aiwg

Complete SDLC framework with 180+ specialized agents for software development lifecycle management.

116 skills · 10 commands · 99 agents

Core AIWG utilities for context regeneration and workspace management.

133 skills · 12 agents

Marketing automation framework with 37 specialized agents for campaign management.

34 skills · 38 agents

Research workflow framework with 9 specialized agents for discovery, acquisition, synthesis, citation management, GRADE quality assessment, and OAIS-compliant archival.

42 skills · 8 agents

Digital forensics and incident response framework with 14 specialized agents covering target profiling, evidence acquisition, log/memory/container/cloud analysis, IOC extraction, and reporting.

21 skills · 13 agents

Applied security framework for cryptographic primitive selection, chain-of-trust design, authentication factor analysis, supply-chain trust, and physical-threat modeling. Complements OWASP-style application audits.

28 skills · 2 agents

Media archive management framework with 7 specialized agents for source discovery, acquisition (yt-dlp / Internet Archive / Bandcamp), quality assessment, metadata tagging, and provenance tracking.

21 skills · 7 agents

Corpus-to-dataset pipeline for AI training data curation. Ingests sources, synthesizes examples, generates DPO/KTO preference pairs, applies decontamination, and exports to Alpaca/ShareGPT/ChatML/JSONL/Parquet with provenance. Optional Python runtime (aiwg-training CLI) for scale.

15 skills · 7 agents

Iterative AI coding loops with automatic recovery - iteration beats perfection

18 skills · 3 agents

Developer tooling for building AIWG itself and AIWG addons/frameworks. Not for end users — install explicitly with `aiwg use aiwg-dev`.

13 skills

Operational infrastructure framework with 12 specialized agents covering incident response, runbook execution, fleet inventory, certificate lifecycle, and disaster recovery planning.

1 skill · 12 agents

Evidence-bound test conformance, platform protocols, normalization transactions and research-guided testing workflows

9 skills · 3 agents

Tools, skills, and CLI extensions for designing and productionizing LLM inference pipelines. Pattern-guided, slim by default, eval-first.

7 skills · 4 agents

RLM-inspired recursive context decomposition for processing arbitrarily large codebases and document corpora through programmatic sub-agent delegation

8 skills · 1 agent

Documentation intelligence addon for scraping, extraction, analysis, and generated-docs auditing.

6 skills · 1 agent

Tools for reading, parsing, validating, and executing OpenProse programs from AIWG workflows

7 skills

Structured YAML manifests for reproducible, agent-driven software installation across platforms. Scripts are the primary artifact; agentic instructions handle adaptation and recovery.

4 skills · 1 agent

Topology-agnostic semantic memory operations: ingest, lint, query-capture, and structured event logging. Consumers declare a memory topology in their manifest.json; kernel skills read that contract to parameterize behavior.

5 skills

Build, enhance, validate, and package Claude skills end-to-end. Coordinates skill-builder, skill-enhancer, quality-checker, and skill-packager via the skill-architect agent.

4 skills · 1 agent

Voice profile system for consistent, authentic writing.

5 skills

Drive a real, user-installed Chromium-derived browser from an AIWG agent. Wraps @playwright/mcp with a setup wizard, health-check doctor, allow-list enforcement, and an opinionated agent persona that respects authorization and audit boundaries.

3 skills · 1 agent

Writing quality validation and AI pattern detection.

1 skill · 3 agents

Color palette selection and review tooling with color theory fundamentals, current trend research, and accessibility analysis.

3 skills

Knowledge-base / wiki framework with skills for ingestion, query, and lint. Build a structured, citable corpus with cross-references and concept pages.

3 skills

Design-time and audit-time workflows for Twelve-Factor and modern 12+ Factor cloud-native application practices.

2 skills · 1 agent

Agent-executable acceptance testing via MCP connections — generate, execute, and report on UAT plans that validate MCP tool surfaces.

1 skill · 2 agents

Persistent daemon session capabilities: Concierge front-end, session memory, scheduler integration

1 skill · 1 agent

Training-free prompting technique that improves output diversity by 1.6-2.1x through verbalized probability distributions, addressing RLHF mode collapse

1 skill · 1 agent

Human-in-the-loop (HITL) gate definitions for agent operations. Provides reusable YAML gates for destructive-action authorization, false-positive override, and recovery escalation. Loaded by agent loops and orchestrators that need bounded human checkpoints.

1 skill

Automatic memory seed templates for AIWG projects

1 skill

Governed orchestration across AIWG line memory, semantic memory, and llm-wiki.

1 skill

Context curation and distractor filtering for production-grade agent reliability

1 agent

MCP server bridging Claude Code to Factory Droid for batch operations and automated fixes

1 skill

Bounded iteration control for autonomous issue-to-code implementation

1 skill

Bounded, plain-text project memory with least-recently-used retention.

1 skill

LLM-maintained markdown wiki that compounds as sources are ingested. Thin topology declaration on the semantic memory kernel — ships schema profiles and page templates, no custom mechanics.

1 skill

Tasteful prompt to encourage users to star the repository after successful command completion

1 skill

Validation Complete for AIWG

1 skill

Automated evaluation framework for agent quality, based on KAMI benchmark methodology and ReAct patterns

Claude Code hooks for workflow tracing and observability.