ignite
Novel ignition ritual for story-bible: 3-line 'previously on' + one pulling question.
Skill by 1337hero
Chalk Labs
Need help deploying ignite?
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/1337hero-ignite
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: writing
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/ignite
What's inside
- Skill name
ignite- Description
- Novel ignition ritual for story-bible: 3-line 'previously on' + one pulling question. Body-double for getting into writing state, zero obligation. Trigger: /ignite, 'ignite', 'novel time', 'story time'.
- License
- WTFPL
- Instructions
- 24 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Ignite — story-bible ignition ritual
Mike wants to finish the novel in 2026. The constraint is ADHD ignition, not ability: progress comes in bursts, and bursts need a way in. You are the way in — a body-double, not a ghost-writer.
**The attempt counts even if no writing happens. Never guilt, never mention streaks, never list tasks.**
## Steps
1. **Read** (from `~/Documents/story-bible`): the characters file(s), then the most recent draft in `Drafts/` (highest-numbered chapter). Skim earlier chapters only if needed for continuity.
2. **Previously on** — exactly 3 lines, written in the book's own tone, ending mid-tension. Not a summary; a re-entry. The goal is that Mike feels the scene again.
3. **One question.** Ask exactly one question about what happens *next in the story* — the kind that pulls: a character's impossible choice, a consequence left hanging, a door the last scene opened. Never craft questions ("what's your theme?"), never process questions ("want to outline?"). Story questions only.
4. **Then follow his lead:**
- If he engages → co-explorer mode. Discuss, push back, hold continuity against the characters file, offer alternatives when asked. Draft prose only if he explicitly asks; his voice writes the book.
- If he redirects ("actually let's fix chapter 2") → follow.
- If he doesn't bite → one line, warm, out: "Not tonight — Varga will keep." Close. No follow-up question, no second attempt.
## Tone
The register of the original late-night conversations: curious, unhurried, treating the story as real. This is the one project on the machine that never needed rescuing — respect that.From 1337hero/claude-toolkit, WTFPL.
More from 1337hero/claude-toolkit
- 0.502score
llama-tune
1337hero
Empirically tune GGUF model's llama-swap/llama.cpp config for multi-GPU rig — card placement, KV-cache quant, context length, batch sizes, prompt-cache…
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
frontend-philosophy
1337hero
React/Preact frontend conventions: TanStack Query for server state, 8-section components, no TypeScript, no barrel files.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
ponytail
1337hero
Forces laziest solution that works — simplest, shortest, most minimal.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
ponytail-audit
1337hero
Whole-repo audit for over-engineering.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
ponytail-review
1337hero
Code review hunting over-engineering only.
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
codebase-documenter
1337hero
Write codebase docs: README, architecture, API, comments.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
caveman
1337hero
Ultra-compressed communication mode.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
frontend-design
1337hero
Create distinctive frontend interfaces: components, pages, dashboards, React, HTML/CSS.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
announce
1337hero
Run the announcement round for a finished project: attribution check, directory submissions, launch-post drafts in Mike's voice.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
improve-codebase-architecture
1337hero
Find architecture improvements: consolidate modules, improve testability and AI navigation.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
playwright-skill
1337hero
Browser automation with Playwright.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
browser-tools
1337hero
Drive VISIBLE Chrome with real profile/logins (CDP :9222).
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 9, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- WTFPL
- Repository
- github.com/1337hero/claude-toolkit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from 1337hero
- 0.502score
llama-tune
1337hero
Empirically tune GGUF model's llama-swap/llama.cpp config for multi-GPU rig — card placement, KV-cache quant, context length, batch sizes, prompt-cache…
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
frontend-philosophy
1337hero
React/Preact frontend conventions: TanStack Query for server state, 8-section components, no TypeScript, no barrel files.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
ponytail-audit
1337hero
Whole-repo audit for over-engineering.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
ponytail
1337hero
Forces laziest solution that works — simplest, shortest, most minimal.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
ponytail-review
1337hero
Code review hunting over-engineering only.
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
codebase-documenter
1337hero
Write codebase docs: README, architecture, API, comments.
SkillCFreshness: C★ 1Claude 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 ignite 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
ignite skill. Agent Mart. https://agentmart.dev/skills/1337hero-ignite (last updated 2026-10-24)