cw/skills/grill-with-docs/SKILL.md
Use when challenging a plan — grills the author against documented decisions and sharpens terminology.
npx skillsauth add haowjy/creative-writing-skills grill-with-docsInstall 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.
Load /intent-modeling if it isn't already loaded.
Interview the author relentlessly about every aspect of their plan until you reach a shared understanding. Walk down each branch of the decision tree, resolving dependencies between decisions one by one.
Keep each turn to the next unresolved branch or a small cluster of related questions the author can answer in one reply, then wait. Provide your recommended answer for each question.
Read the plan or proposed direction the author provides. Identify:
Start with the highest-leverage unresolved dependency — the earliest branch point that unblocks the most downstream decisions.
Check every significant term against the project's existing vocabulary where it exists:
kb/vocab.md for project-wide terms,
kb/<domain>/vocab.md for domain-specific ones.CLAUDE.md — established names and labels.work/ — terms already defined for the current effort.When the author's language conflicts with documented terms, call it out immediately. Name the conflict: "You said X, but the kb defines Y for this concept — which should we use?"
Sharpen vague or overloaded terms into canonical terms. Use concrete
scenarios and edge cases to force precise boundaries — "Does 'sync' here mean
the timeline beat, the character's realization, or something new?" See
/shared-dao for the vocabulary discipline.
When answering requires cross-referencing project materials beyond what is already in context, read the specific files directly, or spawn a focused subagent to gather evidence so your own context stays on the grilling conversation. Scope each lookup to one question and target specific files or directories — chapters, kb entries, outlines, prior decisions.
Frame the lookup as an evidence-seeking question with file/path targets. Act on findings to sharpen your next question or to challenge the author's assumptions with evidence.
Update artifacts inline as decisions crystallize. Reasoning flattens the longer you wait — capture it in the moment.
Record decisions in work/ as they stabilize — the decision, the reasoning,
and any constraints that emerged. Keep open questions visible.
When the session produces a new canonical term or refines an existing one,
update the appropriate vocabulary page: kb/vocab.md for cross-cutting
terms, kb/<domain>/vocab.md for domain-specific ones. Follow /kb-management
for page structure.
Create durable decision records sparingly — only when the choice is hard to
reverse, surprising without context, and involves a real tradeoff. Record it
in the relevant kb page. Keep provisional decisions in work/ until they
prove durable.
Each cycle through a decision branch:
The session ends when all branches of the decision tree are resolved and the documentation reflects the shared understanding.
data-ai
Use before acting on the author's instructions — separate what they said from what they meant.
testing
Creative-writing session lead and entry point. Activate this to get a creative partner that brainstorms, drafts, critiques, revises, and maintains your story's knowledge base. Built for Claude.ai, where there are no subagents: it runs every mode of the work in one conversation. Load alongside the craft skills (writing-principles, prose-writing, scene-construction, prose-critique). Use at the start of any story session.
testing
Shared vocabulary for creative writing projects. Load when establishing canonical story terms, resolving ambiguous names, checking term consistency, or deciding where vocabulary belongs in kb/.
testing
Use when producing written artifacts for humans — catches default LLM writing patterns.