
--- name: canon-governance description: Govern canon changes: require explicit reason/impact/retroactive policy, and produce an actionable propagation plan. --- ## When to use - Author wants to change canon (rules, power system, key facts, naming, world constraints). - A deviation implies a canon drift and you must decide: update canon, or rewrite text back to canon. ## Required fields for a canon change request (must be explicit) - **change**: what changes (before → after) - **reason**: why t
Grep the workspace for a pattern using file_search.
Help the author write narrative unit tests (rules/constraints) and interpret failures with a concrete fix roadmap.
Provide accurate current time by calling get_time tool.
Provide accurate current time by calling get_time tool.
--- name: rewrite-branch-merge description: Manage rewrite branches: when to branch, how to compare, and how to merge back with minimal chaos. --- ## When to use - A change is risky (canon/timeline/payoff) and might break the mainline. - Author wants to explore multiple routes in parallel. ## Branching rules (simple, strict) - Branch if: - canon changes would require editing many existing chapters - timeline constraints are violated and fix is non-local - payoff plan changes the story’s
Lookup up-to-date library docs via Context7 MCP (resolve-library-id / get-library-docs).
Read a small snippet of a text file using file_read.
Evaluate arithmetic expressions precisely by calling py_calc (python-file tool).
Compute text stats via text_stats tool.
Maintain a structured Setup/Payoff ledger (promises, debts, payoffs) and generate a payoff roadmap.
Aggregate a writing session into a readable log + a reusable author-intent prompt.
Read environment variables via get_env tool (mask secrets).
Define what the Story Control Panel shows, how to compute signals, and how the author should act on alerts.
Browse local workspace files via MCP filesystem tools (docker-fs).
Simulate multiple reader personas to score a chapter (爽点/困惑/信息负荷) and propose actionable alternatives.
Convert text to URL-friendly slug via slugify tool.
Turn "AI draft -> author edits" diffs into structured deviation items, an author-intent prompt, and a concrete propagation plan.
Pretty-print JSON via json_prettify tool.