review-schema-first
Review schema as a single source of truth (Schema-first)
Skill by yida29
Chalk Labs
Need help deploying review-schema-first?
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/yida29-review-schema-first-a3c7c7
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/review-schema-first
What's inside
- Skill name
review-schema-first- Description
- Review schema as a single source of truth (Schema-first)
- License
- MIT
- Instructions
- 24 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Schema-first review — single source of truth & contracts Audit whether the project has **one authoritative schema**, and whether all producers/consumers conform. ## Scope Use `$ARGUMENTS` to select the schema (default: the main JSON/data contract) and its producers/consumers. ## Checklist - Where is the **authoritative schema**? (JSON Schema / OpenAPI / protobuf / TS types) - Is it duplicated as hand-written TS interfaces elsewhere? - Do validators enforce the same rules as the schema? - Are there **multiple variants** (input vs processed output)? If yes, are they explicitly versioned? - Do templates/examples/docs match the schema? - Is the schema reference URL **pinned** (tagged) vs `main`? ## Output format 1. **SSoT map**: schema file(s) + all producers/consumers 2. **Divergences** (schema vs code vs docs), with file paths 3. **Minimum path to Schema-first** - e.g. split input/output schemas, generate types, use a single validator $ARGUMENTS
From yida29/archrip, MIT.
More from yida29/archrip
- 0.488score
archrip-scan
yida29
Scan codebase and generate architecture diagram data
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
archrip-update
yida29
Update or refine the architecture diagram
SkillCFreshness: C★ 1Claude Code +9 - 0.426score
review-srp
yida29
Review codebase for SRP (Single Responsibility) and boundaries
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
review-supply-chain
yida29
Review supply-chain and code-execution risks
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
review-ux-diagnostics
yida29
Review UX and diagnostics (errors, hints, verbose mode)
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
review-dry
yida29
Review codebase for DRY (duplication) issues
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
review-typescript-strict
yida29
TypeScript Strict Modeガイドラインを適用してコードレビュー・修正を行う。
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
commit
yida29
diff分析 → 論理的に分割コミット。conventional commitメッセージを自動生成。
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
review-error-handling
yida29
Review error handling consistency and debuggability
SkillDFreshness: D★ 1Claude Code +9 - 0.418score
review-test-strategy
yida29
Review test strategy and regression resistance
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Feb 17, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/yida29/archrip
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from yida29
- 0.488score
archrip-scan
yida29
Scan codebase and generate architecture diagram data
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
archrip-update
yida29
Update or refine the architecture diagram
SkillCFreshness: C★ 1Claude Code +9 - 0.426score
review-srp
yida29
Review codebase for SRP (Single Responsibility) and boundaries
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
review-supply-chain
yida29
Review supply-chain and code-execution risks
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
review-ux-diagnostics
yida29
Review UX and diagnostics (errors, hints, verbose mode)
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
review-dry
yida29
Review codebase for DRY (duplication) issues
SkillDFreshness: D★ 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 review-schema-first 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
review-schema-first skill. Agent Mart. https://agentmart.dev/skills/yida29-review-schema-first-a3c7c7 (last updated 2026-10-24)