Agent skill

Continuity Check

by Ckokoski in Ckokoski/AuthorAgent

Scan manuscript for inconsistencies in characters, timeline, settings, and names

MITAuto-check passed

Install Continuity Check

skills CLI
$ npx skills add Ckokoski/AuthorAgent --skill continuity-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ckokoski/AuthorAgent continuity-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ckokoski/AuthorAgent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/author/continuity-check .claude/skills/continuity-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
continuity-check
GitHub stars
123
Token cost
~1.5k tokens
SKILL.md length
735 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Scan manuscript for inconsistencies in characters, timeline, settings, and names

  • Works in 5 steps: Character Consistency → Timeline and Chronology → Setting and World Details → …
  • SKILL.md covers What to Check, Severity Levels, Output Format and Guidelines
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Continuity Check is an agent skill from Ckokoski/AuthorAgent. Scan manuscript for inconsistencies in characters, timeline, settings, and names

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The Autonomous AI Writing Agent — a secure, author-focused AI for fiction and nonfiction authors (Planning, Revision, Promotion, and more). The licence is MIT.

Example prompts

  • “/continuity-check”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Character Consistency
  2. Timeline and Chronology
  3. Setting and World Details
  4. Names and Terminology
  5. Plot Threads and Objects

What it can do on your machine

Read from SKILL.md and the folder at commit 47e9570. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Continuity Check loads about 1.5k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 735 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ckokoski/AuthorAgent at commit 47e9570, republished under its MIT licence (© Ckokoski). 735 words, ~1,455 tokens.

Download SKILL.mdSave it as .claude/skills/continuity-check/SKILL.md (or your agent's skills folder).
name
continuity-check
description
Scan manuscript for inconsistencies in characters, timeline, settings, and names
author
AuthorAgent
version
1.0.0
triggers
continuity, continuity check, consistency check, find inconsistencies, timeline check, plot holes, check continuity
permissions
file:read

Continuity Check Skill

Scan a manuscript (or set of chapters) for internal inconsistencies. This is not a style review — the goal is to catch factual contradictions within the text itself.

What to Check

1. Character Consistency
  • Physical descriptions: Eye color, hair, height, scars, tattoos — flag if described differently in two places.
  • Age and aging: Does a character's stated age match the timeline? Do children age appropriately between scenes set years apart?
  • Abilities and limitations: A character who can't swim in chapter 3 shouldn't be diving in chapter 12 without explanation.
  • Personality and knowledge: Flag moments where a character suddenly knows something they shouldn't, or behaves in a way that contradicts established traits without narrative justification.
  • Relationships: If two characters are introduced as strangers, they shouldn't reference shared history later (unless a reveal is intended).
2. Timeline and Chronology
  • Event order: Do flashbacks, references to past events, and "three days later" markers add up?
  • Travel time: If two cities are a week's ride apart, a character shouldn't arrive the next morning.
  • Day/night and seasons: If a scene starts at dusk, it shouldn't be noon two paragraphs later without a time skip. Winter shouldn't become summer in a single chapter unless time passes.
  • Parallel scenes: When cutting between storylines, do the timelines stay in sync?
  • Dates and ages: Any specific dates, years, or stated ages must remain consistent throughout.
3. Setting and World Details
  • Geography: A river that flows north in one chapter shouldn't flow south in another. Room layouts, building locations, and distances should stay fixed.
  • World rules: If magic costs energy, characters shouldn't cast freely without consequence. Technology, physics, and social rules must stay consistent.
  • Named places: Spelling and descriptions of locations should not change (e.g., "Thornfield Inn" vs "Thornfeld Inn").
  • Climate and environment: Vegetation, weather patterns, and environmental details should match the established region.
4. Names and Terminology
  • Character names: First names, surnames, nicknames, and titles must be spelled consistently. Flag any drift (e.g., "Katherine" in chapter 1 vs "Catherine" in chapter 8).
  • Place names: Same rule — no unexplained spelling changes.
  • Invented terms: Made-up words, species, technologies, or organizations should be spelled and capitalized the same way every time.
  • Titles and ranks: If a character is a Captain, they shouldn't be called Lieutenant later without a demotion scene.
5. Plot Threads and Objects
  • Chekhov's guns: Note significant objects or plot threads that are introduced but never resolved.
  • Resolved threads: Flag threads that are resolved without adequate setup.
  • Object tracking: If a character drops a sword in a fight, they shouldn't be holding it two scenes later without picking it up.
  • Information flow: If a secret is revealed to Character A in chapter 5, other characters shouldn't know it in chapter 6 unless told on-page or plausibly off-page.
Show full SKILL.md (277 more words)Show less

Severity Levels

Categorize every finding into one of three levels:

ERROR — Definite contradiction

Two statements in the manuscript directly contradict each other. The reader will notice.

Example: "His green eyes narrowed" (ch. 2) vs "She looked into his brown eyes" (ch. 14)

WARNING — Probable inconsistency

Something looks wrong but could be intentional. Needs the author's judgment.

Example: A character who is terrified of heights willingly climbs a tower without internal conflict or acknowledgment.

INFO — Worth verifying

A detail that appears only once and could cause problems later, or a minor drift that might be a typo.

Example: A side character's name appears only twice, spelled slightly differently each time.

Output Format

Organize findings by category. For each finding, include:

[ERROR|WARNING|INFO] Category — Short description
  Evidence: "exact quote" (Chapter X / location)
  Conflicts with: "exact quote" (Chapter Y / location)
  Suggestion: How to resolve the inconsistency
Summary Section

After all findings, provide a summary:

Continuity Check Summary
========================
Errors:   X
Warnings: X
Info:     X

Most affected areas: [list the chapters or sections with the most issues]

Guidelines

  • Quote the text. Every finding must reference specific passages. Never say "somewhere in chapter 3" — give the actual line or paragraph.
  • Do not flag style choices. A character behaving unexpectedly is not an error if the narrative frames it as surprising. Only flag contradictions, not creative decisions.
  • Check the Book Bible first. If a Book Bible exists in workspace/memory/book-bible/, cross-reference it for established facts. If no Book Bible exists, build your reference from the manuscript text itself.
  • Work systematically. Read through the manuscript tracking facts on the first pass, then scan for contradictions on the second. Do not try to do both at once.
  • Group related issues. If the same character's name is misspelled five times, that is one finding with five instances, not five separate findings.
  • Be precise, not exhaustive. Ten real issues are more useful than fifty maybes. When in doubt, use INFO level rather than WARNING.

© Ckokoski, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/author/continuity-check of Ckokoski/AuthorAgent.

Open the folder on GitHubat commit 47e9570

Compare with similar skills

Continuity Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Continuity Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Continuity Check this skillCkokoski/AuthorAgent123—~1.5kAutomated safety check: PassMIT
Scanwshobson/agents40k—~2.2kAutomated safety check: PassMIT
Repo Scanaffaan-m/ECC276k—~1.5kAutomated safety check: PassMIT
Repo Scanaffaan-m/ECC276k—~1.3kAutomated safety check: PassMIT
Continuetelegramdesktop/tdesktop33k2 repos~9.4kAutomated safety check: PassGPL-3.0
Vulnerability Scanningsickn33/agentic-awesome-skills47k1 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • Scan

    wshobson/agents

    Scans the codebase to generate project-doc.md and AGENTS.md.

    40k GitHub stars~2.2k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Repo Scan

    affaan-m/ECC

    固定されレビュー可能なコミットから外部の repo-scan スキルをインストールするブートストラップ用ポインター。クロススタックのソースコード資産監査を実行する前に repo-scan のインストールが必要な場合に使用する。この ECC ポインター自体は監査を実行しない。

    276k GitHub stars~1.5k tokensUpdated 4 days ago
    Auto-check passed
  • Repo Scan

    affaan-m/ECC

    用于从固定且可审查的提交安装外部 repo-scan 技能的引导指针。在运行跨栈源代码资产审计前需要安装 repo-scan 时使用;此 ECC 指针本身不执行审计。

    276k GitHub stars~1.3k tokensUpdated 4 days ago
    Auto-check passed
  • Continue

    telegramdesktop/tdesktop

    Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.

    33k GitHub starsUsed in 2 repos~9.4k tokens
    Productivity & AutomationAuto-check passed
  • Vulnerability Scanning

    sickn33/agentic-awesome-skills

    Scan systems and dependencies for CVEs and security vulnerabilities.

    47k GitHub starsUsed in 1 repo~2.8k tokens
    SecurityAuto-check passed
  • Repo Scan

    affaan-m/ECC

    Bootstrap pointer that installs the external repo-scan skill from a pinned, reviewable commit.

    276k GitHub starsUsed in 1 repo~1.8k tokens
    DevelopmentAuto-check passed

More from Ckokoski/AuthorAgent

All 23 skills in this repo
  • After Action Review

    Ckokoski/AuthorAgent

    Structured post-goal reflection that extracts lessons, evaluates quality, and feeds the self-improvement loop

    123 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Comp Title Finder

    Ckokoski/AuthorAgent

    Find and analyze comparable titles for query letters, marketing, and positioning strategy

    123 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Deep Voice Analysis

    Ckokoski/AuthorAgent

    Advanced 47-marker voice analysis engine — analyzes your writing to build a comprehensive Voice Profile for AuthorClaw

    123 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Dictation Cleanup

    Ckokoski/AuthorAgent

    Transform raw speech-to-text dictation into polished prose while preserving the author's natural voice

    123 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Error Recovery

    Ckokoski/AuthorAgent

    Intelligent error diagnosis, automatic recovery strategies, and prevention of recurring failures

    123 GitHub stars~1.7k tokensUpdated 2 mo ago
    Auto-check passed
  • First Chapter Hook

    Ckokoski/AuthorAgent

    Analyze and rewrite first chapters for maximum reader retention using genre-specific hook patterns

    123 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Continuity Check

What does Continuity Check do?

Scan manuscript for inconsistencies in characters, timeline, settings, and names. Continuity Check is an agent skill from Ckokoski/AuthorAgent.

How do I install Continuity Check in Claude Code?

Run `npx skills add Ckokoski/AuthorAgent --skill continuity-check -a claude-code`. Or copy the skill folder (skills/author/continuity-check in Ckokoski/AuthorAgent) into .claude/skills/continuity-check in your project. Claude Code loads it when a task matches its description.

How do I install Continuity Check in Codex?

Run `npx skills add Ckokoski/AuthorAgent --skill continuity-check -a codex`. Or copy the skill folder (skills/author/continuity-check in Ckokoski/AuthorAgent) into .agents/skills/continuity-check in your project. Codex loads it when a task matches its description.

Can I use Continuity Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ckokoski/AuthorAgent --skill continuity-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/continuity-check, .gemini/skills/continuity-check, .github/skills/continuity-check and .opencode/skills/continuity-check in your project.

What does Continuity Check need to run?

SKILL.md names no scripts, command-line tools or credentials: Continuity Check is instructions for the agent only.

Does Continuity Check access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Continuity Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Continuity Check use?

Continuity Check is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Continuity Check use?

About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Continuity Check?

Skills that share tags, products or a category with Continuity Check: Scan (wshobson/agents, 40k stars), Repo Scan (affaan-m/ECC, 276k stars), Repo Scan (affaan-m/ECC, 276k stars) and Continue (telegramdesktop/tdesktop, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Continuity Check?

Ckokoski (a GitHub user) maintains it in Ckokoski/AuthorAgent, which has 123 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on July 11, 2026.

Source: Ckokoski/AuthorAgent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.