mrkeyoor.com_
Tue 01 Sept 17:45 UTC
AI Toolsevaluationupdated 23 Aug 2026

oh-story-claudecode review

This is a Chinese-first, open-source skill pack for planning, analyzing, drafting, reviewing, and packaging online fiction with coding agents; an English README is available. It turns a general-purpose agent into a structured long-form or short-form writing workflow, with project state, specialist roles, quality checks, and deployment paths for several agent environments.

+226stars / 7d
Verdict

Use it if you write Chinese web fiction and already live in Claude Code, Codex, or a similar file-aware agent: the workflow is unusually specific, actively maintained, and more disciplined than a folder of prompts. Do not mistake the easy package install for a zero-configuration product, and treat the sandbox test exit as a reason to verify the dashboard and hooks on your own platform. For its target audience, it is a strong trial candidate, but human editorial review remains mandatory.

We ran it

Install✓ · 10s3 packages · 19 MB
Buildn/ano build script
Tests✗ · 35s26 passed · 0 failed of 26 (node:test)
Known vulns00 critical · 0 high · 0 moderate · 0 low (npm audit)
Repo545 files~43,892 lines of source · 9.8 MB · 5 CI workflows · tests dir

Answers from our run

Does oh-story-claudecode build from source?

Dependencies installed in 10 seconds (3 packages), and the project has no separate build step. We cloned commit 9d0bd5f into a clean Debian container with 3 CPUs and no project-specific setup.

Do oh-story-claudecode's tests pass?

Yes: 26 of 26 passed when we ran the project's own test command (node:test). Some failures need services or credentials a bare container does not have.

Does oh-story-claudecode have known vulnerabilities in its dependencies?

npm audit found none in the dependency tree at the time of our run.

Who should not use oh-story-claudecode?

Writers who want an English-first interface and examples, because the primary documentation and workflow vocabulary are Chinese

What are the alternatives to oh-story-claudecode?

Anthropic Skills, SillyTavern, Roo Code. Use it if you write Chinese web fiction and already live in Claude Code, Codex, or a similar file-aware agent: the workflow is unusually specific, actively maintained, and more disciplined than a folder of prompts.

Setup3/5Quick install, but setup, hooks, restart, and platform caveats remain
Docs4/5Detailed workflows and caveats, though Chinese-first and dense
Community4/55,967 stars, 8 open issues, recent release and push
Maturity4/5Versioned migrations and tests, with a sandbox test-command failure

Who it’s for

Chinese-language web-fiction writers who want a repeatable agent-assisted workflow
Claude Code or Codex users comfortable installing skills and trusting project hooks
Authors managing long projects who need outlines, continuity tracking, review, and revision in one system
Teams willing to inspect generated prose and keep a human in editorial control

Who it’s NOT for

Writers who want an English-first interface and examples, because the primary documentation and workflow vocabulary are Chinese
Anyone expecting a polished desktop writing app with no terminal or agent configuration
Authors who want autonomous publication, because this is a writing workflow, not a publishing platform
Users unwilling to review hooks, generated files, or model output before trusting it

Setup reality

In our fresh Debian sandbox, npm installation succeeded in 10 seconds, installing 3 packages and using 19 MB on disk; there was no build script, so the build step was skipped. The test command exited 1 after 35 seconds, although node:test reported 26 passed and 0 failed of 26; the final log listed Chromium dashboard end-to-end cases, including line-ending, directory-loading, permission-message, pagination, and mobile-outline scenarios, without showing the underlying cause. The README's one-command global install is plausible for discovering the skills, but the full experience still requires running story-setup, reviewing or trusting project hooks where supported, restarting the agent session, and handling platform-specific fallbacks or symlink issues.

What this project is trying to fix

oh-story-claudecode starts from a sensible observation: asking an agent to "write a novel" is not a workflow. Long fiction needs market research, structural analysis, outlines, chapter production, continuity checks, revision, and persistent project state. This repository packages those jobs as 13 skills for long and short Chinese web fiction. The main documentation is Chinese, with an English README available, and its vocabulary is tied to commercial web-fiction practice: hooks, emotional payoff, pacing, popular-title analysis, and reusable plot modules.

The project supports Claude Code, Codex CLI, OpenCode, ZCode, OpenClaw, Reasonix, and generic file-aware agents, but support is not identical. Claude Code and Codex get specialist agents and hooks, while several other environments use solo or direct fallbacks. This is a coordinated set of instructions, state files, guards, and agent roles, not a model or standalone editor.

What happened when we ran it

We cloned commit 9d0bd5f into a fresh unprivileged Debian container with 3 CPUs, 8 GB of RAM, Node 22, and no secrets. The repository contained 545 files, about 43,892 lines of source, and occupied 9.8 MB. npm installation succeeded in 10 seconds, installed 3 packages, and used 19 MB on disk. npm audit found zero known vulnerabilities.

There was no build script or build target, so the build was skipped. The test command exited 1 after 35 seconds, while node:test reported 26 passed and 0 failed out of 26. The final log listed Chromium dashboard cases covering CRLF and LF preservation, isolated carriage returns, directory navigation, deep-directory search, permission or mount errors, retry behavior, pagination, and opening an outline on mobile. It also listed the mobile Chromium version of that outline case. The log does not reveal why the overall command failed, so we cannot label it a product defect or missing package. The repository simply did not achieve a clean test-command result in our environment.

Where it is unusually strong

The best feature is domain specificity. Separate skills cover trend scanning, long-form and short-form analysis, writing, importing an existing novel, multi-perspective review, removing common AI-writing patterns, cover generation, and a local dashboard. The recommended sequence, setup, restart, import, then continue a named chapter, gives authors a concrete path instead of leaving them to invent file conventions.

The release notes show maintainers testing the workflow at its failure points. Version 0.7.6 addressed a writer agent that was required to count words without Bash access, a sentence-length report that could not be computed, and child-agent instructions that encouraged mechanical one-beat-per-paragraph prose. It added detection for outlines written too much like finished prose while preserving exact phrases that must recur, such as vows or system text. Those are specific operational problems, not cosmetic announcements.

State and safety receive similar attention. The README describes outline and tracking guards, version gates for deployed agent files, context-size reductions, and fallbacks when custom agents are unavailable. Platform sections cover Windows symlinks, session restarts, hook trust, missing capabilities, and stale skill copies. This is dense documentation, but it acknowledges the awkward edges users will hit.

Weaknesses and rough edges

The setup pitch is simpler than the complete setup reality. The global command may install the package quickly, but existing projects should run story-setup again after upgrades, accept generated configuration, inspect hooks, and open a new session. Some platforms cannot run the specialist agents or all lifecycle hooks. Generic and early-support paths lose parts of the orchestration, so "supports" can mean discovery plus fallback rather than feature parity.

The Chinese-first design is another boundary. English documentation helps, but the skill names, market references, output assumptions, and examples target Chinese web fiction. English-language novelists would need to translate editorial concepts and replace market-specific scanning targets. Nor is this a conventional writing application with a familiar editor, cloud collaboration, or publishing pipeline.

Agentic prose systems can enforce process without guaranteeing taste or consistency. Tracking files, reviewer roles, and pattern checks catch mechanical failures, but cannot decide whether a character feels alive. Authors should review every chapter, use version control, and treat cover generation and web scanning as separate permission concerns.

Community health and maintenance

The repository has 5,967 stars and 8 open issues, suggesting substantial interest without an overloaded tracker. Release v0.7.6 arrived on August 13, 2026, and the repository was pushed again on August 22. Five CI workflow files and a tests directory support the impression of active engineering. Stars are not proof of satisfied authors, and the supplied community evidence contains only a GitHub Trending mention, so broad production adoption is unproven. Still, recent activity plus detailed migration notes is healthy.

Where it fits in a real stack

Treat this as the workflow layer between an author and a supported coding agent. Keep the manuscript and project state in a private Git repository, install the skills, run story-setup for the chosen runtime, review generated hooks and configuration, then restart before testing story-review. Use the dashboard and specialist agents for planning and continuity, but keep final editorial decisions, backups, rights management, and publishing outside the system.

For Chinese web-fiction authors already comfortable with file-based agents, the project is worth a controlled pilot on a copy of an existing project or a short new work. For everyone else, its greatest value may be architectural: it demonstrates how to turn a vague creative request into staged, inspectable work. The failed overall test command means we would validate dashboard behavior locally before relying on it for a live manuscript, but the active maintenance and unusually concrete process design justify that effort.

Alternatives

ProjectWhat it isPick it when
Anthropic Skills gh↗A general collection of reusable agent skills rather than a fiction-specific production system.Pick this instead when you want official, broad skill examples and plan to assemble your own writing workflow.
SillyTavern gh↗A local interface centered on character-driven AI conversations and creative roleplay.Pick this instead when interactive character chat matters more than outlines, chapter state, and coding-agent hooks.
Roo Code gh↗An extensible coding-agent environment with custom modes and project automation.Pick this instead when you need a general agent workspace and are prepared to design the fiction process yourself.

What people are saying

  1. [github-trending] worldwonderer/oh-story-claudecode

Sources

  1. worldwonderer/oh-story-claudecode on GitHub
  2. Project releases
  3. English README

More ai tools reviews

claudian · SkillSpector · robin · mjlab · MoGe · awesome-design-md · the whole board →