Specverify Base — Testing skill for Claude Code
specverify base — Universal verification pass (7 items).
How to install Specverify Base
Installs to ~/.claude/commands/frmoretto-specverify-specverify-base.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/frmoretto/specverify/HEAD/.claude/commands/specverify-base.md -o ~/.claude/commands/frmoretto-specverify-specverify-base.md Restart Claude Code, or start a new session, for it to be picked up.
What Specverify Base does
name: specverify-base description: "specverify base — Universal verification pass (7 items). Works with any spec format. Runs deterministic pre-check then LLM evaluation."
$ARGUMENTS
Read and follow the full skill protocol at `~/.claude/commands/specverify/SKILL.md`. Execute the **base** pass as described in `~/.claude/commands/specverify/commands/base.md`. The deterministic pre-check script is at `~/.claude/commands/specverify/scripts/precheck.py`. The report template is at `~/.claude
Alternatives in Testing
- Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
- Letta Evals — Evaluation kit for testing stateful agents 83 ★
- Pi Task — Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→researc 81 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Build Verify
Run the full build / test / analyze / format verification pass for this Flutter app.
Phased Engineering Pipeline
Claude Code skill for building software with AI agents: seven roles, vertical-slice phases, deterministic chec
Dapei Skills Pack En
Quality-gate agent skills: spec-as-contract, no-mock rule, evidence-based verification. Three SKILL.md skills
TDD Check
Run the full pre-commit verification suite — pytest, ruff, mkdocs build
AI Evo
Self-hosted AI evaluation platform for LLMs & Agents — 9 eval types with AI judges, datasets, pre-eval scripts
Agent Eval Design
Design an evaluation for an AI agent or LLM feature: what to test, how to grade it, and how to catch regressio
Related Agents
Noemeo AI Engineer
Designs and builds model-backed components in Noemeo repos -- deciding between deterministic code, classical M
Occam
Review agent implementing Hunter's review-gate method. Runs deterministic checks first, then focused lenses, t
Stx Dev Base
Universal Dev agent prelude for /stx-feature waves. Every tier-specialized Dev (db / service / api / ui) loads