story-bible
Build, reconcile, and retrieve an internal fiction wiki from manuscripts and author notes, preserving evidence, canon status, chronology, and character…
Skill by atrnh
Chalk Labs
Need help deploying story-bible?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/atrnh-story-bible
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/story-bible
What's inside
- Skill name
story-bible- Description
- Build, reconcile, and retrieve an internal fiction wiki from manuscripts and author notes, preserving evidence, canon status, chronology, and character knowledge. Use for maintaining story references or assembling focused context packets.
- License
- MIT
- Instructions
- 62 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- openai.yaml · agents/
- structure.md · references/
SKILL.md (first lines)
# Story bible Maintain the author's internal fiction wiki in the chosen destination. Use the existing organization when it supports the task. For a new story bible, follow [the default structure and entry patterns](references/structure.md), creating only sections supported by the available material. Keep each fact's primary home clear, and link related entries rather than maintaining duplicate accounts. Before reading, recording, or reviewing fiction, read and follow [the editorial contract](../references/editorial-contract.md). ## Ground rules - Give each claim the narrowest applicable status. Status belongs to individual claims; never assign one status to a whole character, place, scene, or page. - **Established:** Reliably established by the manuscript. - **Author decision:** Confirmed privately by the author, whether or not the manuscript reveals it. - **Planned:** Intended but still changeable. - **Possibility:** An option under consideration. - **Inference:** A reading supported by the text but not confirmed. - **Superseded:** Retained for history but no longer current. - **Needs reassessment:** Previously supported, but its supporting evidence is no longer current. Preserve the former evidence; do not present the claim as currently established or disproved. - **Conflict:** Two sources or claims require resolution. Preserve both until the author resolves them. - Record attributed statements separately from the propositions they assert when needed, following the editorial contract. - Record enough provenance to find the evidence again. For manuscript facts, identify the draft or version, stable location, and shortest useful passage. Record a revision date when available; do not invent a version or infer authority from recency alone. For private decisions, identify the author source and date or conversation context. - Use the author's chosen wiki as the system of record. Manuscript sources may live elsewhere. Do not create a parallel wiki or synchronization layer unless requested. ## Choose the operation ### Build Read the requested source material within the stated scope. Inspect the chosen destination before creating anything. Organize claims where the author will look for them, reusing existing entries and conventions. Include private decisions, plans, and possibilities when in scope, with their author sources and statuses. Read [the structure reference](references/structure.md) before creating or organizing entries. Adapt its sections to the destination and the amount of material. Preserve existing paths, page organization, and unrelated page properties; propose any needed migration separately. Keep drafts and editorial feedback in their chosen locations and link to them where useful. Record only source-backed claims. Keep these distinctions explicit wherever they matter: - what happens in world chronology and when the narrative reveals it; - what is true in the world and what each character knows at a given point; - source-universe canon, story canon, and deliberate departures between them. Link related claims when that improves retrieval. Do not fill empty categories or invent details for completeness. ### Update or reconcile Read the existing wiki entries and their cited sources before editing. Change the narrowest affected claims. Add new provenance rather than replacing useful evidence. Honor explicit replacement relationships between drafts. If the author designates draft 2 as replacing draft 1 and a coat changes from red to blue, update the current claim and mark the replaced claim Superseded with its original evidence. A later timestamp alone does not make a draft authoritative. If a revision removes a claim's only support, mark it Needs reassessment and identify the lost support. Do not continue presenting it as currently established or assume its opposite is true. Preserve independently confirmed author decisions. Reserve Conflict for incompatible simultaneously current sources or unclear revision intent. Preserve both claims and ask for resolution rather than choosing by preference. When resolved, record the decision and retain superseded evidence as history. ### Retrieve Answer from the current chosen wiki and cited source material. State claim status and provenance close to the answer. Separate established facts and author decisions from plans, possibilities, inferences, superseded ideas, claims needing reassessment, and unresolved conflicts. Say when the wiki does not support an answer. ### Assemble a context packet Build the smallest packet that supports the stated task. Include its purpose, source scope, spoiler boundary, relevant claims with statuses and provenance, event versus reveal order, character knowledge at the relevant point, applicable canon departures, and unresolved conflicts. Omit unrelated lore and private decisions outside the requested working scope. ## Verify changes After a write, read back every changed entry in the chosen destination. Check claim status, provenance, chronology versus reveal order, character knowledge, and canon scope where applicable. Report what changed and any claim, conflict, or source location that could not be verified. Check that new entries are reachable from the bible's home or a section index, internal links resolve, and repeated summaries point to the claim's primary home. Remove empty placeholders created during the operation; preserve the author's existing material.
From atrnh/skills, MIT.
More from atrnh/skills
- 0.570score
create-lecture
atrnh
Generates a structured lecture from an unordered list of topics.
SkillAFreshness: AClaude Code +9 - 0.570score
create-mcq
atrnh
Generates multiple choice questions (MCQs) from text or documents provided by the user.
SkillAFreshness: AClaude Code +9 - 0.570score
review-fiction
atrnh
Reviews a chapter of the user's fiction and produces a two-column HTML critique page beside the manuscript, with the prose on the left and anchored comments…
SkillAFreshness: AClaude Code +9 - 0.570score
deep-quality-review
atrnh
Reviews any written material (docs, guides, lectures, labs, READMEs, essays, proposals, specs, emails) for both functional quality and deep quality, using the…
SkillAFreshness: AClaude Code +9 - 0.565score
student-question-pass
atrnh
Reviews curriculum material by roleplaying as a target learner, adding student questions as source comments, then interactively turning selected questions…
SkillAFreshness: AClaude Code +9 - 0.565score
line-editor
atrnh
Use when the author wants a line edit, prose notes, or sentence-level feedback on a fiction chapter, scene, or passage.
SkillAFreshness: AClaude Code +9 - 0.565score
triage-feedback
atrnh
Use after an agent or reviewer has produced a batch of proposed changes to text files, such as a deep-quality review, Bugbot or code-review findings, a…
SkillAFreshness: AClaude Code +9 - 0.565score
beep
atrnh
Write and send communications on Ashley's behalf as Beep, her clearly identified robot assistant.
SkillAFreshness: AClaude Code +9 - 0.565score
vaultit
atrnh
Save an assistant response to Obsidian from supplied text, a chat link or message reference, or the immediately preceding response.
SkillAFreshness: AClaude Code +9 - 0.565score
review-lab
atrnh
Reviews lab content drafts from subject matter experts and provides structured editorial feedback.
SkillAFreshness: AClaude Code +9 - 0.561score
grill-my-story
atrnh
Interview a fiction author to explore an uncertain story idea or pressure-test a premise, character choice, scene, or plot problem.
SkillAFreshness: AClaude Code +9 - 0.561score
developmental-editor
atrnh
Give candid developmental critique of fiction or a spoiler-bounded first-reader response, with feedback delivered in the author's chosen workflow.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/atrnh/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from atrnh
- 0.570score
deep-quality-review
atrnh
Reviews any written material (docs, guides, lectures, labs, READMEs, essays, proposals, specs, emails) for both functional quality and deep quality, using the…
SkillAFreshness: AClaude Code +9 - 0.570score
create-lecture
atrnh
Generates a structured lecture from an unordered list of topics.
SkillAFreshness: AClaude Code +9 - 0.570score
create-mcq
atrnh
Generates multiple choice questions (MCQs) from text or documents provided by the user.
SkillAFreshness: AClaude Code +9 - 0.570score
review-fiction
atrnh
Reviews a chapter of the user's fiction and produces a two-column HTML critique page beside the manuscript, with the prose on the left and anchored comments…
SkillAFreshness: AClaude Code +9 - 0.565score
line-editor
atrnh
Use when the author wants a line edit, prose notes, or sentence-level feedback on a fiction chapter, scene, or passage.
SkillAFreshness: AClaude Code +9 - 0.565score
student-question-pass
atrnh
Reviews curriculum material by roleplaying as a target learner, adding student questions as source comments, then interactively turning selected questions…
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get story-bible running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
story-bible skill. Agent Mart. https://agentmart.dev/skills/atrnh-story-bible (last updated 2026-10-24)