aminblg/simpleenglish

Agent skill: make LLMs write docs in ASD-STE100 Simplified Technical

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 23 minutes ago
Added to GitGenius on September 20th, 2026
Created on July 21st, 2026
Open Issues & Pull Requests: 2 (+0)
GitHub issues: Enabled
Number of forks: 127
Total Stargazers: 3,462 (+0)
Total Subscribers: 8 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 36.5 hours
Mean response time: 2.6 days
90th percentile: 5.8 days
Tracked items: 15

Most active contributors

Sign in to see contributor activity.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 2
New in 7 days: 0
Closed in 7 days: 1
Avg open age: 13 days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 0
Closed in 7 days: 1
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

Sign in to see which issues are moving.

Detailed Description

SimpleEnglish is an agent skill that constrains large language models to write documentation in ASD-STE100 Simplified Technical English, the controlled language standard used in aerospace since 1983.

The tool addresses the problem that LLMs naturally produce verbose, ambiguous prose unsuitable for safety-critical documentation. It works by injecting rules derived from ASD-STE100 into the model's system prompt, guiding the model toward shorter sentences, restricted vocabulary, active voice, and unambiguous phrasing. The skill operates as a standard Agent Skills module, compatible with any agent framework that implements the open standard, including Claude Code, Cursor, VS Code Copilot, and others. Installation requires no dependencies and works from a single folder.

The project suits teams writing technical documentation where clarity and precision matter—particularly in aerospace, manufacturing, or other regulated domains where misreading instructions carries real cost. It works in two modes: layman-readable by default, or strict STE compliance on request. For developers already using an agent that supports the Agent Skills standard, adoption is straightforward. For those without skill support, the system prompt rules can be pasted directly into `.cursorrules` or equivalent configuration files, with a compact 60-token version available for token-constrained scenarios.

Development activity shows consistent refinement of the core constraint system. The project maintains evaluation results documenting measured improvements in output quality across multiple model variants. The skill definition follows the open Agent Skills specification, ensuring compatibility across the growing ecosystem of agent platforms. The codebase includes both the core skill logic and optional session hooks for agents that support them, with separate documentation for hook setup requirements.