Skill rating

Auto-fix discoverable issues

Auto-fix discoverable issues

Provide provider capability awareness and route commands by answering what the current provider supports natively vs must emulate

Orchestrate compliance validation workflow with requirements mapping, audit evidence collection, gap analysis, remediation tracking, and attestation

Orchestrate production deployment with strategy selection, validation, automated rollback, and regression gates

Orchestrate hypercare monitoring period with 24/7 support, SLO tracking, and rapid issue response

Orchestrate handoff validation between SDLC phases and tracks (Discovery→Delivery, Delivery→Ops, phase transitions)

Orchestrate production incident triage, escalation, resolution, and post-incident review using ITIL best practices

Delegate approved one-shot or incremental dataset execution to the shared orchestration service with resumable receipts.

List the installed decision pattern packs and run their offline recorded fixtures through the production decision evaluator

Correlate auth.log, syslog, journald, application, and web logs to detect brute force, privilege escalation, and lateral movement.

Orchestrate SDLC phase gate validation with multi-agent review and comprehensive reporting

Apply metadata tags, embed artwork, and organize media files with consistent naming

Scan existing codebase and generate intake documents by analyzing code, dependencies, and infrastructure. Accepts optional guidance text to tailor analysis.

Report on research corpus health, completeness, and integrity

Orchestrate Knowledge Transfer flow with assessment, documentation, shadowing, validation, and handover

Execute multi-stage research workflows

End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions

Download media from discovered sources with format selection and progress tracking

Update AIWG CLI and redeploy frameworks/tools to current project without leaving the session

Use when validating YAML flow syntax accepted by the pinned reference parser.

Use when validating the minimal normative Agent Skills fixture.

Recommend an independently composable dataset capability profile with plain-language rationale and safe defaults.

Evaluate synthetic local multi-agent monitorability fixtures and label content, tool, state, and evidence blind spots

Plan and review a bounded, non-mutating dataset source check and redacted preview.

Review an immutable dataset plan, impacts, capability degradation, and approval requirements before execution.

Plan and delegate a governed portable dataset or lineage export with explicit standards coverage and loss reporting.

Turn a source path or URI and desired outcome into a governed dataset intake envelope for any AIWG domain.

Plan and delegate safe dataset retirement, tombstoning, derived-artifact cleanup, and reconciliation.

Verify a dataset plan or run receipt, checkpoint continuity, provenance completeness, and derived-artifact freshness.

Explain dataset, record, field, index, graph, and export lineage using evidence-bearing bounded queries.

Evaluate a pinned normalized decision ruleset through an explicitly configured Jev or LLM-subagent binding

Explain schema value to a non-specialist and guide them through examples-first contract creation.

Author and register a canonical governed schema with fixtures and consumer metadata from a schema brief.

Generate, analyze, compare, export, and suggest color palettes using color theory. Use when user asks about colors, palettes, color schemes, or needs help choosing colors for a project.

Research current color trends from Pantone, architecture, film, and design. Use when user asks about trending colors, popular palettes, or wants research-backed color inspiration.

Parallel fan-out processing - spawn multiple sub-agents for chunked context processing

Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly

Use this complete portable fixture to verify Agent Skills round trips.

List and filter tickets/issues from configured backend

Capture query synthesis as durable pages in semantic memory

Configure, use, troubleshoot, or extend AIWG composable output modes (also called output masks), including Wittgenstein-inspired clarity, engineering controlled language, and personal syntax profiles

AUTO-INVOKE for ANY AIWG capability question, framework/addon/extension query, steward routing, MCP profile, or when unsure where to start. ALWAYS consult before filesystem search on .claude/.factory/

Validate manually-created campaign intake forms and kick off Strategy phase with agent assignments

Apply a voice profile to transform content. Use when the user asks to write in a specific voice, match a tone, or sound like a particular voice profile.

Use when testing Claude native skill portability and projection.

Decision aid for authentication factor architecture — have/know/are mapping, coercion resistance, FIDO2 PIN/UV policy, and PRF hot-path anti-patterns.

Rebuild bidirectional citation edges in a research corpus. Scans outgoing citations, computes the inverse map, rewrites incoming tables. Fixes one-directional graphs.

Audit an application against Twelve-Factor and modern 12+ Factor criteria with structured evidence, risks, and remediation tasks.

Combine multiple voice profiles with weighted mixing to create hybrid voices