strict-api

$npx mdskill add alirezarezvani/claude-skills/strict-api

Inventing a function that doesn't exist is the opposite of efficiency. You wrote a line that looks minimal. You shipped a bug that takes an hour to debug. The true minimal path is: use only what is provably there.

SKILL.md

.github/skills/strict-apiView on GitHub ↗
---
name: "strict-api"
description: "Use when the user says 'no hallucinations', 'verify APIs' or 'don't invent functions', or code depends on a library version you have not checked. Requires proof that every method, import and variable exists in the installed version before using it."
---

# Strict API Verification

Inventing a function that doesn't exist is the opposite of efficiency. You wrote a line that looks minimal. You shipped a bug that takes an hour to debug. The true minimal path is: use only what is provably there.

## Overview

This skill is a reality-check layer applied before any code is written. It is not about being slow — it is about being correct the first time. Use it alongside `minimalist` when the user wants both less code and verified code.

## The Only Rule

Before you write any function call, import, or method access, you must be able to answer:

**"Does this exist in the version the user is running?"**

If the answer is "probably" or "I think so" — **stop**. You don't know. Say so.

## What This Blocks

**Made-up methods:**
- `fs.readFileLines()` does not exist in Node.js.
- `path.combine()` is .NET, not Node.js.
- `csv.read_csv()` is pandas, not Python's `csv` module.

Writing these is not minimal code — it is confident garbage.

**Framework confusion.** Every framework has a twin that sounds like it:
- `render_template` (Flask) vs `render()` (Django)
- `useForm()` (react-hook-form) vs nothing built into React
- `app.listen()` (Express) vs `server.listen()` (raw Node.js `http`)

**Deprecated APIs.** Writing a deprecated method is writing code that will break on the next upgrade.

## Workflow

1. **Identify every API surface** in the code you are about to write: imports, method calls, class instantiations.
2. **Verify each one** against the user's stated version. If no version is stated, ask once.
3. **Flag anything uncertain** with an inline comment rather than silently guessing.
4. **Prefer verbose-but-correct** over terse-but-wrong.

When you are not sure if a method exists, annotate it inline:

    // verify fs.openAsBlob exists in your Node.js version (>= 20.0)
    const blob = await fs.openAsBlob(path);

One comment costs nothing. A silent wrong call costs an hour of the user's time.

If the uncertainty is too high to write correct code without guessing, say:

    "I'd need to check whether X exists in version Y before using it. What version are you on?"

## Anti-Patterns

| Anti-Pattern | What to do instead |
|---|---|
| Writing a method call you vaguely remember | Stop and verify the exact signature |
| Silently using a deprecated API | Use the current API and note the deprecation |
| Assuming API parity across frameworks | Explicitly name the framework and version |
| Guessing import paths | Check the package's actual export structure |
| Using an API from a different language's stdlib | Verify it exists in this language |
| Writing "it should work" without checking | Ask what version the user is on |

## Cross-References

- Related: `engineering/minimalist` — use together: minimalist reduces code volume; strict-api ensures what is written is correct.
- Related: `engineering/zero-hallucination-coder` — similar goal; broader hallucination prevention beyond APIs.
- Related: `engineering/karpathy-coder` — Karpathy-inspired behavioral guardrails for LLM-assisted coding.

More from alirezarezvani/claude-skills

SkillDescription
a11y-auditUse for any accessibility audit or a11y fix (WCAG 2.2 A/AA, color contrast, compliance report, CI check) in React, Next.js, Vue, Angular, Svelte or HTML. Scans with a11y_scanner.py and checks contrast with contrast_checker.py, then fixes and re-verifies.
ab-test-setupUse before planning or launching any A/B, split or multivariate test, or when asked if a result is significant. Sizes the test with sample_size_calculator.py and writes the hypothesis, metric and stop rule first, so it is not called early on noise.
access-lifecycleUse when preparing or running a user access review, checking that leavers lost their access, finding orphaned or ownerless service accounts, answering an auditor's access-control request for SOC 2, ISO 27001, PCI DSS, HIPAA or NIST 800-53, or checking whether a finished review campaign will hold up. Diffs the HR roster against account exports, tests the campaign for coverage, self-review, unremoved revokes and rubber-stamping, and maps every exception to the controls it breaks.
ad-creativeUse for any ad copy request (RSA headlines, Meta, LinkedIn or TikTok ads, bulk variations), before writing. Checks every line against platform character limits and policy with ad_copy_validator.py. Campaign strategy and budgets: paid-ads.
adversarial-reviewerTough, critical review of a diff or PR before merge, through hostile reviewer personas that catch shared blind spots. Use whenever the user wants a change torn apart, a harsh second opinion, or a self-review felt too agreeable.
aeoUse when content should be cited by ChatGPT, Perplexity, Claude or Gemini (answer engine optimization), before rewriting it. Scores E-E-A-T and structure with aeo_audit.py, rewrites with aeo_optimizer.py and logs citations with citation_tracker.py.
agent-decision-receiptsUse when an autonomous agent takes a side-effecting action (deploy, delete, pay, grant access) that may need proving later, or for EU AI Act Art. 12 record-keeping. Builds a tamper-evident signed receipt with build_action_manifest.py and verifies it.
agent-designerDesign multi-agent systems (supervisor, swarm, pipeline) and tool schemas; find bottlenecks in run logs. Use whenever agents split work or a run is slow or costly. Not for Claude Code workflow files (workflow-builder).
agent-harnessUse when an agent should drive a goal in one of this repo's domains to a verified close, before starting the work. Compiles the goal into a task plan with goal_compiler.py and runs it through loop_controller.py, which verifies each task, caps retries and escalates.
agent-launcher-orchestratorUse when someone wants to build, launch, grade or schedule a Claude Managed Agent in their own Anthropic account ('build me an agent', 'run this nightly'). Reads the session goal, routes with goal_router.py and compiles the loop with loop_compiler.py.