verification-loop
Run a practical quality gate before closing work — typecheck, sync/consistency check, and task-specific validation.
Skill by signalo-rust
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/signalo-rust-verification-loop
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: not checked yet.
What's inside
- Skill name
verification-loop- Description
- Run a practical quality gate before closing work — typecheck, sync/consistency check, and task-specific validation. Scale the checks to the size of the change.
- License
- MIT
- Instructions
- 36 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Verification Loop Use this before considering a meaningful task complete. ## Baseline Checks Run the smallest complete set that matches the task. ### Default - run the repo's sync/consistency check ### Code Changes - run the type checker - run the repo's sync/consistency check ### Larger or Cross-Package Changes - run the full verify pipeline (typecheck + sync check + build) ## Task-Specific Additions - Prisma/schema work: - regenerate the ORM client - run the migration - package-local build checks: - build the affected workspace package(s) individually ## Final Review Questions - Did we update delivery docs? - Did we preserve the API contract, or change it intentionally? - Did we introduce new env vars, migrations, or storage assumptions? - Did we leave debug logging or incomplete TODOs behind?
From signalo-rust/ai-guardrails, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 11, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/signalo-rust/ai-guardrails
- 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 signalo-rust
- 0.497score
anti-bug-prevention
signalo-rust
Production deploy safety pipeline.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
brainstorm-first
signalo-rust
Before starting any non-trivial task (>0.5 day, new feature, new UI page, new integration, refactor spanning >5 files), it is mandatory to ask the requester…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
api-contract-audit
signalo-rust
Inventory every API endpoint that surfaces a field to clients BEFORE dropping, renaming, or semantically changing it.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
content-hash-cache-pattern
signalo-rust
Cache expensive file processing results via SHA-256 content hashes — path-independent, auto-invalidating, service layer separation.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
docker-push-verify
signalo-rust
After `docker buildx build --push`, always verify the image actually landed on the upstream registry.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
eval-harness
signalo-rust
Formal eval-driven development (EDD) framework.
SkillCFreshness: C★ 1Claude Code +9
Cite this page
verification-loop skill. Agent Mart. https://agentmart.dev/skills/signalo-rust-verification-loop (last updated 2026-10-24)