← all publishers

haowjy

@haowjy source repo

46 published skills

  1. Sync Fiction Platforms · haowjy bundle
    Use when synchronizing fiction chapters from a project's canonical source to Royal Road, FanFiction.net, Webnovel, AO3, or another browser-based publishing dashboard. Normalizes chapter content, inventories remote chapters, updates published prose, and publishes missing chapters without assuming a source format, repository layout, or story.
    0
    installs
  2. Prompt Review · haowjy bundle
    Load when an agent, skill, or prompt needs strict review. Focuses on failure modes, severity, and clear feedback.
    0
    installs
  3. Agent Artifacts · haowjy bundle
    Load when writing or reviewing agent .md files. Covers agent artifact shape, frontmatter, and Meridian-specific agent conventions.
    0
    installs
  4. Skill Artifacts · haowjy
    Load when writing or reviewing skills. Covers SKILL.md shape, loading mechanics, and how to structure bundled resources.
    0
    installs
  5. Prompt Principles · haowjy bundle
    Load when writing or reviewing prompts, skills, or agents. Gives the core heuristics for writing prompts that steer LLM behavior reliably.
    0
    installs
  6. Mermaid · haowjy bundle
    Rules and validation for Mermaid diagrams. Use when creating or editing Mermaid diagrams in documentation.
    0
    installs
  7. Plan Task · haowjy bundle
    Breaks the next task from a plan into an implementable task file. Use when decomposing a multi-step plan into ordered work units.
    0
    installs
  8. Reviewing · haowjy bundle
    Reviews code against project rules and curated reference files. Use when auditing files for violations, reviewing changes, or generating cleanup tasks.
    0
    installs
  9. Run Agent · haowjy bundle
    Agent execution engine that composes prompts, routes models, and writes run artifacts. Use when launching subagent runs.
    0
    installs
  10. Scratchpad · haowjy bundle
    Conventions for disposable scratch code and verification scripts. Use when writing smoke tests, quick probes, or temporary artifacts during task execution.
    0
    installs
  11. Orchestrate · haowjy bundle
    Multi-model supervisor that discovers skills, picks models, and composes runs. Use when executing multi-step plans across multiple models.
    0
    installs
  12. Researching · haowjy bundle
    Explores codebases and evaluates approaches before planning. Use when investigating a problem space, comparing alternatives, or gathering context for a plan.
    0
    installs
  13. Spec Aligning · haowjy
    Verifies implementation aligns with stated requirements and acceptance criteria. Use before implementation (to clarify scope) and before final sign-off (to detect gaps).
    0
    installs
  14. Grill · haowjy
    Use in conversation to stress-test a plan or direction. Interviews the human branch by branch, sharpens terminology, challenges assumptions, and asks the next high-leverage question with a recommended answer.
    0
    installs
  15. Handoff · haowjy
    Produce a transition brief and launch command for the user's next interactive primary.
    0
    installs
  16. Reflect · haowjy
    User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge capture.
    0
    installs
  17. Goal Writing · haowjy
    Load when turning intent into an executable goal for an agent, spawn, work item, experiment, or handoff. Use to define outcome, evidence, constraints, anti-goals, stop conditions, and reporting shape before work begins.
    0
    installs
  18. Qi Maintenance · haowjy
    Always load on agents that make durable source changes: keep colocated agent-facing knowledge synchronized with the source.
    0
    installs
  19. Session Mining · haowjy
    Use when recovering decisions or context from conversation history: session log navigation, transcript delegation.
    0
    installs
  20. Work Artifacts · haowjy bundle
    Anchor work in a work item: artifacts on disk, not in context.
    0
    installs
  21. Intent Modeling · haowjy
    Use before acting on human instructions: separate what they said from what they meant.
    0
    installs
  22. Shared Workspace · haowjy
    Use when a workspace has changes from other agents: safe orientation, preserving unfamiliar files.
    0
    installs
  23. Explore And Engage · haowjy
    Investigate and engage concurrently: don't block on evidence before surfacing your read.
    0
    installs
  24. Grill With Evidence · haowjy
    Use when grilling should be grounded in evidence. Loads `/grill`, then checks the plan, terms, and assumptions against project artifacts first and primary sources when needed.
    0
    installs
  25. Meridian Privilege Escalation · haowjy
    Use when a spawn fails due to sandbox or permission restrictions.
    0
    installs
  26. Reader Sim · haowjy
    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.
    1
    install
  27. Qi Layer · haowjy bundle
    Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or CLAUDE.md mirrors: keep intent docs minimal and load-bearing.
    1
    install
  28. Zoom Out · haowjy
    Use when orienting in an unfamiliar area — fans out exploration across structure, knowledge, and history, then synthesizes one orientation map.
    1
    install
  29. Story Memory · haowjy bundle
    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 a knowledge agent such as kb-lead, load this for the fiction-specific categories and conventions your general methodology doesn't cover.
    1
    install
  30. Story Review · haowjy bundle
    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.
    1
    install
  31. Shared Dao · haowjy
    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/.
    1
    install
  32. Character Sim · haowjy
    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.
    1
    install
  33. LLM Writing · haowjy
    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.
    1
    install
  34. Kb Management · haowjy
    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.
    1
    install
  35. Md Validation · haowjy bundle
    Use when validating markdown links or Mermaid diagrams.
    1
    install
  36. Project Setup · haowjy
    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.
    1
    install
  37. Writing Staffing · haowjy
    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 versus run parallel lanes. Load when staffing a workflow.
    1
    install
  38. Creative Research · haowjy
    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.
    1
    install
  39. Grill With Docs · haowjy
    Use when challenging a plan — grills the author against documented decisions and sharpens terminology.
    1
    install
  40. Writing Principles · haowjy bundle
    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.
    1
    install
  41. Knowledge Layers · haowjy bundle
    Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
    1
    install
  42. Creative Writing Muse · haowjy
    Load when no subagents are available and one agent must plan, draft, critique, research, and capture memory by switching stances.
    1
    install
  43. Structured Artifact · haowjy bundle
    Load when building a static HTML artifact — single page or multi-page site — to make structured information explorable through layout and navigation.
    1
    install
  44. Creative Writing Craft · haowjy bundle
    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.
    1
    install
  45. Creative Writing Modes · haowjy bundle
    Creative-writing addendum to /llm-writing. Load when putting prose on the page: draft, revise, bridge, vary, or polish.
    1
    install
  46. Information Hierarchy · haowjy
    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.
    1
    install