grace
Route Grace repository work to current workflow, domain, contract, runtime, testing, and documentation guidance.
Skill by ScottArbeit
Chalk Labs
Need help deploying grace?
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/scottarbeit-grace
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: documents, testing, 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/grace
What's inside
- Skill name
grace- Description
- Route Grace repository work to current workflow, domain, contract, runtime, testing, and documentation guidance.
- License
- MIT
- Instructions
- 32 lines in SKILL.md · view on GitHub
Files (12)
- SKILL.md
- openai.yaml · agents/
- actors-and-durability.md · references/
- contracts-and-shared.md · references/
- docs-and-contributing.md · references/
- project-map.md · references/
- public-surfaces.md · references/
- runtime-and-storage.md · references/
- security-and-auth.md · references/
- specification-profile.md · references/
- tests.md · references/
- workflow.md · references/
SKILL.md (first lines)
# Grace Read root and nearest AGENTS.md before editing. For non-trivial tracked work, use the repository's docs/Development process.md and installed `dev-process`. Current source and live tracker evidence determine implementation facts. ## Load the relevant context | Task | Reference | | --- | --- | | Repository layout and project boundaries | [Project map](references/project-map.md) | | Tracker, branch, review, validation, or cleanup | [Workflow](references/workflow.md) | | Specification and readiness | [Specification profile](references/specification-profile.md), with installed specification | | DTOs, events, parameters, serializers, shared code | [Shared contracts](references/contracts-and-shared.md) | | HTTP, SDK, CLI, authorization at public entrypoints | [Public surfaces](references/public-surfaces.md) | | Orleans, event sourcing, replay, durable transitions | [Actors and durability](references/actors-and-durability.md) | | RBAC, PATs, OIDC, TestAuth, path permissions | [Security](references/security-and-auth.md) | | Uploads, manifests, ContentBlocks, Service Bus, Aspire | [Runtime and storage](references/runtime-and-storage.md) | | Selecting or changing tests | [Tests](references/tests.md) | | Contributor, product, or workflow documentation | [Docs](references/docs-and-contributing.md) | Load only the references needed for the current slice. The installed `specification` owns feature lifecycle and traceability; `design-readiness` resolves open product/domain/architecture choices; `dev-process` owns delivery. Avoid repeating their full checklists here. ## Grace-specific defaults Grace uses Product V1 unless the owner chooses another profile. It has no production legacy data; add compatibility or migration behavior only for a requirement that actually exists. Prefer a vertical slice through the nearest stable public boundary. Propagate a changed public or durable contract through the relevant Types, Shared, Server, Actors, SDK, CLI, generated artifacts, docs, and tests. Preserve established Grace vocabulary. Use focused local evidence and required GitHub Validate on the final PR revision. Local Fast is optional broad preflight; Full is for integration reproduction or diagnosis. The repository owns current commands and project membership. Planning-only requests remain planning. Tracker setup and implementation follow the user's requested scope. Use PowerShell and Markdown skills for generated scripts and documents, with PowerShell examples before bash / zsh where applicable. Explain unresolved product decisions through concrete user behavior.
From ScottArbeit/Grace, MIT.
More from ScottArbeit/Grace
- 0.747score
code-review-stabilizer
ScottArbeit
Compatibility entrypoint for older Grace review-recovery prompts; route to the current dev-process review protocol.
SkillBFreshness: B★ 590Claude Code +9 - 0.526score
AGENTS.md · ScottArbeit/Grace
ScottArbeit
AGENTS.md from ScottArbeit/Grace: 122 lines covering Agent Quickstart (Local), Issue Tracking, Development Process, Markdown Guidelines and more.
TemplateBFreshness: B★ 590Codex +5
Signals
- Stars
- 590
- Forks
- 19
- Open issues
- 52
- Last commit (this folder)
- Sep 5, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ScottArbeit/Grace
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ScottArbeit
- 0.747score
code-review-stabilizer
ScottArbeit
Compatibility entrypoint for older Grace review-recovery prompts; route to the current dev-process review protocol.
SkillBFreshness: B★ 590Claude Code +9 - 0.526score
AGENTS.md · ScottArbeit/Grace
ScottArbeit
AGENTS.md from ScottArbeit/Grace: 122 lines covering Agent Quickstart (Local), Issue Tracking, Development Process, Markdown Guidelines and more.
TemplateBFreshness: B★ 590Codex +5
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 grace 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
grace skill. Agent Mart. https://agentmart.dev/skills/scottarbeit-grace (last updated 2026-10-24)