Skill Tighten

Skill Tighten is an AI Engineering skill for Claude Code, published by techygarg in lattice.

185 stars13 forkson techygarg/latticeAdded 2026/09/06+1% in starsRepository updated 2026/09/04

agentagent-frameworkagent-skillsagenticagentic-aiclaude-code-pluginclaude-skillsclean-architecturecodexcodex-plugincodex-skillscontext-engineeringcursor-plugindddengineering-enablementgorkkimikimi-codelatticesdlc-workflow

Install in seconds

Install Skill Tighten

Copy Skill Tighten into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/techygarg/lattice/tree/main/dev-skills/skill-tighten ~/.claude/skills/skill-tighten

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/techygarg/lattice.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: dev-skills/skill-tighten/SKILL.md in techygarg/lattice
Installs to: ~/.claude/skills/skill-tighten
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 3278 skills

What Skill Tighten does

Skill Tighten audits Lattice skill files for language compliance and rewrites phrasing that agents may underweight at runtime. It removes rationale prose, tightens soft language into imperatives, adds STOP gates to hard rules, and cuts redundant repetition.

Skill Tighten is cataloged under AI Engineering on DirSkills. Skill Tighten comes from a repository tagged agent, agent-framework, agent-skills, agentic and agentic-ai.

Documentation

README

Excerpt

Skill Tighten

Core responsibility: Fix language that causes agents to skip or underweight instructions. Not behavioral gaps — that is skill-review's job. Only phrasing: rationale prose, soft language, missing enforcement signals, redundant repetition.

Input: One or more of:

A file path: source/atoms/clean-code/SKILL.md
A skill name: clean-code (resolves to the correct path automatically)
A tier: atoms (tightens all skills in that tier)
No argument: tightens all skills across all tiers

Output: Edited files + a report per skill:

## skill-tighten — {skill-name}
Lines: {before} → {after}
Changes:
1. {what changed} — {one-line reason}
2. ...
Result: TIGHTENED ({N} changes) | CLEAN (no changes needed)

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Skill Tighten

What else does techygarg publish alongside Skill Tighten?
Skill Tighten is one of 25 skills that DirSkills catalogs from techygarg/lattice, the repository it ships in. Its siblings there include Architecture, Architecture Compass and Architecture Refiner. Each one is a separate skill with its own page in this directory, installs the same way Skill Tighten does, and is maintained by techygarg in that same repository. The rest of the collection is listed on the techygarg/lattice page.
How does Skill Tighten compare to other AI Engineering skills?
Skill Tighten ranks #3026 by stars among the 3278 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Skill Tighten against them. Open each page to compare what they document and how they install.