arc-kit

auto-memory

This skill should be used when the user asks to 'set up memory', 'create memory files', 'create MEMORY.md', 'set up topic files', 'improve memory organization', 'what should I remember', 'how to structure memory files', 'MEMORY.md is too long', 'what goes in memory vs topic files', 'memory best practices', or wants to establish a persistent knowledge base across Claude Code sessions. Triggers on: memory setup, MEMORY.md, topic files, cross-session knowledge, persistent notes, memory maintenance, memory pruning.

new-command-docs

This skill should be used when a new ArcKit command has been added and documentation needs updating across the repository. Triggers: update documentation for new command, update command count, add command to README, update DEPENDENCY-MATRIX, update docs/index.html, new command documentation checklist, update all docs for new command, add command to dependency matrix, update command tables, sync documentation after adding command, I added a new command what do I update, post-command documentation, new slash command docs.

pr-review-community-overlay

Use when reviewing a PR to tractorjuice/arc-kit that adds or extends a community jurisdictional overlay (e.g. au-*, ca-*, uae-*, fr-*, at-*, eu-*, future state-level like au-vic-*) — produces a structured review with blockers, important issues, minor issues, and positive callouts.

release

Cut a new ArcKit release — bump versions in lockstep, regenerate non-Claude formats, validate plugin/marketplace agreement, tag, and push to standalone repos. Use when the user says 'cut a release', 'release ArcKit', 'ship vX.Y.Z', 'bump the version and release', 'do the release flow', 'tag and publish', or 'push the extensions'. This is a manual, high-consequence workflow: it never runs automatically.

architecture-workflow

Recommends which /arckit:* commands to run, and in what order, for a new or in-flight architecture project, from a short triage of sector, project type, current stage and timeline. Backs /arckit:start. Not needed when the user has already named the command they want, or is asking about the content of an artefact rather than the sequence.

arckit-build

Bulk-builds a project's ArcKit artefacts in parallel from a YAML recipe: computes the artefact dependency DAG, dispatches one subagent per target per wave, validates each output, commits the wave and persists progress to .arckit/state.json so a build can resume. Manual only: run /arckit:arckit-build with --plan, --resume, --target, --refresh or --recipe. Not needed for a single artefact; run that /arckit:* command directly.

mermaid-syntax

Mermaid syntax reference for writing or fixing a diagram in an artefact: flowchart, sequence, class, state, ER, Gantt, C4, mindmap, timeline and the other diagram types, node shapes, styling, theming, and why a diagram fails to render. Not needed for PlantUML (plantuml-syntax), or when the request is for a governed diagram artefact with document control, which /arckit:diagram produces.

plantuml-syntax

PlantUML syntax reference, C4-PlantUML first, for writing or fixing a diagram in an artefact: sequence, class, activity, state, ER, component, deployment and use-case diagrams, skinparams and themes, C4 layout conflicts and rendering errors. Not needed for Mermaid (mermaid-syntax), or when the request is for a governed diagram artefact with document control, which /arckit:diagram produces.

wardley-mapping

Wardley Mapping reference for a map, a positioning question or a strategic read: value-chain decomposition, evolution stages, OnlineWardleyMaps syntax, gameplay, doctrine and climatic patterns, build-versus-buy and inertia. Also loaded while a WARD artefact is being written. Not needed when the request is for a governed Wardley artefact with document control; the /arckit:wardley, wardley.value-chain, wardley.doctrine, wardley.gameplay and wardley.climate commands produce those.

g-cloud-framework-questions

Answers quick questions about the Digital Marketplace question structure for a G-Cloud submission: character and word limits, how many features and benefits, lot 1, 2 and 3 categories, the service and declaration questions CCS asks, pricing format and mandatory exclusion grounds. Not needed when the request is for the submission content itself; /arckit-uk-gcloud:service-design, pricing, declaration and the sdd-lot commands write that.

sfia-skills--day-rates

Answers questions about SFIA 8 levels, role-to-skill mappings, DDaT role equivalents, consultancy day-rate benchmarks and Lot 3 cloud-support team shapes for a G-Cloud submission. Not needed when the request is for the Lot 3 service definition or the pricing document; /arckit-uk-gcloud:sdd-lot3 and pricing produce those from the same data.