comsky/remy-skill-recipes

Engineering-grade skill recipes for LLM agents. 7 structured prompt workflows following the SKILL.md open standard.

What's novel

Engineering-grade skill recipes for LLM agents. 7 structured prompt workflows following the SKILL.md open standard.

Code Analysis

10 files read · 3 rounds

A curated collection of 12 structured prompt workflows (SKILL.md files) for LLM coding agents, each defining gated procedures, guardrails, failure patterns, and examples for engineering tasks like code review, CJK text debugging, Git branch safety, and Notion knowledge management.

Strengths

The SKILL.md files contain genuinely domain-expert knowledge (CSS specificity for CJK wrapping, Git safety matrices, GitHub PR workflows) with real depth rather than generic prompt filler. The validation script, architecture doc, and template system create a coherent, enforceable framework for skill quality.

Weaknesses

No automated tests exist beyond the structural validation script — the actual prompt effectiveness is untested and unverifiable. The project is entirely markdown content with minimal executable code, so 'engineering-grade' is aspirational rather than demonstrated through testable artifacts.

Score Breakdown

Innovation

5 (25%)

Craft

71 (35%)

Traction

11 (15%)

Scope

62 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+1

Concept Novelty+1

Craft

Ci+5

Tests+8

Polish+2

Releases+3

Has License+5

Code Quality+21

Readme Quality+15

Recent Activity+7

Structure Quality+3

Commit Consistency+2

Has Dependency Mgmt+0

Traction

Forks+0

Stars+6

Hn Points+0

Watchers+0

Early Traction+5

Devto Reactions+0

Community Contribs+0

Scope

Commits+7

Languages+3

Subsystems+0

Bloat Penalty+0

Completeness+4

Contributors+5

Authored Files+12

Readme Code Match+3

Architecture Depth+7

Implementation Depth+8

Evidence

Commits

Contributors

Files

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

MIT