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

Devkit Create Framework

ASecurity

Comma-separated phase names

211 stars
0 votes
0 copies
2 views
Added 9/21/2026
ai-agentsgobashnodedocumentation

Works with

cli

Security Analysis

A100/100

Scanned 9/21/2026

$npx -y skills add jmagly/ai-writing-guide --skill devkit-create-framework --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Devkit Create Framework?

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

Security grade badge for Devkit Create Framework
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jmagly-devkit-create-framework-72387c1a/badge)](https://www.skillsdirectory.com/skills/jmagly-devkit-create-framework-72387c1a)

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
---
namespace: aiwg
name: devkit-create-framework
platforms: [all]
description: Comma-separated phase names
---

# Create AIWG Framework

Create a new AIWG framework with complete lifecycle structure.

## Process

### 1. Validate Framework Name

Check that `$ARGUMENTS` contains a valid framework name:
- Must be kebab-case (lowercase with hyphens)
- Must not conflict with existing frameworks

Check existing frameworks:
```bash
ls ~/.local/share/ai-writing-guide/agentic/code/frameworks/
```

### 2. Interactive Design (if --interactive)

If `--interactive` is specified, guide the user through framework design:

**Framework Purpose**:
> What lifecycle does this framework manage? (e.g., software development, marketing campaigns, legal cases)

**Target Audience**:
> Who will use this framework? (e.g., development teams, marketing departments, legal firms)

**Phase Structure**:
> What phases does this lifecycle include?
> Default: inception, elaboration, construction, transition
> Custom examples: discovery, analysis, synthesis, publication

**Agent Categories**:
> What types of roles are needed?
> - Analysis roles (analysts, researchers)
> - Design roles (architects, designers)
> - Implementation roles (developers, writers)
> - Quality roles (reviewers, testers)
> - Management roles (coordinators, managers)

**Template Categories**:
> What artifact types will be produced?
> - Planning documents
> - Requirements documents
> - Design documents
> - Implementation artifacts
> - Quality artifacts
> - Deployment artifacts

### 3. Execute Scaffolding

Run the CLI scaffolding tool:

```bash
node ~/.local/share/ai-writing-guide/tools/scaffolding/scaffold-framework.mjs \
  <name> \
  --description "<derived from interactive>" \
  --phases "<phase1,phase2,...>"
```

### 4. Post-Creation Guidance

After scaffolding, provide guidance on next steps:

**Immediate Actions**:
1. Review and customize `actors-and-templates.md`
2. Define your first agents for each phase
3. Create initial templates for key artifacts

**Agent Creation Priority**:
- Phase 1: Create 2-3 core agents per phase
- Phase 2: Add specialized agents as needed
- Phase 3: Add orchestration agents for workflows

**Command Creation Priority**:
- Phase 1: Create phase execution commands (`flow-<phase>`)
- Phase 2: Create transition commands (`flow-<phase>-to-<next>`)
- Phase 3: Create utility commands (status, validation)

**Template Creation Priority**:
- Phase 1: Create 2-3 key templates per phase
- Phase 2: Add specialized templates
- Phase 3: Create cross-cutting templates

### 5. Provide Reference Resources

Point to existing frameworks as examples:
- `sdlc-complete`: 53 agents, 48 commands, comprehensive lifecycle
- `media-marketing-kit`: 37 agents, marketing-focused lifecycle

Reference documentation:
- `docs/development/framework-creation-guide.md`
- `docs/development/devkit-overview.md`

## Output Format

```
Framework Created: <name>
─────────────────────────

Location: ~/.local/share/ai-writing-guide/agentic/code/frameworks/<name>/

Phases: <phase1> → <phase2> → ... → <phaseN>

Created:
  ✓ manifest.json
  ✓ README.md
  ✓ plan-act-<name>.md
  ✓ actors-and-templates.md
  ✓ agents/manifest.md
  ✓ commands/manifest.md
  ✓ templates/manifest.json
  ✓ flows/<phase>.md (for each phase)
  ✓ metrics/tracking-catalog.md
  ✓ config/models.json

Next Steps:
  1. Define actors: Edit actors-and-templates.md
  2. Add agents:    aiwg add-agent <name> --to <framework>
  3. Add commands:  aiwg add-command <name> --to <framework>
  4. Add templates: aiwg add-template <name> --to <framework> --category <phase>
  5. Deploy:        aiwg use <framework>
```

## Notes

- Framework creation is a significant undertaking (50+ agents typical)
- Study existing frameworks before creating new ones
- Use `--interactive` for guided design process
- Start small and iterate (core agents first, then expand)

## References

- @$AIWG_ROOT/${CLAUDE_PLUGIN_ROOT}/README.md — aiwg-dev addon overview
- @$AIWG_ROOT/docs/extensions/overview.md — Extension system architecture
- @$AIWG_ROOT/docs/cli-reference.md — CLI reference including scaffold-framework command
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/README.md — SDLC framework as reference implementation
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/god-session.md — Scope guidelines for agent design within frameworks

Attribution

jmaglyjmagly
View sourceSee grades on GitHubMore from jmagly →
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', ...

698621 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 →