Skill rating

Run the full Recursive Language Model pipeline — prep, fan out across chunks, and recursively synthesize until results fit one context window

Spawn sub-agent to process focused context and return structured result

Dispatch the same query to multiple subagents in parallel across chunks in a manifest and aggregate results with source provenance

Split a file into overlapping chunks suitable for parallel fanout processing and emit a manifest describing each chunk

Orchestrate a pragmatic npm supply-chain hardening pass: dependency-source audit, release-age gate, lifecycle-script review, trusted publishing, signed releases, SBOM, and user verification docs.

Capture and expand free-form research thoughts into wiki memory without requiring REF-* structure.

SBOM analysis, build pipeline forensics, and dependency verification covering package integrity, build reproducibility, and CI/CD pipeline tampering

Orchestrate autonomous issue-to-code implementation using existing tools and agents with bounded iteration

Simulate project outcomes with variable modeling, risk assessment, and resource optimization scenarios.

Compare API/ABI surfaces between refs, flag incompatible changes, and generate deprecation/changelog notes for library projects

Regenerate .windsurfrules for Windsurf with preserved team directives

Analyze team retrospectives for insights

Quick triage investigation following RFC 3227 volatility order

Generate summaries and literature notes from research papers

Regenerate .cursorrules for Cursor with preserved team directives

Generalized Linux incident response and forensic analysis covering Debian/Ubuntu, RHEL/CentOS/Rocky, and SUSE families

Package research artifacts for long-term archival

Build or rebuild the SDLC artifact index for agent-navigable discovery

Analyze overall project health and metrics

Audit and maintain harness memory through reviewed aiwg memory plans, with owner receipts, verification and recovery.

W3C PROV-O patterns for tracking media derivation chains and production history

Show research corpus health and statistics

Execute STRIDE threat modeling, vulnerability scanning, and security control validation with risk scoring

Interactive tuning of Verbalized Sampling diversity parameters with preset management and A/B comparison

Extract and enrich indicators of compromise

Regenerate OpenCode context file (.opencode/context.md) with AIWG framework content

Run a workflow multiple times and compare outputs to produce a similarity score and pass/fail verdict

Create a W3C PROV-compliant provenance record for an artifact

Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only

Regenerate AGENTS.md for Factory AI with hook file architecture

Pull the latest upstream AIWG updates into the user's fork and rebuild — preserves user customizations

Clean up .aiwg/working/ by promoting, archiving, or deleting temporary files

opustags and ffmpeg patterns for applying metadata to audio and video files

Regenerate AGENTS.md with vendor-neutral content for multi-platform support

Create a new AIWG extension (framework expansion pack) with AI-guided setup

Regenerate Codex context file (CODEX.md or ~/.codex/instructions.md) with AIWG framework content

Regenerate WARP.md for Warp Terminal with preserved team directives

Audit codebase for dead code, unused exports, orphaned files, and stale manifests

Generate MCP environment definition for MCPSmith with Docker and Node.js verification

Generate system definition file for ToolSmith with tested OS commands

Enable agent loops to learn from similar past tasks and share patterns across loops

Mark an issue as complete with comprehensive summary and verification

Create a new AIWG addon with AI-guided setup

Rebuild and redeploy AIWG from local customization source — makes recent edits live

Migrate the .aiwg/ directory from single-framework layout to the multi-framework layout with an automatic backup

Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions

Reorganize and update .aiwg/ documentation to reflect current project reality

Create a Product Requirements Document (PRD) for a product feature

Evaluate architectural decisions using Tree of Thoughts exploration

Execute a `setup.aiwg.io/v1` SetupManifest, performing cross-platform installati