agentmods.dev

cc-proficiency: Skill for Claude Code

.claude/skills/verify/SKILL.md

verify is a skill for Claude Code from Z-M-Huang/cc-proficiency. It costs 0 tokens per session (3,970 once invoked), scanned A, original, Apache-2.0.

A verification routine for the cc-proficiency project. It checks the code, runs tests and a build, exercises command-line commands, and validates generated output.

In plain words
What is it for?
Run it after code changes to check type errors, linting, tests, builds, CLI behavior, and output files.
Why use it?
It finds broken code, failed tests, build problems, unusable commands, and invalid artifacts after changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Z-M-Huang/cc-proficiency's own configuration. It tells Claude Code how to work on cc-proficiency itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cc-proficiency configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node dist/cli/index.js config locale invalid-locale 2>&1.

Part of the cc-proficiency plugin — 1 skill, 1 hook shipped together

not rated 5repo 5mo ago A scan 0 tokens original Apache-2.0
View source ↗ Z-M-Huang/cc-proficiency
Reuse

Borrowing it

Nothing to install: this file belongs to Z-M-Huang/cc-proficiency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Z-M-Huang/cc-proficiency/main/.claude/skills/verify/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Z-M-Huang/cc-proficiency

Made for: Claude Code.

Or install cc-proficiency, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/z-m-huang/cc-proficiency/verify/github.svg)](https://agentmods.dev/skills/z-m-huang/cc-proficiency/verify)
Your own site
<a href="https://agentmods.dev/skills/z-m-huang/cc-proficiency/verify"><img src="https://agentmods.dev/badge/skills/z-m-huang/cc-proficiency/verify/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verify

Your own site · 80×15
<a href="https://agentmods.dev/skills/z-m-huang/cc-proficiency/verify"><img src="https://agentmods.dev/badge/skills/z-m-huang/cc-proficiency/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.03970
Opus 5 $0.00000 $0.01985
Sonnet 5 $0.00000 $0.00794
Haiku 4.5 $0.00000 $0.00397

Measured 9d ago against content hash df5383d62e1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/verify/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify

Run all verification checks to ensure cc-proficiency builds, lints, passes tests, all CLI commands work, and output artifacts are valid.

Usage

Run /verify after making code changes to confirm nothing is broken.

Instructions

Run ALL of the following steps in order, stopping on the first failure:

Step 1 — Code quality

  1. Typecheck: Run npx tsc --noEmit via Bash. If it fails, report the errors and stop.

  2. Lint: Run npx eslint src/ hooks/ via Bash. If it fails, report the errors and stop.

  3. Test: Run npm test via Bash. If any tests fail, report which ones and stop.

  4. Build: Run npm run build via Bash. If it fails, report the errors and stop.

Step 2 — CLI smoke tests

Run each command via Bash (node dist/cli/index.js <cmd>) and verify expected output:

  1. version: Must print cc-proficiency v followed by a semver string.

  2. help: Run with no args — must print usage text containing Commands:.

  3. analyze: Run node dist/cli/index.js analyze --full — must produce output containing domain scores or "No sessions found". If sessions are found, output should contain Tokens: followed by /24h and /30d (token consumption status). Must not error.

  4. explain: Run node dist/cli/index.js explain — must produce output containing the locale-appropriate strengths label (e.g., Strengths: for en, 优势： for zh-CN) or "No analysis data" / the locale equivalent. Must not error.

  5. achievements: Run node dist/cli/index.js achievements — must produce output containing the locale-appropriate achievements title (e.g., Achievements ( for en) or "No analysis data" / the locale equivalent. Must not error.

  6. status: Run node dist/cli/index.js status — must produce output containing cc-proficiency status. Must not error.

  7. config: Run node dist/cli/index.js config — must produce valid JSON output containing autoUpload. Must not error.

  8. badge: Run node dist/cli/index.js badge — must produce output containing Badge saved to. The generated SVG is a multi-locale badge using SVG <switch> elements. Must not error.

Read the full file on GitHub · 260 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 260 lines · 0 tokens per session scan A df5383d62e1e

Subscribe to this mod's changes

verify is a skill published in the GitHub repository Z-M-Huang/cc-proficiency (5 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,970 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeTestingai-toolsanthropicbadgeclaudecli
Related

Other skills, from other repositories

api-tester

Test HTTP APIs, validate responses, generate test suites, and diagnose API issues.

profclaw/profclaw · 19 tokens

caliber-testing

Writes Vitest tests following project patterns: tests/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment variable save/restore in beforeEach/afterEach, vi.clearAllMocks() lifecycle, and test file organization. Use when user says…

caliber-ai-org/ai-setup · 113 tokens

Vizra ADK Evaluation Framework

Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.

vizra-ai/vizra-adk · 26 tokens

beta-testing

Beta testing strategy for iOS/macOS apps. Covers TestFlight program setup, beta tester recruitment, feedback collection methodology, user interviews, signal-vs-noise interpretation, and go/no-go launch readiness decisions. Use when planning a beta, setting up TestFlight, collecting user feedback, or deciding if ready…

rshankras/claude-code-apple-skills · 67 tokens

screenshot-automation

Generates an automated App Store screenshot pipeline with UI tests for screenshot capture, device framing, localized caption overlays, and multi-size batch export. Use when user wants automated screenshots, App Store screenshot generation, or a fastlane snapshot replacement.

rshankras/claude-code-apple-skills · 52 tokens

test-generator

Generate test templates for unit tests, integration tests, and UI tests using Swift Testing and XCTest. Use when adding tests to iOS/macOS apps.

rshankras/claude-code-apple-skills · 33 tokens