haowjy/writing-staffing
cw/skills/writing-staffing/SKILL.md
Team composition for writing workflows: which subagents to use, how many, what focus areas to assign, and how to scale effort. Use when composing critic panels, staffing draft/revise loops, or setting up brainstorm fan-outs.
$ install --global
skillsauthnpx skillsauth add haowjy/creative-writing-skills writing-staffingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 7, 2026, 2:40 AM15.6s1 file scanned
SKILL.md
- name:
- writing-staffing
- description:
- >
- Team composition for writing workflows:
- which subagents to use, how many, what focus areas to assign, and how to scale effort. Use when composing critic panels, staffing draft/revise loops, or setting up brainstorm fan-outs.
Writing Staffing
Compose the right team for each writing task. The goal is coverage across perspectives: critics with different focus areas and brainstormers exploring different angles. Avoid redundant passes from the same angle.
General Principles
Delegation keeps context clean. Each mode of work benefits from a fresh context window: drafting needs voice fidelity, critique needs adversarial distance, research needs breadth. Use subagents to mode-switch rather than doing everything in the main conversation.
Review convergence. Critic loops run until convergence (no new substantive findings), not a fixed number of passes.
Brainstorm diversity over brainstorm volume. Three brainstormers exploring different angles beats five exploring the same angle.
Style creation and style evaluation are separate modes. Creating style reference files from sample prose is an analytical task (use @style-creator). Evaluating whether a draft maintains voice is a critique task with voice focus (use @critic).
Effort Scaling
Effort scaling applies mainly to critics: the role that fans out within a draft/revise cycle.
- Low-stakes drafts (brainstorm captures, wiki stubs): 1-2 critics
- Standard chapters: 3 critics with split focus areas
- Pivotal scenes (character deaths, reveals, arc climaxes): 4-5 critics
Subagent Catalog
Writers
- @writer: generative prose from briefs. One writer per scene/chapter. Use opus for voice fidelity.
- @revision-writer: surgical revision from critique findings. Preserves voice while fixing specific issues.
- @bridge-writer: transitions, time compression, connective passages between pivotal scenes.
Critics and Reviewers
- @critic: adversarial prose critique. Fan out with different focus areas: voice, pacing, character, continuity. Sonnet default; use opus for final-pass on pivotal scenes.
- @continuity-checker: specialist: checks draft against canon files. Use when a scene references established facts.
- @reader-sim: experiential reading. Reports what it felt like to read the draft. Use for pivotal scenes or when something feels off but you can't name it. Opus for nuance.
Exploration
- @brainstormer: wide-open idea exploration. Fan out for diversity.
- @character-sim: character voice performance. Spawn when you need to hear how a character talks or test relationship dynamics.
- @outliner: story structure at arc/chapter/beat levels.
- @style-creator: analyzes prose and produces style reference files.
Knowledge
- @chronicler: extracts facts from chapters into the kb. Cheap (haiku) and focused.
Parallelism
Think about what depends on what:
- Critics need a finished draft: they wait for the writer
- Critics examine different dimensions: fan them all out simultaneously
- Brainstormers are independent: fan them out
- Character simulations in a multi-character scene are independent: fan out
- Chronicler runs after a chapter is finalized, not during drafting
Related Skills
haowjy/intent-modeling
data-ai
VerifiedTrustedCommunity
Use before acting on the author's instructions — separate what they said from what they meant.
239SKILL.mdUpdated Jun 7, 2026
haowjy/grill-with-docs
testing
VerifiedTrustedCommunity
Use when challenging a plan — grills the author against documented decisions and sharpens terminology.
239SKILL.mdUpdated Jun 7, 2026
haowjy/cw-muse
testing
VerifiedTrustedCommunity
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.
239SKILL.mdUpdated Jun 7, 2026
haowjy/shared-dao
testing
VerifiedTrustedCommunity
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/.
239SKILL.mdUpdated May 23, 2026