Writing staffing skill
Dispatch reference for composing writing teams.
by haowjy·Apache-2.0 license·★ 506 Stars on the repo·GitHub ↗
npx degit haowjy/creative-writing-skills/cw/skills/writing-staffing#main ~/.claude/skills/writing-staffingChecked ·commit main
Files of Writing staffing
Show the full text112 lines
Writing Staffing
Each subagent has its own skill set. This skill teaches what extra skills to load and reference when dispatching work.
Fan-out gives the same question and files to different model families for independent judgment. Reserve it for high-stakes calls where model diversity can reveal different blind spots. Parallel lanes use different prompts or focus areas; use them when the work divides cleanly.
Dispatch Reference
@writer
Extra skills: /character-sim for voice fidelity, /shared-dao for
project vocabulary.
Reference: name the production mode from /creative-writing-modes →
resources/prose-modes.md (fresh draft, revision, bridge, alternate take,
line polish). Point to /creative-writing-craft →
resources/prose-writing.md or resources/scene-construction.md when
relevant. Include style and character state for everyone who
appears, plus continuity anchors.
One writer per scene — voice consistency degrades when multiple writers handle adjacent content.
@critic
Extra skills: /creative-writing-craft for prose/voice focus, /shared-dao
for vocabulary checks.
Assign a focus area: structure, character, voice, prose, or continuity. Include style for voice critique. Include character state for character or continuity focus.
Run different focus areas as parallel lanes. Scale to stakes: 1–2 for low-stakes, 3 for standard chapters, 4–5 for pivotal scenes with duplicated coverage on the critical dimension.
For a pivotal scene or disputed judgment, fan out the same critical dimension once across two strong model families, then synthesize the disagreement.
@editor
Name the edit level: editorial review, developmental, line edit, copyedit,
proofreading. Point to /story-review → resources/editorial-review.md for
holistic pass, or the specific edit-level resource.
Use when the draft needs a priority order across concerns. For depth on
one dimension, use @critic.
@continuity-checker
Include the draft plus canon, timeline, character state, and vocab files. More expensive than a critic with continuity focus — reads broadly. Use the critic for routine checks, the continuity-checker for deep validation.
@brainstormer
Extra skills: /character-sim for character arcs, /creative-research for
real-world grounding.
Run parallel lanes on different angles, not the same angle. Three perspectives beats five instances of one.
@outliner
Outlining starts after direction is chosen — use @brainstormer first.
The outliner's output feeds the writer.
@style-creator
Include sample chapters or existing style files. Point to
/creative-writing-craft → resources/style-analysis.md.
@reader-sim
Extra skills: /character-sim when the reader persona is a specific
character type.
Specify the reader persona and knowledge boundary (what has this reader already read). Include the draft.
Run after the write/critique loop converges, before presenting to the author. A scene can be technically clean and leave a reader cold.
@character-sim
Include character state and style. Specify the scenario or relationship to explore. Use one parallel lane per character or perspective for independent exploration; use one shared simulation when testing their interaction.
@web-researcher
Specify the question, story context, and what the story currently assumes so the researcher can flag contradictions.
Effort Scaling
Scale critic coverage to stakes. Knowledge maintenance waits until direction or chapters settle. Reader-sim runs after the write/critique loop converges.
| 1 | |
| 2 | name writing-staffing |
| 3 | description > |
| 4 | Dispatch reference for composing writing teams. Teaches which skills to |
| 5 | load for each subagent, which resources to reference, and when to fan out |
| 6 | versus run parallel lanes. Load when staffing a workflow. |
| 7 | |
| 8 | |
| 9 | # Writing Staffing |
| 10 | |
| 11 | Each subagent has its own skill set. This skill teaches what *extra* skills |
| 12 | to load and reference when dispatching work. |
| 13 | |
| 14 | **Fan-out** gives the same question and files to different model families for |
| 15 | independent judgment. Reserve it for high-stakes calls where model diversity |
| 16 | can reveal different blind spots. **Parallel lanes** use different prompts or |
| 17 | focus areas; use them when the work divides cleanly. |
| 18 | |
| 19 | ## Dispatch Reference |
| 20 | |
| 21 | ### `@writer` |
| 22 | |
| 23 | Extra skills: `/character-sim` for voice fidelity, `/shared-dao` for |
| 24 | project vocabulary. |
| 25 | |
| 26 | Reference: name the production mode from `/creative-writing-modes` → |
| 27 | `resources/prose-modes.md` (fresh draft, revision, bridge, alternate take, |
| 28 | line polish). Point to `/creative-writing-craft` → |
| 29 | `resources/prose-writing.md` or `resources/scene-construction.md` when |
| 30 | relevant. Include style and character state for everyone who |
| 31 | appears, plus continuity anchors. |
| 32 | |
| 33 | One writer per scene — voice consistency degrades when multiple writers |
| 34 | handle adjacent content. |
| 35 | |
| 36 | ### `@critic` |
| 37 | |
| 38 | Extra skills: `/creative-writing-craft` for prose/voice focus, `/shared-dao` |
| 39 | for vocabulary checks. |
| 40 | |
| 41 | Assign a focus area: structure, character, voice, prose, or continuity. |
| 42 | Include style for voice critique. Include character state for |
| 43 | character or continuity focus. |
| 44 | |
| 45 | Run different focus areas as parallel lanes. Scale to stakes: |
| 46 | 1–2 for low-stakes, 3 for standard chapters, 4–5 for pivotal scenes with |
| 47 | duplicated coverage on the critical dimension. |
| 48 | |
| 49 | For a pivotal scene or disputed judgment, fan out the same critical dimension |
| 50 | once across two strong model families, then synthesize the disagreement. |
| 51 | |
| 52 | ### `@editor` |
| 53 | |
| 54 | Name the edit level: editorial review, developmental, line edit, copyedit, |
| 55 | proofreading. Point to `/story-review` → `resources/editorial-review.md` for |
| 56 | holistic pass, or the specific edit-level resource. |
| 57 | |
| 58 | Use when the draft needs a priority order across concerns. For depth on |
| 59 | one dimension, use `@critic`. |
| 60 | |
| 61 | ### `@continuity-checker` |
| 62 | |
| 63 | Include the draft plus canon, timeline, character state, and vocab files. |
| 64 | More expensive than a critic with continuity focus — reads broadly. Use the |
| 65 | critic for routine checks, the continuity-checker for deep validation. |
| 66 | |
| 67 | ### `@brainstormer` |
| 68 | |
| 69 | Extra skills: `/character-sim` for character arcs, `/creative-research` for |
| 70 | real-world grounding. |
| 71 | |
| 72 | Run parallel lanes on different *angles*, not the same angle. Three perspectives |
| 73 | beats five instances of one. |
| 74 | |
| 75 | ### `@outliner` |
| 76 | |
| 77 | Outlining starts after direction is chosen — use `@brainstormer` first. |
| 78 | The outliner's output feeds the writer. |
| 79 | |
| 80 | ### `@style-creator` |
| 81 | |
| 82 | Include sample chapters or existing style files. Point to |
| 83 | `/creative-writing-craft` → `resources/style-analysis.md`. |
| 84 | |
| 85 | ### `@reader-sim` |
| 86 | |
| 87 | Extra skills: `/character-sim` when the reader persona is a specific |
| 88 | character type. |
| 89 | |
| 90 | Specify the reader persona and knowledge boundary (what has this reader |
| 91 | already read). Include the draft. |
| 92 | |
| 93 | Run after the write/critique loop converges, before presenting to the |
| 94 | author. A scene can be technically clean and leave a reader cold. |
| 95 | |
| 96 | ### `@character-sim` |
| 97 | |
| 98 | Include character state and style. Specify the scenario or |
| 99 | relationship to explore. Use one parallel lane per character or perspective |
| 100 | for independent exploration; use one shared simulation when testing their |
| 101 | interaction. |
| 102 | |
| 103 | ### `@web-researcher` |
| 104 | |
| 105 | Specify the question, story context, and what the story currently assumes |
| 106 | so the researcher can flag contradictions. |
| 107 | |
| 108 | ## Effort Scaling |
| 109 | |
| 110 | Scale critic coverage to stakes. Knowledge maintenance waits until direction |
| 111 | or chapters settle. Reader-sim runs after the write/critique loop converges. |
| 112 |
Discussion
Browse more free Claude skills.