haowjy
122 verified skills19,561 total stars
knowledge-layers
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
development298
zoom-out
Use when orienting in an unfamiliar area — fans out exploration across structure, knowledge, and history, then synthesizes one orientation map.
tools298
llm-writing
Load before writing or revising human-facing text. Choose words deliberately, ground the piece in the reader's context, and remove default LLM phrasing before the final draft.
testing298
information-hierarchy
Load for large human-facing outputs: reports, docs, multi-section explanations, artifacts. Choose the right form for each beat (prose, diagram, table, mockup) and put the answer first, depth behind it. If the medium allows, use progressive disclosure.
development298
qi-layer
Use when exploring or changing the codebase: read AGENTS.md first, use .context/CONTEXT.md for detail, keep intent docs succinct.
development298
md-validation
Use when validating markdown links or Mermaid diagrams.
data-ai298
reflect
User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge capture.
testing298
structured-artifact
Load when building a static HTML artifact — single page or multi-page site — to make structured information explorable through layout and navigation.
development298
interactive-artifact
Build a self-contained HTML file that makes structured information explorable through interaction — clicking, filtering, sorting, expanding. Default to Mermaid diagrams; choose a different interaction pattern when the data calls for it.
tools290
intent-modeling
Use before acting on human instructions: separate what they said from what they meant.
data-ai287
reader-sim
Read as a specified first-time reader persona and report the felt experience. Use for skill-only workflows when a draft needs persona-bound reader-response signal instead of analytical critique.
testing287
creative-research
Load when a story needs factual grounding the writer doesn't have: historical detail, cultural texture, domain accuracy, or how other authors handled similar material. Pass the question and story context; returns a sourced report the writer can draw from.
documentation287
character-sim
Speak as a specified character from their current knowledge, voice, and emotional state. Use for skill-only workflows that need in-character conversation, voice discovery, or relationship pressure tests.
testing287
project-setup
One-time project setup for creative writing. Interviews you about your project, collects writing samples, proposes kb structure, and creates CLAUDE.md with project conventions.
tools287
creative-writing-muse
Load when no subagents are available and one agent must plan, draft, critique, research, and capture memory by switching stances.
data-ai287
creative-writing-craft
Craft references for writing fiction well: prose, scenes, style, voice, and genre/page-level technique. Load when a writer, critic, or muse needs how-to-write guidance rather than a production mode.
documentation287
writing-staffing
Dispatch reference for composing writing teams. Teaches which extra skills to attach via --skills, which resources to reference in spawn prompts, and when to fan out. Load when staffing a workflow.
data-ai287
writing-principles
What fiction readers want (reader reward channels) and the specific ways LLM training damages them. Load when drafting prose, critiquing, or diagnosing why a passage feels flat.
testing287
creative-writing-modes
Creative-writing addendum to /llm-writing. Load when putting prose on the page: draft, revise, bridge, vary, or polish.
data-ai287
story-planning
Planning work before prose: creative direction, story-planning, outlining, and story architecture. Load when deciding what should happen or how a story should be structured.
testing287
creative-writing-craft
Craft references for writing fiction well: prose, scenes, style, voice, and genre/page-level technique. Load when a writer, critic, or muse needs how-to-write guidance rather than a production mode.
documentation287
creative-research
Load when a story needs factual grounding the writer doesn't have: historical detail, cultural texture, domain accuracy, or how other authors handled similar material. Pass the question and story context; returns a sourced report the writer can draw from.
documentation287
story-planning
Planning work before prose: creative direction, story-planning, outlining, and story architecture. Load when deciding what should happen or how a story should be structured.
testing287
shared-dao
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/.
testing287
story-memory
Creative-writing domain knowledge for durable story state. Load when preserving or retrieving project memory — fact extraction, context scoping, reference writing, artifact layout, and issue tracking. If you are @kb-lead, load this for the fiction-specific categories and conventions your general methodology doesn't cover.
development287
story-review
Review work after prose exists: editorial review, craft critique, continuity/voice review, copyediting, proofreading, and synthesis of reader-sim signal. Load when diagnosing a draft rather than rewriting it.
tools287
story-memory
Creative-writing domain knowledge for durable story state. Load when preserving or retrieving project memory — fact extraction, context scoping, reference writing, artifact layout, and issue tracking. If you are @kb-lead, load this for the fiction-specific categories and conventions your general methodology doesn't cover.
development287
reader-sim
Read as a specified first-time reader persona and report the felt experience. Use for skill-only workflows when a draft needs persona-bound reader-response signal instead of analytical critique.
testing287
creative-writing-muse
Load when no subagents are available and one agent must plan, draft, critique, research, and capture memory by switching stances.
data-ai287
writing-staffing
Dispatch reference for composing writing teams. Teaches which skills to load for each subagent, which resources to reference, and when to fan out. Load when staffing a workflow.
data-ai287
character-sim
Speak as a specified character from their current knowledge, voice, and emotional state. Use for skill-only workflows that need in-character conversation, voice discovery, or relationship pressure tests.
testing287
story-review
Review work after prose exists: editorial review, craft critique, continuity/voice review, copyediting, proofreading, and synthesis of reader-sim signal. Load when diagnosing a draft rather than rewriting it.
tools287
kb-management
Maintaining the story knowledge base: creating, updating, and organizing wiki-style reference pages in kb/. Use when capturing finalized story knowledge, updating character profiles, documenting world mechanics, or restructuring the kb.
documentation287
creative-writing-modes
Creative-writing addendum to /llm-writing. Load when putting prose on the page: draft, revise, bridge, vary, or polish.
data-ai287
writing-principles
What fiction readers want (reader reward channels) and the specific ways LLM training damages them. Load when drafting prose, critiquing, or diagnosing why a passage feels flat.
testing287
character-voice
Speaking as a specific character from a full profile or bare sketch. Use when exploring voice, testing relationships, or writing dialogue in character.
testing270
prose-writing
Prose-level immersion patterns: psychic distance, free indirect discourse, rhythm, sensory grounding. Use when writing or revising narrative prose.
tools270
reader-experience
Experiential reading through the four reader reward channels. Use when a draft needs reader-response signal: what it felt like to read, moment by moment, rather than analytical critique.
tools270
story-context
Context scoping for writing handoffs. Use when deciding what story context to pass, whether to materialize decisions before handoff, and how much is enough.
testing270
writing-issues
Tracking writing issues that persist beyond a single critique: recurring tics, cross-chapter inconsistencies, structural concerns. Use when a problem is worth logging for future revision.
testing270
fact-extraction
Extracting factual state changes from written chapters into the kb. Use when a chapter needs its canon, timeline, character state, and terminology captured.
tools270
style-analysis
How to analyze prose and produce style reference files. Use when creating, updating, or evaluating the style files that capture a project's voice patterns.
research270
production-drafting
Turning confirmed creative direction into finished drafts. Use when running write/critique/revise cycles to produce polished prose.
documentation270
character-voice
Speaking as a specific character from a full profile or bare sketch. Use when exploring voice, testing relationships, or writing dialogue in character.
testing270
creative-direction
Shape what the story wants to be before producing pages. Use when brainstorming with the author, synthesizing options, or deciding how much ceremony a piece of story work needs.
testing270
cw-muse
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.
testing270
fact-extraction
Extracting factual state changes from written chapters into the kb. Use when a chapter needs its canon, timeline, character state, and terminology captured.
tools270
creative-direction
Shape what the story wants to be before producing pages. Use when brainstorming with the author, synthesizing options, or deciding how much ceremony a piece of story work needs.
testing270
production-drafting
Turning confirmed creative direction into finished drafts. Use when running write/critique/revise cycles to produce polished prose.
documentation270
prose-writing
Prose-level immersion patterns: psychic distance, free indirect discourse, rhythm, sensory grounding. Use when writing or revising narrative prose.
tools270
reader-experience
Experiential reading through the four reader reward channels. Use when a draft needs reader-response signal: what it felt like to read, moment by moment, rather than analytical critique.
tools270
style-analysis
How to analyze prose and produce style reference files. Use when creating, updating, or evaluating the style files that capture a project's voice patterns.
research270
writing-issues
Tracking writing issues that persist beyond a single critique: recurring tics, cross-chapter inconsistencies, structural concerns. Use when a problem is worth logging for future revision.
testing270
writing-artifacts
Where writing artifacts live: kb for durable knowledge, work directory for scratch. Use when deciding where to read from or write to.
testing250
story-context
Context scoping for writing subagents: use when deciding what context a subagent should receive, whether ephemeral story decisions should be written down before handoff, and how much to pass. Poor context handoffs cause writers to invent contradictions and critics to miss relevant history.
testing239
grill-with-docs
Use when challenging a plan — grills the author against documented decisions and sharpens terminology.
testing239
brainstorming
Story brainstorming capture: minimal notes that preserve creative freedom. Use when exploring narrative ideas, discussing characters, planning chapters, or thinking through story possibilities.
data-ai239
prose-critique
Adversarial reading methodology for narrative fiction: find what doesn't work, not confirm what does. Focus-area driven with dedicated resources per area. Use when reviewing drafts, evaluating prose quality, or assessing changes at any stage.
testing239
story-architecture
Arc structure, narrative design, and pacing at multiple scales: saga, arc, chapter, scene. Use when structuring story at any level, planning arcs, designing chapter outlines, or evaluating whether narrative structure serves the story's goals.
development239
writing-artifacts
Where writing artifacts live: kb/ for durable knowledge, work/ for scratch. Use when deciding where to read from or write to.
testing239
scene-construction
How to build scenes: entry, dialogue, pacing, transitions. Use when writing or evaluating how scenes work on the page.
development239
story-architecture
Arc structure, narrative design, and pacing at multiple scales: saga, arc, chapter, scene. Use when structuring story at any level, planning arcs, designing chapter outlines, or evaluating whether narrative structure serves the story's goals.
development214
brainstorming
Story brainstorming capture: minimal notes that preserve creative freedom. Use when exploring narrative ideas, discussing characters, planning chapters, or thinking through story possibilities.
data-ai214
prose-critique
Adversarial reading methodology for narrative fiction: find what doesn't work, not confirm what does. Focus-area driven with dedicated resources per area. Use when reviewing drafts, evaluating prose quality, or assessing changes at any stage.
testing214
scene-construction
How to build scenes: entry, dialogue, pacing, transitions. Use when writing or evaluating how scenes work on the page.
development191
wiki-docs
Encyclopedic reference documentation for fictional worlds — wiki pages, character profiles, lore entries. Use when creating or updating reader-facing reference pages. Covers link discipline, citation conventions, and mermaid relationship diagrams. Distinct from the knowledge base, which is author/agent-facing knowledge.
testing150
orchestrate
Shared coordination model for writing orchestrators — delegation discipline, convergence loops, critique synthesis, and artifact persistence. Load when you coordinate work across multiple spawns rather than producing content directly.
testing133
story-decisions
Story decision capture and mining — recording what was decided, what was rejected, and why, inline with the artifacts they relate to. Use whenever story direction is being chosen, brainstorm options are being narrowed, character or world choices are being made, or past decisions need to be recovered from session history.
testing133
knowledge-graph
Project document navigation. Use when you need to understand how documents connect, find related content, identify orphaned pages, or orient on a project's structure before doing other work.
documentation133
story-decisions
Story decision capture and mining — recording what was decided, what was rejected, and why, inline with the artifacts they relate to. Use whenever story direction is being chosen, brainstorm options are being narrowed, character or world choices are being made, or past decisions need to be recovered from session history.
testing133
wiki-docs
Encyclopedic reference documentation for fictional worlds — wiki pages, character profiles, lore entries. Use when creating or updating reader-facing reference pages. Covers link discipline, citation conventions, and mermaid relationship diagrams. Distinct from the knowledge base, which is author/agent-facing knowledge.
testing133
mermaid
Rules and validation for Mermaid diagrams. Use when creating or editing Mermaid diagrams in documentation.
documentation133
orchestrate
Shared coordination model for writing orchestrators — delegation discipline, convergence loops, critique synthesis, and artifact persistence. Load when you coordinate work across multiple spawns rather than producing content directly.
testing133
cw-router
Quick guide to choosing the right creative writing skill or agent. Use when you need help deciding which skill to load or which agent to spawn for a specific task — brainstorming vs documentation, critique vs writing, analysis vs architecture, etc.
testing128
cw-brainstorming
Creative writing skill for capturing story brainstorming. Use when the user is exploring narrative ideas, discussing characters, planning episodes, or thinking through story possibilities. Creates minimal working notes that preserve creative freedom by recording only what was stated and marking sources.
data-ai100
cw-style-skill-creator
Creative writing skill for creating style skills that teach Claude to write in specific styles. Use when you want to create style guides that the cw-prose-writing skill can follow. Creates either simple markdown files or full .skill packages. Audience is AI (Claude), format is directive and example-based.
development100
cw-official-docs
Creative writing skill for creating canonical reference documentation (wikis) for fictional worlds, characters, and story events. Use when creating or updating wiki pages, official documentation, character profiles, location documentation, or lore pages. Creates polished, sourced, encyclopedic reference material.
testing100
cw-story-critique
Creative writing skill for analyzing and critiquing story content. Use when the user requests feedback, critique, or analysis of their writing. Provides balanced feedback calibrated to intended audience.
content-media100
cw-router
Quick guide to choosing the right creative writing skill. Use when you need help deciding which creative writing skill to use for a specific task - brainstorming vs documentation, critique vs writing, etc.
testing100
cw-prose-writing
Creative writing skill for drafting and editing narrative fiction prose. Use when writing new scenes, chapters, or dialogue, or when editing existing prose. Discovers and follows project-specific style guides, character voice conventions, and formatting preferences.
development100
prose-analysis
Mechanical prose metrics — sentence length, opener variety, dialogue ratio, repetition, pronoun distribution. Use when you need quantitative signals about prose before making subjective judgments, or when comparing a draft against the project's baseline.
data-ai
story-architecture
Arc structure, narrative design, and pacing at multiple scales — saga, arc, chapter, scene. Use when structuring story at any level, planning arcs, designing chapter outlines, or evaluating whether narrative structure serves the story's goals. Not prescriptive about methodology.
development
skill-creator
Author, edit, review, split, or refactor meridian skill files — the SKILL.md files with YAML frontmatter that live under `skills/<name>/` in a source submodule and carry reference material loaded into agents on demand. Load this skill whenever you're writing a skill from scratch, updating a SKILL.md body, adding or reorganizing `resources/`, splitting a long skill into variants, or deciding whether something should be a skill at all. Phrases that should trigger this skill: "write a skill", "create a skill", "add resources to this skill", "the SKILL.md needs updating", "split this skill", "this skill is too long", "refactor this skill's description".
development
prose-writing
Prose drafting technique for narrative fiction. Use when writing new scenes, chapters, or dialogue — whether in conversation with an author or producing a draft autonomously from a brief. Covers craft fundamentals; project-specific voice comes from style files passed alongside this skill.
testing
prose-writing
Prose drafting technique for narrative fiction. Use when writing new scenes, chapters, or dialogue — whether in conversation with an author or producing a draft autonomously from a brief. Covers craft fundamentals; project-specific voice comes from style files passed alongside this skill.
testing
prose-critique
Adversarial reading methodology for narrative fiction — find what doesn't work, not confirm what does. Focus-area driven with dedicated resources per area. Use when reviewing drafts, evaluating prose quality, or assessing changes at any stage.
testing
prose-analysis
Mechanical prose metrics — sentence length, opener variety, dialogue ratio, repetition, pronoun distribution. Use when you need quantitative signals about prose before making subjective judgments, or when comparing a draft against the project's baseline.
data-ai
mermaid
Rules and validation for Mermaid diagrams. Use when creating or editing Mermaid diagrams in documentation.
documentation
meridian-work-coordination
Meridian work lifecycle and artifact placement. Use this whenever you need to create, switch, update, or complete a work item, or decide where work-scoped notes versus broader shared docs belong.
testing
meridian-spawn
Multi-agent coordination via the meridian CLI. Use this skill whenever you need to delegate work to another agent, run tasks in parallel, check on spawn progress, coordinate multiple agents, or inspect spawn outputs. Also use when you want to route work to a specific model or provider.
tools
meridian-privilege-escalation
How to escalate agent permissions in meridian when a spawn hits capability limits — sandbox tiers, approval modes, model/harness switching, and per-spawn overrides. Use when a spawned agent fails because of sandbox restrictions, missing tools, harness limitations, or insufficient permissions, and you need to change the spawn configuration to unblock it.
tools
knowledge-graph
Project document navigation. Use when you need to understand how documents connect, find related content, identify orphaned pages, or orient on a project's structure before doing other work.
documentation
knowledge-graph
Project document navigation. Use when you need to understand how documents connect, find related content, identify orphaned pages, or orient on a project's structure before doing other work.
documentation
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
development
agent-creator
Author, edit, review, or refactor meridian agent profiles — the markdown files with YAML frontmatter that live in an `agents/` directory and define reusable spawn configurations (model, system prompt, tools, permissions, skills). Load this skill whenever you're writing an agent from scratch, tweaking an existing profile, splitting one agent into several, reviewing an agent for quality, or deciding whether something should be an agent at all. Phrases that should trigger this skill: "write an agent", "create a profile", "edit this agent", "add a reviewer agent", "refactor the coder agent", "this agent's prompt needs work", "add tools to this profile", "tighten up this agent's description".
tools
brainstorming
Story brainstorming capture — minimal notes that preserve creative freedom. Use when exploring narrative ideas, discussing characters, planning chapters, or thinking through story possibilities. Supports interactive conversation and autonomous report mode for fan-out exploration.
data-ai
meridian-spawn
Multi-agent coordination via the meridian CLI. Use this skill whenever you need to delegate work to another agent, run tasks in parallel, check on spawn progress, coordinate multiple agents, or inspect spawn outputs. Also use when you want to route work to a specific model or provider.
tools
writing-artifacts
Shared artifact convention between orchestrators — what goes where in `$MERIDIAN_FS_DIR/` and `$MERIDIAN_WORK_DIR/`, how artifacts flow between phases, and what each directory means. Use whenever work artifacts, style files, knowledge entries, drafts, or critique reports are being created, referenced, or discussed.
development
meridian-privilege-escalation
How to escalate agent permissions in meridian when a spawn hits capability limits — sandbox tiers, approval modes, model/harness switching, and per-spawn overrides. Use when a spawned agent fails because of sandbox restrictions, missing tools, harness limitations, or insufficient permissions, and you need to change the spawn configuration to unblock it.
tools
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
development
skill-creator
Author, edit, review, split, or refactor meridian skill files — the SKILL.md files with YAML frontmatter that live under `skills/<name>/` in a source submodule and carry reference material loaded into agents on demand. Load this skill whenever you're writing a skill from scratch, updating a SKILL.md body, adding or reorganizing `resources/`, splitting a long skill into variants, or deciding whether something should be a skill at all. Phrases that should trigger this skill: "write a skill", "create a skill", "add resources to this skill", "the SKILL.md needs updating", "split this skill", "this skill is too long", "refactor this skill's description".
development
story-decisions
Story decision capture and mining — recording what was decided, what was rejected, and why, inline with the artifacts they relate to. Use whenever story direction is being chosen, brainstorm options are being narrowed, character or world choices are being made, or past decisions need to be recovered from session history.
testing
writing-issues
Logging and referencing writing issues — craft problems, tics, inconsistencies, and structural concerns found during analysis, critique, or review. Use when an agent identifies something worth tracking beyond a single critique report: repeated tics across chapters, inconsistencies that affect multiple scenes, structural problems that need the author's attention, or patterns that should be fixed in revision.
testing
writing-artifacts
Shared artifact convention between orchestrators — what goes where in `$MERIDIAN_FS_DIR/` and `$MERIDIAN_WORK_DIR/`, how artifacts flow between phases, and what each directory means. Use whenever work artifacts, style files, knowledge entries, drafts, or critique reports are being created, referenced, or discussed.
development
writing-issues
Logging and referencing writing issues — craft problems, tics, inconsistencies, and structural concerns found during analysis, critique, or review. Use when an agent identifies something worth tracking beyond a single critique report: repeated tics across chapters, inconsistencies that affect multiple scenes, structural problems that need the author's attention, or patterns that should be fixed in revision.
testing
writing-principles
What fiction readers actually want, framed as four composable reward channels (transportation, aesthetic, social simulation, flow), and the specific documented ways alignment training damages each one. Grounded in reader-psychology research and empirical NLP findings. Load when drafting prose, critiquing a draft, deciding whether to show or tell, diagnosing why a passage feels flat, or reasoning about why a scene is or isn't working.
testing
writing-principles
What fiction readers actually want, framed as four composable reward channels (transportation, aesthetic, social simulation, flow), and the specific documented ways alignment training damages each one. Grounded in reader-psychology research and empirical NLP findings. Load when drafting prose, critiquing a draft, deciding whether to show or tell, diagnosing why a passage feels flat, or reasoning about why a scene is or isn't working.
testing
writing-staffing
Team composition for writing workflows — which agents to spawn, how many, what focus areas to assign, and how to scale effort. Use when composing critic panels, dispatching researchers, staffing draft/revise loops, or setting up brainstorm fan-outs.
data-ai
writing-staffing
Team composition for writing workflows — which agents to spawn, how many, what focus areas to assign, and how to scale effort. Use when composing critic panels, dispatching researchers, staffing draft/revise loops, or setting up brainstorm fan-outs.
data-ai
story-decisions
Story decision capture and mining — recording what was decided, what was rejected, and why, inline with the artifacts they relate to. Use whenever story direction is being chosen, brainstorm options are being narrowed, character or world choices are being made, or past decisions need to be recovered from session history.
testing
meridian-work-coordination
Meridian work lifecycle and artifact placement. Use this whenever you need to create, switch, update, or complete a work item, or decide where work-scoped notes versus broader shared docs belong.
testing
meridian-cli
Mental model and principles for the meridian and mars CLIs. Use when an agent needs to discover what meridian can do, learn a subcommand, diagnose a failure, or understand why meridian behaves the way it does. Points at `meridian --help` and `meridian mars --help` as the canonical reference rather than duplicating them.
tools
brainstorming
Story brainstorming capture — minimal notes that preserve creative freedom. Use when exploring narrative ideas, discussing characters, planning chapters, or thinking through story possibilities. Supports interactive conversation and autonomous report mode for fan-out exploration.
data-ai
agent-creator
Author, edit, review, or refactor meridian agent profiles — the markdown files with YAML frontmatter that live in an `agents/` directory and define reusable spawn configurations (model, system prompt, tools, permissions, skills). Load this skill whenever you're writing an agent from scratch, tweaking an existing profile, splitting one agent into several, reviewing an agent for quality, or deciding whether something should be an agent at all. Phrases that should trigger this skill: "write an agent", "create a profile", "edit this agent", "add a reviewer agent", "refactor the coder agent", "this agent's prompt needs work", "add tools to this profile", "tighten up this agent's description".
tools
meridian-cli
Mental model and principles for the meridian and mars CLIs. Use when an agent needs to discover what meridian can do, learn a subcommand, diagnose a failure, or understand why meridian behaves the way it does. Points at `meridian --help` and `meridian mars --help` as the canonical reference rather than duplicating them.
tools
prose-critique
Adversarial reading methodology for narrative fiction — find what doesn't work, not confirm what does. Focus-area driven with dedicated resources per area. Use when reviewing drafts, evaluating prose quality, or assessing changes at any stage.
testing
story-context
Context scoping for writing agent spawns — use when deciding what context a spawned agent should receive, whether ephemeral story decisions should be materialized before handoff, and how much to pass. Poor context handoffs cause writers to invent contradictions and critics to miss relevant history.
testing
story-context
Context scoping for writing agent spawns — use when deciding what context a spawned agent should receive, whether ephemeral story decisions should be materialized before handoff, and how much to pass. Poor context handoffs cause writers to invent contradictions and critics to miss relevant history.
testing
story-architecture
Arc structure, narrative design, and pacing at multiple scales — saga, arc, chapter, scene. Use when structuring story at any level, planning arcs, designing chapter outlines, or evaluating whether narrative structure serves the story's goals. Not prescriptive about methodology.
development
wiki-docs
Encyclopedic reference documentation for fictional worlds — wiki pages, character profiles, lore entries. Use when creating or updating reader-facing reference pages. Covers link discipline, citation conventions, and mermaid relationship diagrams. Distinct from $MERIDIAN_FS_DIR/ which is author/agent-facing knowledge.
testing
wiki-docs
Encyclopedic reference documentation for fictional worlds — wiki pages, character profiles, lore entries. Use when creating or updating reader-facing reference pages. Covers link discipline, citation conventions, and mermaid relationship diagrams. Distinct from $MERIDIAN_FS_DIR/ which is author/agent-facing knowledge.
testing
mermaid
Rules and validation for Mermaid diagrams. Use when creating or editing Mermaid diagrams in documentation.
documentation