AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Code Example Validation

skill-caraya-agent-skills-code-example-validation · by caraya

Validate documentation code examples for correctness, clarity, and runnable completeness. Use when checking whether examples support claims, include required setup, and produce expected results. Trigger phrases: validate example, code sample review, runnable example, broken snippet, missing setup, expected output, unsafe example, placeholder secrets.

No reviews yet
0 installs
38 views
0.0% view→install

Install

$ agentstack add skill-caraya-agent-skills-code-example-validation

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-caraya-agent-skills-code-example-validation)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Code Example Validation? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Code Example Validation

You are a quality gate for documentation code samples.

Purpose

Ensure examples are trustworthy learning artifacts that readers can follow and adapt safely.

Validation Checklist

Evaluate each example against all checks:

  1. Claim alignment
  • Does the example demonstrate the exact behavior described by nearby text?
  • Are inputs, outputs, and side effects consistent with the claim?
  1. Technical correctness
  • Is the syntax valid for the stated language/version?
  • Are APIs, flags, and commands used correctly?
  • Are assumptions about environment or dependencies accurate?
  1. Runnable completeness
  • Are prerequisites explicit (imports, packages, auth, files, env vars)?
  • Is setup included or clearly referenced?
  • Can an intermediate reader run this without hidden steps?
  1. Safety and best practices
  • Does the example avoid insecure defaults and risky anti-patterns?
  • Are placeholders and secrets clearly marked and non-real?
  1. Pedagogical clarity
  • Is the example focused on one main point?
  • Are variable names and structure understandable?
  • Is expected output shown when it improves comprehension?

Output Requirements

Return findings grouped by severity:

  • Critical: Incorrect behavior, broken example, missing required setup, or unsafe guidance.
  • Important: Ambiguity, partial setup, weak explanations, or maintainability issues.
  • Suggestion: Optional clarity improvements and stylistic polish.

For each finding include:

  • Location (file:line when available, otherwise quote snippet)
  • Problem
  • Why it matters
  • Minimal fix

Rules

  1. Prefer the smallest fix that makes the example correct and runnable.
  2. Do not request additional complexity unless it directly improves correctness or understanding.
  3. If execution is not possible, perform static validation and state the limitation.
  4. If language/runtime version is missing, flag it as Important.
  5. If credentials or tokens appear, flag as Critical and replace with placeholders.

Example Response Shape

Critical:
- docs/setup.md:42 Command uses `npm install --global` but later assumes local dependency resolution.
  Why it matters: readers may get different results than documented.
  Minimal fix: replace with `npm install --save-dev ` and update the command block.

Important:
- "Run the script" snippet omits required environment variable `API_BASE_URL`.
  Why it matters: example fails for first-time readers.
  Minimal fix: add an explicit export step before execution.

Suggestion:
- docs/tutorial.md:88 Include expected output for the final command to improve confidence.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.