Inkos
This is a full-stack autonomous novel writing system built around a multi-agent pipeline that takes you from creative brief to finished EPUB with zero intervention per chapter. It runs a three-phase loop (creative writing at temp 0.7, state settlement with schema validation, then 33-dimension quality audits with auto-revision) and maintains seven truth files so your world state and character arcs stay consistent across long-form work. Native English support covers ten genre profiles like LitRPG and progression fantasy, plus Chinese web novel genres. The standout piece is the hook ledger system that tracks narrative payoffs across chapters, and the InkOS Studio web UI gives you visual book management, real-time progress, and cover generation. If you're prototyping serialized fiction or need to crank out consistent chapters at scale, this handles the orchestration.
- skills.sh installs
- 638
- GitHub stars
- 11.1K
- last updated
- Jun 3, 2026
Install
$ npx -y skills add narcooo/inkos --skill inkos --agent claude-codeInstalls into .claude/skills of the current project.
Files
InkOS Creative Harness
InkOS is a text-creation harness. The main Pi agent understands the request, activates professional Skills, invokes typed capability actions, and reports only persisted results.
Core contract
- Discussion stays discussion. Creation and mutation happen only through capability actions.
- A successful action is proven by its
ActionResultand artifact revision, never by assistant prose. - User intent, current Work constraints, established facts, and explicit prohibitions outrank model defaults.
- Skills provide professional methods but never grant write permission.
- Review returns evidence-backed observations. It does not score prose, reject a chapter, or authorize an automatic rewrite.
- Revision is an explicit action. Preserve source revisions and report the new artifact revision.
- Context is assembled per task: LLM semantic selection chooses relevant source sections after deterministic candidate discovery. Protected intent and selected current facts are never compressed; lower-priority context is semantically compiled only on budget overflow.
Creation profiles
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/narcooo/inkos
- First seen
- Jun 3, 2026
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs