# Structure AI Project Workflows

AI-assisted projects can lose context across sessions and tasks. This skill provides lightweight memory files, mini planning, and local log helpers to keep work traceable.

## Install

```bash
npx skillstore add carl-312/ai-architect-lite
```

## Metadata

- - Slug: carl-312-ai-architect-lite
- - Version: 1.0.0
- - Author: Carl-312
- - GitHub username: Carl-312
- - License: MIT
- - Repository: https://github.com/Carl-312/devlog-starter/tree/main/
- - Ref: main
- - Supported tools: Claude, Codex, Claude Code
- - Risk level: medium
- - Risk factors: scripts, filesystem, external\_commands
- - Quality score: 50
- - Quality tier: warning
- - Public page: https://skillstore.pages.dev/skills/carl-312-ai-architect-lite
- - Manifest: https://skillstore.pages.dev/api/skills/carl-312-ai-architect-lite/manifest

## Capabilities

- Defines a lightweight .ai\_context workflow for active task tracking.
- Provides an append-only development log template for project work.
- Includes a local Python helper to append structured log entries.
- Includes a local Python helper to generate mini execution plans.
- Documents slash-first dispatch and manifest-based workflow conventions.
- Provides bilingual English and Chinese usage documentation.

## Use Cases

- Bootstrap a small AI-assisted project: Create a simple active task file and use a mini plan before editing project files.
- Keep session handoffs readable: Record decisions, changes, outcomes, and next steps in a consistent local log.
- Port a lightweight workflow pattern: Adapt the AI Architect memory and dispatch pattern without adopting a larger framework.

## Prompt Templates

### Create a mini plan

```
Use AI Architect Lite to create a short plan for this goal: [goal]. Include constraints, three steps, and validation.
```

### Initialize task context

```
Set up the lightweight .ai_context active task workflow for this repository. Explain each file change before making it.
```

### Append a development log

```
Add a structured development log entry for this work: [summary]. Include changes, outcome, and next step.
```

### Audit workflow readiness

```
Review this repository for AI Architect Lite readiness. Check active task context, logging practices, manifest usage, and safety gaps.
```

## Limitations

- Does not implement a full project management system.
- Does not synchronize logs to remote services or databases.
- Requires users to review file paths before running local helper scripts.
- Does not validate user-provided log text for sensitive data.

## Best Practices

- Review the target path before running either helper script.
- Keep active task notes concise and free of secrets.
- Record validation results after each meaningful change.

## Anti Patterns

- Do not store API keys, credentials, or private tokens in .ai\_context files.
- Do not run helper scripts with elevated privileges unless required and reviewed.
- Do not treat generated plans as a substitute for testing.

## Security Audit

- - Safe to publish: true
- - Audited at: 2026-06-28T20:29:39.709\+00:00
- - Summary: Static analysis reported many high-risk patterns, but most are false positives from Markdown backticks, documentation examples, Chinese text entropy, and security guidance that mentions secrets. No prompt injection, network exfiltration, shell spawning, or credential access was found. The confirmed risk is local filesystem modification through bundled helper scripts, which is legitimate for this workflow but should be disclosed to users.

## Stats

- - Views: 273
- - Downloads: 5
- - Favorites: 1
- - Popularity score: 0