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

Build

ASecurity

Build, test, and run the service locally. This is the local development loop — no platform deployment happens here.

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

Works with

mcp

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Build?

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

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

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

Download with Pro
Files
SKILL.md
---
name: build
description: "Build, test, and run the service locally. This is the local development loop — no platform deployment happens here."
---

## User Input

You **MUST** consider the user input before proceeding (if not empty).

## Purpose

This command is the **local development loop**. It compiles, tests, and runs
the service locally so you can iterate quickly. No Docker images are built,
no containers are pushed, no platform deployments happen. When the service
works locally and you're ready to ship, hand off to `/akka:deploy`.

## Outline

1. **Compile**: Use the `akka_maven_compile` MCP tool to compile the project.
   If compilation fails, the tool returns extracted `[ERROR]` lines — read them,
   report to the user, and fix the code before proceeding.

2. **Test**: Use the `akka_maven_test` MCP tool to run all tests. If tests fail:
   - The tool returns test failure details and `[ERROR]` lines
   - Report which tests failed and why
   - Suggest fixes based on the failure messages
   - Stop and hand off to `/akka:implement` for fixes

3. **Start local environment**: Use the `akka_local_start` MCP tool to start
   the local development environment in the background. **Tell the user** that
   the local runtime is starting — it provides gRPC proxying, service discovery,
   and trace collection on `localhost:9889`. This is idempotent — if already
   running, tell the user it is already active and report its status.

4. **Run the service**: Use `akka_local_run_service` to start the service
   locally. This tool compiles first (catching errors immediately), then runs
   `mvn exec:java` in the background. **Tell the user** the service is
   launching against the local runtime.
   - Pass the `environment` parameter to set additional environment variables
     (e.g. `{"LOG_LEVEL": "DEBUG", "DB_HOST": "localhost"}`). These are merged
     with the current environment — useful for config overrides, debug flags,
     or connecting to external services during local development.

5. **Verify**: Use `akka_local_status` to confirm the service registered.
   Use `akka_local_logs` with `source: "service"` to check for runtime errors.
   Test endpoints through the local proxy (`localhost:9889`). **Tell the user**
   the service endpoint URL and whether it started successfully.

6. **Report**: Summarize local build results:
   - Compilation: pass/fail
   - Tests: N passed, M failed
   - Local service: running/failed (with endpoint URLs via local proxy)
   - Next step: inspect with `/akka:inspect`, iterate with `/akka:implement`,
     or ship with `/akka:deploy`

## Error Handling

When any step fails:
1. **Read the error carefully** — `akka_local_run_service` returns Maven `[ERROR]` lines when compilation fails. Don't guess — read the actual error.
2. **Tell the user** what failed and the specific error message before attempting a fix.
3. **Fix the code** based on the error, then retry from the failed step (not from the beginning).
4. **Check service logs** — use `akka_local_logs` with `source: "service"` to read Maven/application output if the service crashes after starting.
5. **Don't retry blindly** — if the same error persists after one fix attempt, stop and ask the user for guidance.

Common Maven errors and what to do:
- `cannot find symbol` — wrong import or missing class. Check the constitution for correct annotations and imports.
- `package does not exist` — missing dependency in pom.xml or wrong package name.
- `port already in use` — another service is running. Use `akka_local_stop` then restart.

If `akka_local_start` reports a port conflict, ask the user whether to:
- Stop the process using that port, or
- Use a different port (pass the `port` parameter to `akka_local_start`)

## Key Rules

- This is LOCAL ONLY — do not build Docker images or deploy to the platform
- Always compile before testing
- Always test before running locally
- The local environment (akka_local_start) provides gRPC proxying and service discovery
- Report failures clearly with actionable fixes
- If the user explicitly asks to deploy, hand off to `/akka:deploy`

## Done When

- [ ] `akka_maven_compile` returned success — no `[ERROR]` lines remain unaddressed.
- [ ] `akka_maven_test` completed and every reported failure was either fixed or explicitly handed off to `/akka:implement`.
- [ ] `akka_local_start` reports the local runtime active on `localhost:9889` (idempotent — already-running is fine).
- [ ] The service was launched via `akka_local_run_service`; any `environment` overrides requested by the user were passed through.
- [ ] `akka_local_status` confirms the service registered, and `akka_local_logs` (`source: "service"`) shows no unhandled startup errors.
- [ ] The report summarizes compilation (pass/fail), tests (N passed, M failed), local service status with endpoint URL through the local proxy, and the next-step recommendation (`/akka:inspect` to inspect, `/akka:implement` to iterate, or `/akka:deploy` to ship).
- [ ] NO Docker image was built and NO platform deploy was attempted — this stayed strictly local.

Attribution

akkaakka
View sourceMore from akka →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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 →