skills/story-context/SKILL.md
Context scoping for writing handoffs. Use when deciding what story context to pass, whether to materialize decisions before handoff, and how much is enough.
npx skillsauth add haowjy/creative-writing-skills story-contextInstall 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.
Every spawn starts with a context decision. Get it wrong and the writer invents facts that contradict established canon, the critic misses a continuity issue because it never saw the relevant chapter, or the brainstormer explores territory the author already rejected.
The spawn mechanics (-f, --from, spawn commands) are documented in meridian spawn -h. This skill teaches the judgment: what story context to pass, when to materialize decisions before spawning, and how much is enough.
Three options, each for a different situation. meridian spawn -h has the
command syntax; this section covers when to use which.
Files (-f): when context already exists as files: chapters, outlines,
wiki pages, style files, character state. Default choice because files are
stable, inspectable, and survive compaction. Scope tightly: pass the files
that matter, not everything.
Session history (--from): when the agent needs decisions, reasoning, or
brainstorm context that hasn't been written down yet. Session history captures
the why behind choices: why the author picked this angle, what they rejected.
Materialize first: when context is too important to be ephemeral. If
critical story decisions only live in conversation, write them to the kb or
work directory before spawning. If a writer could accidentally contradict
this context, materialize it. If it's supplementary background, --from is
fine.
Writers need enough to stay in voice and on-canon, not everything ever written. The essential context:
vocab.md files when the scene uses invented terms, magic/faction names, titles, relationship labels, or genre terms with project-specific meaningsTell the writer where to find more if it needs to explore, for example: "the full arc outline is in the work directory; focus on the Route 1 section." Avoid attaching everything preemptively.
Critics need the draft plus enough context to judge it against:
-f--from if the orchestrator discussed direction with the author, or via materialized decision notesvocab.md files when consistency of naming, aliases, deprecated terms, or invented language mattersBrainstormers need constraints, not answers:
Don't pass too much: brainstormers that receive the full project history tend to produce conservative ideas that fit neatly into existing patterns instead of exploring fresh territory.
-f, plus existing canon files, timeline entries, and vocab files for deduplication--from pointing at the conversation to mine, plus kb paths for where to write findingsCarry forward what a previous phase learned using --from <prior-spawn-id>.
The revision writer benefits from seeing what the first-draft writer
discovered. The critic benefits from seeing prior critique rounds.
Combine mechanisms when phases produce artifacts: --from for reasoning
context, -f for the files the prior phase created.
Treat vocabulary as operational story context. If a writer, critic, or
brainstormer could choose the wrong name for a concept, pass the relevant
vocab.md file or materialize the decision before spawning. This matters most
for magic systems, factions, recurring in-world phrases, titles, relationship
labels, and terms the author corrected during conversation.
When a session settles terminology, record it before handoff: canonical name, meaning, aliases still in circulation, and boundaries that prevent likely confusion.
tools
Use when orienting in an unfamiliar area — fans out exploration across structure, knowledge, and history, then synthesizes one orientation map.
development
Load when building a static HTML artifact — single page or multi-page site — to make structured information explorable through layout and navigation.
testing
User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge capture.
development
Use when exploring or changing the codebase: read AGENTS.md first, use .context/CONTEXT.md for detail, keep intent docs succinct.