Implement

A pragmatic framework for writing code that actually works, built from analyzing 21,000+ real implementation sessions. The core insight is simple: verify every 2-3 edits instead of batching everything at the end, which eliminates most debugging spirals. It gives you a five-phase loop (orient, plan, implement, verify, commit) with concrete heuristics like reading 10+ files before your first edit and maintaining a 9:1 ratio of editing existing files versus creating new ones. The discipline section directly addresses common LLM coding problems like overcomplicating abstractions and making silent assumptions. Use this when you're doing actual feature work or debugging, not one-line config fixes.

skills.sh installs: 577
GitHub stars: 36
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add hyperb1iss/hyperskills --skill implement --agent claude-code

Installs into .claude/skills of the current project.

Files

Implementation

The user's instructions take precedence over this skill; carry existing authorization forward, finish the work within scope, and do not add approval gates.

Orient to the Change

Before editing, inspect status and existing diffs on touched files; the checkout is shared space, so never run autofix across other agents' work. Trace behavior through actual callers and consumers. Find the nearest existing instance of the pattern in the repository, and any prior work in project memory, before building new structure; name it. Search by syntax for structure and by text for names. Recheck volatile API and dependency claims against current primary evidence. "Why does this happen?" calls for a confirmed cause first, then a check that distinguishes broken from intended behavior.