Skill rating

Audit generated HTML, Markdown, crawler controls, model-readable docs, structured data, API specs, and URL-class drift from one local source graph.

Plan iterations, delegate to SDLC agents, and compile iteration status

Validate provenance records and chains for completeness and consistency

Verify all citations in a document against the research corpus

Comma-separated phase names

Comma-separated phase names

Steward-assisted prep for filing issues and PRs — environment capture, template selection, duplicate detection, delivery-policy compliance check

Author, validate, explain, dry-run, and inspect optional graph.flow.aiwg.io GraphPlaybooks over the AIWG Flow runtime substrate

Check a file for citation quality and GRADE compliance

Verify citations against the research corpus to prevent hallucinated references and enforce GRADE compliance

Generate comprehensive test suite for $ARGUMENTS following project testing conventions and best practices.

Perform comprehensive security assessment

Generate corpus-wide GRADE quality distribution report

Scaffold endurance, stress, and adversarial-input tests that reveal degradation rather than immediate crashes

Update project CLAUDE.md with AIWG framework context and configuration

Enable interactive design mode

Enable interactive design mode

Execute tests on generated code and iterate until passing

Show analytics and metrics from agent loop execution history

Extract cited decisions, requirements, risks, entities, and relationships from session history and review exact candidate versions before memory promotion

Configure and operate the Droid Bridge MCP integration that delegates authorized batch work to Factory Droid and exposes task monitoring.

Run a diversity-first premortem with bounded deep dives, blind plausibility and impact verification, and explicit provenance labels.

Configure AIWG automatic-memory seed templates for project overview, testing, debugging, and architecture knowledge, with provider compatibility guidance.

Retain and retrieve small durable project facts through a bounded, recency-ordered plain-text memory

Generate or complete intake forms (project-intake, solution-profile, option-matrix) with interactive questioning and optional guidance. INTENDED FOR SUBSTANTIAL NEW WORK — new addons, new frameworks,

Manage the AIWG skills registry by listing, searching, inspecting, installing, and publishing skills

Show status of RLM task tree execution

Show status of RLM task tree execution

Validate and ablate readable NLAH.md harness policy without executing ambiguous prose

Preflight issue bodies for prompt-injection and supply-chain risk before address-issues acts on them

Full multi-agent investigation workflow

Audit source-control organization settings for strong 2FA/MFA requirements across all committers

Review long-horizon obligations, stable cores, dependencies, replacement paths, stewardship, degradation, evidence, and meaning preservation

Automatically manage regression test baseline lifecycle triggered by releases, deployments, and quality gates

Build a safe strict-LCM or adaptive polyrhythmic FlowGraph for explicit multi-track reasoning.

Detect breaking changes in API contracts across REST, GraphQL, and gRPC interfaces with semver enforcement

Compare orchestration topologies on one task family using integrity-gated observations and coordination metrics

Generate forensic investigation report

Generate troubleshooting documentation

Orchestrate cross-team synchronization with dependency mapping, sync cadence, blocker escalation, integration planning, and cross-team demos

Benchmark compressed context against summary, direct retrieval, and provider-context baselines without enabling product integration

Patterns for acquiring content from Internet Archive and archival sources

Analyze gaps in research coverage

Update AGENTS.md with project-specific context for Factory AI based on codebase analysis

Change a governed schema with conservative compatibility analysis, consumer impact review, migration, and deprecation planning.

Review a schema or data-contract change for authority, correctness, compatibility, fixtures, security, and projection integrity.

Orchestrate systematic retrospective cycle with structured feedback collection, improvement tracking, and action item management

AIWG addons + extensions language map — categories, curated discover phrases, and per-bundle pointers covering everything beyond the framework quickrefs

Research-grounded SDLC issue planner — dispatches parallel research, generates the supporting doc corpus, then files prioritized cross-referenced issues for human review.

Ingest the Project Intake Form and kick off Concept → Inception with agent assignments, accepts optional guidance to tailor process