAdded 9mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutPlaywright E2E Testing Automation Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 14
Unraid API Automation Operator Skill
Unraid-focused automation skill for agent-driven maintenance, observability, and repeatable operations.
Level:advancedType:generalVerified:draftAdded 3mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutUnraid API Automation Operator Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 15
Unraid API v2 Capability Pack Skill
Expert Unraid API skill with endpoint behavior, auth flows, error patterns, and production-safe automation guardrails.
Level:expertType:capability-packVerified:validatedAdded 3mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutUnraid API v2 Capability Pack Skill is included because it has maintainer-built package, safety notes present, privacy notes present, first-party source posture.
- 16
/review - Code Review Command for Claude Code
Comprehensive code review with security analysis, performance optimization, and best practices validation
Invocation:/review [options] <file_or_directory>Added 10mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cut/review - Code Review Command for Claude Code is included because it has safety notes present, privacy notes present, source-backed source posture.
Reach for insteadIf this will touch credentials, local files, or production systems, inspect the upstream source first.
- 17
/test-advanced - Advanced Test Planning Custom Command
Custom .claude/commands/test-advanced.md recipe for planning deeper, source-grounded test coverage without claiming a built-in Claude Code command.
Invocation:Create .claude/commands/test-advanced.md, then run: /test-advanced <file-or-function>Added 10mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cut/test-advanced - Advanced Test Planning Custom Command is included because it has safety notes present, privacy notes present, source-backed source posture.
Reach for insteadIf this will touch credentials, local files, or production systems, inspect the upstream source first.
- 18
AutoGen Multi-Agent Workflow for Claude
Orchestrate multi-agent workflows using Microsoft AutoGen v0.4 with role-based task delegation, conversation patterns, and collaborative...
Invocation:/autogen-workflow [options] <workflow_description>Added 9mo agoSafety ✓ Privacy ✓by JSONboredWhy it made the cutAutoGen Multi-Agent Workflow for Claude is included because it has safety notes present, privacy notes present, source-backed source posture.
Reach for insteadIf this will touch credentials, local files, or production systems, inspect the upstream source first.
Missing a pick? Propose an edit to this list — every change goes through the same review queue as new entries.
Suggest a pickGet the weekly brief
One calm read on Claude workflows. Sundays. No tracking pixels.
Unsubscribe any time. No tracking pixels. No partner blasts.