Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Akka Sdd

ASecurity

Use when working on Akka SDK projects, Akka Spec-Driven Development, or when the user asks for workflows equivalent to Claude commands such as /akka:specify, /akka:plan, /akka:tasks, /akka:implement, /akka:review, /akka:build, /akka:deploy, /akka:analyze, /akka:clarify, /akka:checklist, or /akka:issues.

7 stars
0 votes
0 copies
1 views
Added 9/20/2026
ai-agentsshelldocumentation

Works with

climcp

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add akka/ai-marketplace --skill akka-sdd --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Akka Sdd?

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

Security grade badge for Akka Sdd
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/akka-akka-sdd/badge)](https://www.skillsdirectory.com/skills/akka-akka-sdd)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: akka-sdd
description: Use when working on Akka SDK projects, Akka Spec-Driven Development, or when the user asks for workflows equivalent to Claude commands such as /akka:specify, /akka:plan, /akka:tasks, /akka:implement, /akka:review, /akka:build, /akka:deploy, /akka:analyze, /akka:clarify, /akka:checklist, or /akka:issues.
---

# Akka Spec-Driven Development For Codex

Use the Akka CLI MCP server whenever its tools are available. The plugin registers the server with:

```json
{
  "command": "akka",
  "args": ["mcp", "serve", "--disable-prompt"]
}
```

Before using an Akka SDD workflow, verify the MCP server is available by listing MCP tools/resources. If Akka MCP tools are unavailable, tell the user to confirm the plugin is installed/enabled and that `akka mcp serve --disable-prompt` starts from the repo root.

## Project Rules

- Follow the repository `AGENTS.md` instructions for Akka SDK component architecture, package layout, tests, and documentation reads.
- Prefer Akka MCP tools for spec files, task generation, branch helpers, and Akka CLI operations.
- Use local `akka-context/` documentation before coding first-time Akka component types.
- For CLI commands run directly from Codex, use non-interactive flags where available: `--disable-prompt`, `--output json`, and explicit context/config options when relevant.

## Claude Command Mapping

- `/akka.specify`: create or update a feature specification. Use Akka MCP spec tools first, then create or update `specs/<number>-<short-name>/spec.md`.
- `/akka.plan`: create the technical plan from the selected spec. Use Akka MCP template/spec tools, then produce `plan.md`, `research.md`, `data-model.md`, contracts, and quickstart artifacts as needed.
- `/akka.tasks`: derive actionable tasks from the plan and write `tasks.md`.
- `/akka.implement`: execute `tasks.md` on the feature branch, preserving user changes and verifying with Maven tests.
- `/akka.review`: review implementation against the spec, plan, tasks, and Akka SDK rules.
- `/akka.build`: build, test, and run the Akka service locally.
- `/akka.deploy`: use Akka CLI deployment commands only after confirming target project, region, service name, and credentials.
- `/akka.analyze`: inspect an existing Akka project and report architecture, components, gaps, and risks.
- `/akka.clarify`: identify unresolved requirements and update the spec only after user answers.
- `/akka.checklist`: create or update quality checklists for the active spec.
- `/akka.issues`: summarize open spec, plan, task, build, and review issues.

## MCP Usage Expectations

When MCP tools exist, prefer typed MCP calls over shelling out to `akka` for the same operation. When shelling out is required:

```powershell
akka --disable-prompt --output json <command>
```

Use text output only when the user asks to see human-readable CLI output.

Attribution

akkaakka
View sourceMore from akka →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

693621 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →