plugins/gwt/skills/gwt-spec-plan/SKILL.md
Generate planning artifacts for an existing `gwt-spec`: `plan.md`, `research.md`, `data-model.md`, `quickstart.md`, and `contracts/*`, including a constitution check against `memory/constitution.md`. Use directly or through `gwt-spec-ops`.
npx skillsauth add akiojin/gwt gwt-spec-planInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill to translate a clarified spec.md into implementation-ready planning artifacts.
spec.md still has critical clarification gaps, use gwt-spec-clarify first.gwt-spec-register first.spec.md artifact from the target gwt-specmemory/constitution.mdCreate or update these artifacts as issue comments:
doc:plan.mddoc:research.mddoc:data-model.mddoc:quickstart.mdcontract:<name> when interface or schema details are neededplan.md structureplan.md must contain:
Read the source artifacts.
spec.md and memory/constitution.md.spec.md is missing or a user decision still blocks planning.Establish technical context.
Run the constitution check.
memory/constitution.md.Complexity Tracking.Produce supporting artifacts.
research.md: unknowns, tradeoff decisions, external findingsdata-model.md: entities, shapes, lifecycle, invariantsquickstart.md: minimum validation flow for reviewers and implementerscontracts/*: only when external or internal interfaces need a stable contractWrite plan.md.
Continue into task generation.
gwt-spec-ops, or proceed directly to gwt-spec-tasks when the workflow is already in motion.Planning is complete only when:
Constitution Check is present and non-emptypython3 "${CLAUDE_PLUGIN_ROOT}/skills/gwt-spec-ops/scripts/spec_artifact.py" \
--repo "." \
--issue "<number>" \
--upsert \
--artifact "doc:plan.md" \
--body-file /tmp/plan.md
python3 "${CLAUDE_PLUGIN_ROOT}/skills/gwt-spec-ops/scripts/spec_artifact.py" \
--repo "." \
--issue "<number>" \
--upsert \
--artifact "doc:research.md" \
--body-file /tmp/research.md
python3 "${CLAUDE_PLUGIN_ROOT}/skills/gwt-spec-ops/scripts/spec_artifact.py" \
--repo "." \
--issue "<number>" \
--upsert \
--artifact "doc:data-model.md" \
--body-file /tmp/data-model.md
python3 "${CLAUDE_PLUGIN_ROOT}/skills/gwt-spec-ops/scripts/spec_artifact.py" \
--repo "." \
--issue "<number>" \
--upsert \
--artifact "doc:quickstart.md" \
--body-file /tmp/quickstart.md
tools
Create distinctive, production-grade terminal user interfaces. Use when building TUI components with ratatui, CLI output styling, or xterm.js terminal rendering. Triggers: 'design TUI', 'terminal UI', 'TUIデザイン', 'ターミナルUI', 'ratatui widget'
testing
Semantic search over SPEC Issues (GitHub Issue cache at ~/.gwt/cache/issues/) using vector embeddings. Use when searching for existing specs, finding related specs, checking for duplicate specs, or determining which spec owns a scope. Mandatory preflight before gwt-discussion when the work may need a SPEC owner. Use when user says 'search specs', 'find related specs', 'check for duplicate specs', or asks which spec owns a scope.
testing
Mandatory preflight before gwt-discussion, gwt-register-issue, and gwt-fix-issue. Use proactively before creating any SPEC or Issue owner or before reusing an existing one. Searches SPEC Issues, GitHub Issues, and project files via ChromaDB. Triggers: 'search', 'find related', 'check duplicates'.
business
Use when the user wants to register new work from a bug report, idea, or task description and an existing GitHub Issue number is not already known.