auto-rolling-roadmap
Maintain ROADMAP.md as the project's living product, architecture, and long-horizon development checkpoint.
Skill by CardSorting
Chalk Labs
Need help deploying auto-rolling-roadmap?
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/cardsorting-auto-rolling-roadmap
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
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/auto-rolling-roadmap
What's inside
- Skill name
auto-rolling-roadmap- Description
- Maintain ROADMAP.md as the project's living product, architecture, and long-horizon development checkpoint. Use when steering project direction, updating roadmap checkpoints, or resolving code soup drift.
- License
- Apache-2.0
- Instructions
- 965 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- body: 965 lines (spec recommends under 500)
Files (1)
- SKILL.md
SKILL.md (first lines)
# DietCode Skill: Auto-Rolling Roadmap Checkpoint System ## Skill Purpose Maintain an evolving `ROADMAP.md` file that acts as the project's living product, architecture, and long-horizon development checkpoint. This skill exists to prevent code soup, preserve project coherence, and keep long-running development aligned around a clear center of gravity. The roadmap is not a wishlist. The roadmap is not a backlog. The roadmap is not a promise. The roadmap is the project's steering surface. It should help humans and agents answer: * What is this project becoming? * What matters now? * What should happen next? * What should remain deferred? * What changed recently? * What risks are accumulating? * Is the system becoming more coherent or more fragmented? ## Primary Output This skill must create or update: ```text ROADMAP.md ``` `ROADMAP.md` is the canonical checkpoint file for long-horizon project steering. If the file does not exist, create it. If the file exists, evolve it carefully. Do not replace useful history with generic text. Do not append endlessly. Do not turn the roadmap into a backlog dump. Each update should make the roadmap more useful, more current, and easier to navigate. ## Prime Directive Every roadmap pass must answer: ```text Did the latest work strengthen or weaken the project's center of gravity? ``` If the answer is unclear, the skill must investigate before adding or promoting roadmap items. A roadmap item that does not connect to the project's center of gravity should remain in Discovery, be reframed, or be archived. ## Definition: Center of Gravity The project's center of gravity is the smallest set of concepts, workflows, abstractions, and operational paths that explain how the system fundamentally works. A strong center of gravity means: * there is one obvious way to perform core operations * agents can predict where changes belong * contributors can understand the system without reading everything * new features attach to existing architecture instead of creating parallel systems * operational behavior is inspectable * maintenance burden stays bounded * long-term development feels navigable A weak center of gravity means: * duplicate abstractions appear * multiple workflows compete * state ownership becomes unclear * debugging paths fragment * agents invent local patterns * hidden orchestration grows * roadmap direction becomes disconnected from implementation reality ## Core Philosophy Centralization does not mean giant files, giant classes, or rigid architecture. Centralization means clear authority. Modules may be distributed. Authority should not be. The roadmap should continuously protect: * canonical workflows * canonical mutation paths * canonical runtime inspection * canonical state ownership * canonical terminology * canonical architectural intent The system should feel extensible without becoming incoherent. ## Required Inputs When invoked, inspect available project context before editing `ROADMAP.md`. Use any available sources such as: * existing `ROADMAP.md` * README files * architecture docs * recent commits * changed files * tests * scripts * issue notes
From CardSorting/HEAV3NS-CODE, Apache-2.0.
More from CardSorting/HEAV3NS-CODE
- 0.566score
adversarial-auditor
CardSorting
Adversarial auditor that red-teams technical plans, asserts fail-closed factual provenance, decomposes cognitive token spend, and prevents premature completion.
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
golden-cartridge-protocol
CardSorting
Optimize for verified engineering value with finite context, execution, mutation, and review capacity.
SkillBFreshness: B★ 4Claude Code +9 - 0.561score
code-refactor
CardSorting
Clean architecture refactoring specialist enforcing SOLID principles, strict TypeScript interfaces, and zero barrel imports.
SkillBFreshness: B★ 4Claude Code +9 - 0.561score
performance-auditor
CardSorting
A high-throughput performance auditor that verifies zero-GC boundaries, memory slab invariants, and hot-path execution latencies.
SkillBFreshness: B★ 4Claude Code +9 - 0.561score
security-sentinel
CardSorting
Security sentinel that analyzes ASTs for injection risks, verifies file path sandboxing, and prevents command tampering.
SkillBFreshness: B★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 16, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/CardSorting/HEAV3NS-CODE
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from CardSorting
- 0.566score
adversarial-auditor
CardSorting
Adversarial auditor that red-teams technical plans, asserts fail-closed factual provenance, decomposes cognitive token spend, and prevents premature completion.
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
golden-cartridge-protocol
CardSorting
Optimize for verified engineering value with finite context, execution, mutation, and review capacity.
SkillBFreshness: B★ 4Claude Code +9 - 0.561score
code-refactor
CardSorting
Clean architecture refactoring specialist enforcing SOLID principles, strict TypeScript interfaces, and zero barrel imports.
SkillBFreshness: B★ 4Claude Code +9 - 0.561score
performance-auditor
CardSorting
A high-throughput performance auditor that verifies zero-GC boundaries, memory slab invariants, and hot-path execution latencies.
SkillBFreshness: B★ 4Claude Code +9 - 0.561score
security-sentinel
CardSorting
Security sentinel that analyzes ASTs for injection risks, verifies file path sandboxing, and prevents command tampering.
SkillBFreshness: B★ 4Claude 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 auto-rolling-roadmap 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
auto-rolling-roadmap skill. Agent Mart. https://agentmart.dev/skills/cardsorting-auto-rolling-roadmap (last updated 2026-10-24)