SkillsAdd

smithery.ai

determinism

Design machine-checkable assertions, stable hashes, fixtures, and exit-code contracts for behavior that must be reproducible.

First seen Apr 17, 2026

Installation

$ npx skills add https://smithery.ai
View on skills.sh ↗ Website ↗

Summary

  • Design machine-checkable assertions, stable hashes, fixtures, and exit-code contracts for behavior that must be reproducible.
  • Use when an outcome currently depends on subjective agent judgment or when prompts and generated artifacts need versioned integrity checks.
  • Do not use merely to run an existing repository verification gate; that is verify's job.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

agent-browser Shared topics
vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…

810.4K installs
vercel-react-best-practices Shared topics
vercel-labs/agent-skills 697.8K installs
web-design-guidelines Shared topics
vercel-labs/agent-skills

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…

617.3K installs
microsoft-foundry Shared topics
microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …

576.5K installs
azure-hosted-copilot-sdk Shared topics
microsoft/azure-skills 440.4K installs
azure-enterprise-infra-planner Shared topics
microsoft/azure-skills

Architect and provision enterprise Azure infrastructure from workload descriptions. For cloud a…

402.8K installs

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai
smithery-ai-cli 7.8K frontend-design 6.2K skill-creator 2.5K ck:ui-ux-pro-max 1.3K pdf 1.2K xlsx 966 pptx 894 docx 884 webapp-testing 1 web-design-reviewer 657

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,463 B
  • docs SUMMARY.md 309 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

Determinism

Turn a repeated judgment into an executable contract.

Procedure

  1. Name the exact input, expected invariant, and authoritative readback.
  2. Use the simplest deterministic mechanism: parser, schema, fixture, checksum, query, or narrow test.
  3. Return a meaningful exit status: 0 for satisfied, nonzero for a specific failure class.
  4. Keep diagnostics compact and stable enough for another script or agent to consume.
  5. Version prompts or generated contracts when their semantics affect the result; record a hash when drift must be detected.
  6. Prove both a passing case and a deliberately failing case.

Boundary

  • determinism designs the assertion or integrity mechanism.
  • verify selects and runs the repository's declared gates.
  • testing skills construct broader behavioral test suites.

References

  • [references/code-verification.md](references/code-verification.md) — executable assertion patterns.
  • [references/prompt-versioning.md](references/prompt-versioning.md) — semantic versions and hashes for prompt contracts.