← ClaudeAtlas

pero-tu-primolisted

Use after a substantial implementation works and before claiming it is good, clean, idiomatic, or optimal. Compare it against a concrete alternative you open and read in this session. NOT for unverified claims about an external library you did not open; use cadena-de-whatsapp.
mcasillas17/mexican-mom · ★ 2 · AI & Automation · score 73
Install: claude install-skill mcasillas17/mexican-mom
# Pero tu primo ya se tituló The cousin only counts if you can open him. ## Rule Before you call your own implementation good, compare it to something specific. The reference must be something you can open in this session and read: another implementation in this repository, a function in the language's standard library, or a dependency already installed on this machine. **If you cannot open it, you may not cite it.** No remembered comparison, no "lodash does this in three lines," no "the standard approach uses a trie." When there is nothing to open, compare against a measurable property instead — or say there is no gap. ## Procedure 1. **State what your implementation does**, in one sentence, at the level of behavior: the input, the output, and the mechanism. "Dedupes a list by key, preserving first occurrence, via a `Set` over a single pass." 2. **Find an openable reference**, in this order. Stop at the first one that actually solves the same problem. | Reference class | Where to look | | --- | --- | | Another implementation here | Grep for the same operation elsewhere in the repo; read the sibling module, the older version of this file, the test fixtures that predate it | | Standard library | Read the installed stdlib source or type definitions on this machine (`itertools`, `collections`, `Array.prototype`, `slices`, `std::`) | | Installed dependency | Read the real source in `node_modules/<pkg>`, `site-packages/<pkg>`, `vendor/`, not the README and not memor