Verification Loop

After a feature or refactor on this Windows estate, run six checks in order and write a PASS or FAIL note before a draft pull request. Use when work is about to be committed, pushed, or handed to another harness.

48 stars 6 forksGit & Code Review Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add frankxai/claude-skills-library

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add frankxai/claude-skills-library --skill verification-loop
Manual install
git clone --depth 1 https://github.com/frankxai/claude-skills-library.git /tmp/claude-skills-library
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-library/absorbed/harness/verification-loop ~/.claude/skills/verification-loop

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Estate verification loop

Run the checks in this order. Stop at the first hard failure. Record a result for every check you could not run. A missing tool is not a pass.

1. Install and build with the repo's package manager. Prefer `pnpm` when `pnpm-lock.yaml` is present. Prefer `uv` for Python. Do not switch the repo to npm because a snippet says `npm run build`.
2. Types. For TypeScript, `pnpm exec tsc --noEmit` from the package that owns the change. For Python, `uv run pyright` only when that project already uses it.
3. Lint with the formatter the repo already configured. Do not add a new linter config to make this step green.
4. Tests the change can affect. State the command, the pass count, and the fail count from the tool output.
5. Secret scan of the diff for private-key blocks, `sk-ant`, GitHub token prefixes, and Slack token prefixes. Reading a local env file during development is normal on this machine. Committing one is not.
6. `git diff --stat` against the branch you will push. Name the files. Confirm you did not sweep another agent's untracked work.

## How to score

- Build, types, and tests are hard gates when those tools exist for the files you changed.
- A coverage number near 80 percent is a target for product code. It does not block a docs-only change or an ops handover.
- `console.log` left in application code is a warning. It does not fail the build by itself.
- If a check cannot run, write `NOT RUN` and the reason. Do not invent a pass.

## Report
Read the full skill on GitHub

Details

Skill name
verification-loop
Path
absorbed/harness/verification-loop/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Verification Loop skill do?

After a feature or refactor on this Windows estate, run six checks in order and write a PASS or FAIL note before a draft pull request. Use when work is about to be committed, pushed, or handed to another harness.

How do I install the Verification Loop skill?

Claude Code plugin: /plugin marketplace add frankxai/claude-skills-library. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Verification Loop popular?

It lives in frankxai/claude-skills-library, which has 48 GitHub stars and 6 forks.

Related skills

Acos Meta

48

frankxai/claude-skills-library

ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new skills/commands/agents, and how to debug the hook system. Use when building new ACOS capabilities, understanding the system architecture, or onboarding to ACOS for the first time.

Software Development

Acos Visual Gen

48

frankxai/claude-skills-library

Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.

Images, Video & Audio

Agent Harness Construction

48

frankxai/claude-skills-library

Shape an agent's tools, observations, and recovery without adding a second coordinator. Use when defining a tool, a skill, a hook, or a worktree lane.

AI, LLMs & Agents

Argumentation

45

pjt222/agent-almanac

Construct well-structured arguments using the hypothesis-argument-example triad. Covers formulating falsifiable hypotheses, building logical arguments (deductive, inductive, analogical, evidential), providing concrete examples, and steelmanning counterarguments. Use when writing or reviewing PR descriptions that propose technical changes, justifying design decisions in ADRs, constructing substantive code review feedback, or building a research argument or technical proposal.

Git & Code ReviewIn 1 list

To Spec

48

frankxai/claude-skills-library

Turn what has already been discussed into a spec and file it as a GitHub issue on the product repo, without interviewing the user again. Use when the user says write this up as a spec, open an issue for this, or turn this into a ticket, after the decisions are made.

Git & Code Review

Build Pkgdown Site

45

pjt222/agent-almanac

Build and deploy a pkgdown documentation site for an R package to GitHub Pages. Covers _pkgdown.yml configuration, theming, article organization, reference index customization, and deployment methods. Use when creating a documentation site for a new or existing package, customizing layout or navigation, fixing 404 errors on a deployed site, or migrating between branch-based and GitHub Actions deployment methods.

Git & Code ReviewIn 1 list

Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.