wordle/.claude/skills/gds-create-game-brief/customize.toml

# DO NOT EDIT -- overwritten on every update.
#
# Workflow customization surface for gds-create-game-brief.
#
# Override files (not edited here):
#   {project-root}/_bmad/custom/gds-create-game-brief.toml         (team)
#   {project-root}/_bmad/custom/gds-create-game-brief.user.toml    (personal)

[workflow]

# --- Configurable below. Overrides merge per BMad structural rules: ---
#   scalars: override wins • arrays: append

# Steps to run before the standard activation (config load, greet).
# Use for pre-flight loads, compliance checks, etc.
activation_steps_prepend = []

# Steps to run after greet but before the workflow begins.
# Use for context-heavy setup that should happen once the user has been acknowledged.
activation_steps_append = []

# Persistent facts the workflow keeps in mind for the whole run
# (studio standards, platform constraints, stylistic guardrails).
# Each entry is either a literal sentence, a skill prefixed with `skill:`, or a
# `file:`-prefixed path/glob whose contents are loaded as facts. Empty by default.
#
# Common opt-ins (set in team/user override TOML):
#   "file:{project-root}/**/project-context.md"                   # load project context if gds-generate-project-context produced one
#   "skill:acme-studio:brand-and-rating-guidelines"              # a skill that contains studio info
#   "Every game brief must anchor on a single core fantasy players can describe in one sentence."
persistent_facts = []

# Executed when the workflow completes (after the user has been told the
# brief is ready). Accepts either a string scalar (single instruction)
# or an array of instructions executed in order. Empty for none.
on_complete = ""

# Default game-brief structure. Treated as a starting point — the LLM adapts it
# to the game, purpose, and genre. Override the path in team/user TOML to enforce
# a different structure (e.g. live-service, narrative-heavy, mobile-F2P).
brief_template = "assets/brief-template.md"

# Run folder location. The brief and optional addendum land inside
# `{brief_output_path}/{run_folder_pattern}/`. Resume-check scans
# `{brief_output_path}` for prior unfinished runs.
brief_output_path = "{planning_artifacts}/briefs"
run_folder_pattern = "brief-{project_name}-{date}"

# Polish passes applied to human-consumed docs at finalize. Each entry is a
# `skill:`, `file:`, or plain-text directive run as a parallel subagent against
# the draft; findings are applied before the user sees it. Encodes standards,
# not options.
#
# Examples:
#   "skill:bmad-editorial-review-prose"
#   "file:{project-root}/_bmad/style-guides/studio-voice.md"
#   "Convert all dates to ISO 8601 format."
#
# Suggested order (broader passes first, narrower last):
#   1. Structural (cuts, reorganization, section sizing)
#   2. Content/voice/conventions (studio standards, tone, terminology, rating)
#   3. Prose mechanics (grammar, clarity, typos)
#
# Override the array in team/user TOML to add additional standards. Append-only:
# base entries cannot be removed or replaced (resolver has no removal mechanism).
polish_passes = [
  "skill:bmad-editorial-review-structure",
  "skill:bmad-editorial-review-prose",
]

# Reviewer panel applied at finalize, after polish_passes. Each entry is a
# `skill:`, `file:`, or plain-text directive run as a parallel subagent that
# critiques the draft and returns findings (it does not silently rewrite).
# Prefix an entry with `required:` to make it a hard gate — the workflow will
# not present the brief as final until that reviewer passes or the user waives
# it. `finalize_reviewers` is an alias surface for the same gate. Empty by default.
#
# Examples (set in team/user override TOML):
#   "skill:acme-studio:greenlight-review"
#   "required:Confirm the core fantasy is stated in a single sentence and the MVP is truly minimal."
#   "When the brief targets a rated platform, cross-check content against corp:rating_reference."
reviewers = []
finalize_reviewers = []

# Name or directive of the single reviewer treated as the required gate when
# not expressed inline via a `required:` prefix above. Empty by default.
required_reviewer = ""

# External-source registry. Natural-language directives describing knowledge
# bases, MCP tools, or internal systems the LLM may consult during the workflow
# when a relevant need surfaces. The LLM does NOT query these preemptively — it
# consults them on demand (during Discovery, validation, drafting, etc.). Each
# entry names the tool, the conditions for using it, and any fields it needs.
# If a named MCP tool is unavailable at runtime, the LLM falls back to standard
# behavior and notes the gap. Empty by default.
#
# Examples (set in team/user override TOML):
#   "When researching genre context, consult corp:kb_search (database='game-design-docs') before web search."
#   "For player-sentiment signal during Discovery, query corp:wishlist_search with project={project_name}."
#   "When validating platform-rating claims, cross-check against corp:rating_reference."
external_sources = []

# External-handoff routing. Natural-language directives the LLM applies at
# Finalize to route outputs beyond local files (Confluence, Notion, Google
# Drive, ticket systems, etc.). Each entry names the MCP tool, the destination,
# and the fields it needs. Handoffs run after the artifact is polished and
# before the final user-facing message. URLs or IDs returned by the destination
# are captured and surfaced to the user. If a named tool is unavailable at
# runtime, the handoff is skipped and flagged in the JSON status; local files
# always exist regardless. Fires automatically — users can opt out in their
# prompt for a specific run. Empty by default.
#
# Examples (set in team/user override TOML):
#   "After finalize, upload brief.md and addendum.md to Confluence via corp:confluence_upload (space_key='GAME', parent_page='Game Briefs', label='brief', author={user_name})."
#   "Post a ready-for-review ping to Slack via corp:slack_post (channel='#game-design', text='New game brief: '+{confluence_url})."
external_handoffs = []