Not in the top 1,000 by GitHub stars
JordanCoin/codingskills
Coding principles for Claude Code and AI agents. KISS, DRY, SOLID, YAGNI, separation of concerns, and more. Language-agnostic skills that help agents ship production-quality code.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/boy-scout-rule/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d990b56b72f3
No earlier version was observed for comparison.
skills/convention-over-configuration/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d990b56b72f3
No earlier version was observed for comparison.
skills/detect-stack/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d990b56b72f3
No earlier version was observed for comparison.
skills/dry/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d990b56b72f3
No earlier version was observed for comparison.
skills/kiss/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d990b56b72f3
No earlier version was observed for comparison.
skills/law-of-demeter/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d990b56b72f3
No earlier version was observed for comparison.
skills/separation-of-concerns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d990b56b72f3
No earlier version was observed for comparison.
skills/solid/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d990b56b72f3
No earlier version was observed for comparison.
skills/yagni/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d990b56b72f3
No earlier version was observed for comparison.
Verified commit d990b56b72f3f4203c13d1ef40e815893d9e7c54
git clone --filter=blob:none --no-checkout https://github.com/JordanCoin/codingskills.git .hotskills/jordancoin-codingskills && git -C .hotskills/jordancoin-codingskills checkout --detach d990b56b72f3f4203c13d1ef40e815893d9e7c54
# Copy each selected skill directory from .hotskills/jordancoin-codingskills into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/JordanCoin/codingskills.git .hotskills/jordancoin-codingskills && git -C .hotskills/jordancoin-codingskills checkout --detach d990b56b72f3f4203c13d1ef40e815893d9e7c54
# Copy each selected skill directory from .hotskills/jordancoin-codingskills into .agents/skills/<skill-name>/Heat
2.9- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- boy-scout-rule
skills/boy-scout-rule - convention-over-configuration
skills/convention-over-configuration - detect-stack
skills/detect-stack - dry
skills/dry - kiss
skills/kiss - law-of-demeter
skills/law-of-demeter - separation-of-concerns
skills/separation-of-concerns - solid
skills/solid - yagni
skills/yagni
How it works
boy-scout-rule
When your agent uses it
When touching existing code and wanting to leave it better. Use when the user says "clean this up while I'm here," "should I fix this," "tech debt," "while I'm in this file," or "incremental improvement." For full refactoring, see solid or separation-of-concerns.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
902 tokensWhen the skill is activated
Reference documents
9,087 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before Applying
- Principle
- Why This Matters in Production
- Rules
- What Counts as "A Little Better"
- What Does NOT Count
- Boundaries
- Code Review Checklist
- Related Skills
Files
../../.claude-plugin/marketplace.jsonasset1,083 bytesSKILL.mdcore4,146 bytes../convention-over-configuration/SKILL.mddoc5,962 bytes../detect-stack/SKILL.mddoc2,971 bytes../dry/SKILL.mddoc5,659 bytes../kiss/SKILL.mddoc5,282 bytes../law-of-demeter/SKILL.mddoc5,352 bytes../separation-of-concerns/SKILL.mddoc5,771 bytes../solid/SKILL.mddoc7,066 bytes../yagni/SKILL.mddoc4,966 bytes
Read SKILL.md
# Boy Scout Rule
## Before Applying
If `.agents/stack-context.md` exists, read it first. Apply this principle using idiomatic patterns for the detected stack. For framework-specific details, use context7 MCP or web search — don't guess.
## Principle
Leave every file you touch a little better than you found it. Not a lot better — a little better. Incremental improvement compounds into a clean codebase over time.
## Why This Matters in Production
Codebases don't rot overnight. They degrade one shortcut at a time — a hardcoded value here, a skipped rename there, a TODO that lives for three years. The Boy Scout Rule is the antidote: it makes improvement the default, not a scheduled event.
View the complete source on GitHubconvention-over-configuration
When your agent uses it
When organizing project structure, establishing patterns, or reducing configuration overhead. Use when the user says "how should I organize this," "what's the convention," "too much config," "project structure," "naming pattern," or "standardize this." For code-level structure, see separation-of-concerns.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
1,220 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before Applying
- Principle
- Why This Matters in Production
- Rules
- Anti-Patterns
- Examples
- Boundaries
- Code Review Checklist
- Related Skills
Files
SKILL.mdcore5,962 bytesSKILL.mdcore5,962 bytes
Read SKILL.md
# Convention over Configuration
## Before Applying
If `.agents/stack-context.md` exists, read it first. Apply this principle using idiomatic patterns for the detected stack. For framework-specific details, use context7 MCP or web search — don't guess.
## Principle
Adopt sensible defaults and consistent patterns so that decisions are made once and applied everywhere. Reserve explicit configuration for the cases that genuinely need to differ from the default.
## Why This Matters in Production
Every configuration option is a decision that someone must make, document, understand, and maintain. Misconfigured systems are a top cause of production incidents — wrong environment variables, typos in YAML, conflicting settings between services.
View the complete source on GitHubdetect-stack
When your agent uses it
Analyze a codebase to detect its language, framework, conventions, and CI gates. Run this on first use in a project to generate stack context that all coding principle skills reference. Use when the user says "detect stack," "analyze this project," or "what's this codebase using."
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
746 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What to Detect
- Output
- Stack-Specific Principle Application
- When to Re-Run
Files
SKILL.mdcore2,971 bytes
Read SKILL.md
# Detect Stack
Analyze the current codebase and generate `.agents/stack-context.md`. Run this on first use in a project, or when the stack context is missing or stale.
## What to Detect
Scan the project root for these signals:
**Language** — Count file extensions (`.rs`, `.py`, `.ts`, `.go`, `.swift`, `.java`, `.rb`, `.cs`, `.ex`, etc.). Primary = most files. Note secondary languages.
**Framework** — Read the package manifest:
- `Cargo.toml` → check `[dependencies]` for axum, actix, rocket, sqlx, diesel, tokio
- `package.json` → check for react, next, svelte, express, fastify, prisma
- `go.mod` → check for gin, echo, fiber, chi, sqlcView the complete source on GitHubdry
When your agent uses it
When writing or reviewing code to eliminate duplicated knowledge and business logic. Use when the user says "this is duplicated," "we have this in two places," "single source of truth," "DRY this up," or "shotgun surgery." For premature abstraction concerns, see yagni.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
1,176 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before Applying
- Principle
- Why This Matters in Production
- Rules
- Anti-Patterns
- The Wrong Kind of DRY
- The Right Kind of DRY
- Boundaries
- Code Review Checklist
- Related Skills
Files
SKILL.mdcore5,659 bytesSKILL.mdcore5,659 bytesSKILL.mdcore5,659 bytesSKILL.mdcore5,659 bytesSKILL.mdcore5,659 bytes
Read SKILL.md
# DRY — Don't Repeat Yourself
## Before Applying
If `.agents/stack-context.md` exists, read it first. Apply this principle using idiomatic patterns for the detected stack. For framework-specific details, use context7 MCP or web search — don't guess.
## Principle
Every piece of knowledge in a system should have a single, authoritative representation. When that knowledge changes, you should only need to change it in one place.
## Why This Matters in Production
Duplicated logic is a ticking time bomb. When a business rule changes and you update it in one place but miss the copy in another, you get inconsistent behavior that's hard to detect and harder to debug. The more copies exist, the more likely one diverges silently.
View the complete source on GitHubkiss
When your agent uses it
When writing or reviewing code to reduce complexity and improve readability. Use when the user says "simplify this," "too complex," "hard to read," "clean up," "what does this do," or "can't follow this code." For over-engineering concerns, see yagni. For structural clarity, see separation-of-concerns.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,154 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before Applying
- Principle
- Why This Matters in Production
- Rules
- Anti-Patterns
- Examples
- Boundaries
- Code Review Checklist
- Related Skills
Files
SKILL.mdcore5,282 bytes
Read SKILL.md
# KISS — Keep It Simple
## Before Applying
If `.agents/stack-context.md` exists, read it first. Apply this principle using idiomatic patterns for the detected stack. For framework-specific details, use context7 MCP or web search — don't guess.
## Principle
Given two solutions that produce the same result, prefer the one that is easier to read, understand, and change.
## Why This Matters in Production
Simple code survives contact with production. Complex code breaks in ways that are hard to diagnose, hard to fix, and hard to verify the fix didn't break something else. Every incident response starts with someone reading code under pressure — if they can't understand it quickly, the outage gets longer.
View the complete source on GitHublaw-of-demeter
When your agent uses it
When reviewing code for excessive coupling and deep object chains. Use when the user says "too coupled," "train wreck," "chained calls," "feature envy," "mocking is painful," or "this reaches too deep." For broader structural coupling, see solid.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,152 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before Applying
- Principle
- Why This Matters in Production
- Rules
- Anti-Patterns
- Examples
- Boundaries
- Code Review Checklist
- Related Skills
Files
SKILL.mdcore5,352 bytes
Read SKILL.md
# LoD — Law of Demeter (Principle of Least Knowledge)
## Before Applying
If `.agents/stack-context.md` exists, read it first. Apply this principle using idiomatic patterns for the detected stack. For framework-specific details, use context7 MCP or web search — don't guess.
## Principle
A component should only talk to its immediate collaborators. Don't reach through an object to access its internals, its children's internals, or anything deeper.
More precisely: a method should only call methods on (1) itself, (2) its own fields, (3) its parameters, (4) objects it creates, and (5) global/singleton services.
## Why This Matters in Production
View the complete source on GitHubseparation-of-concerns
When your agent uses it
When structuring code into layers and modules with clear boundaries. Use when the user says "this function does too much," "fat controller," "mixed concerns," "where should this logic go," or "separate the layers." For interface-level design, see solid. For object-level coupling, see law-of-demeter.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,173 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before Applying
- Principle
- Why This Matters in Production
- Rules
- Anti-Patterns
- Examples
- Boundaries
- Code Review Checklist
- Related Skills
Files
SKILL.mdcore5,771 bytes
Read SKILL.md
# SoC — Separation of Concerns
## Before Applying
If `.agents/stack-context.md` exists, read it first. Apply this principle using idiomatic patterns for the detected stack. For framework-specific details, use context7 MCP or web search — don't guess.
## Principle
Each module, layer, or component in a system should address a single concern. A concern is a distinct aspect of functionality — data access, business rules, presentation, authentication, error handling, logging.
## Why This Matters in Production
When concerns are entangled, changes become dangerous. Modifying the database schema shouldn't break the UI. Changing the logging format shouldn't affect business logic. Adding authentication shouldn't require rewriting every handler.
View the complete source on GitHubsolid
When your agent uses it
When designing module boundaries, interfaces, or class hierarchies for maintainable architecture. Use when the user says "how should I structure this," "too coupled," "hard to test," "dependency injection," "single responsibility," or "interface design." For simpler structural concerns, see separation-of-concerns.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,426 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before Applying
- Principle
- Why This Matters in Production
- Boundaries
- Code Review Checklist
- Related Skills
Files
SKILL.mdcore7,066 bytes
Read SKILL.md
# SOLID Principles
## Before Applying
If `.agents/stack-context.md` exists, read it first. Apply this principle using idiomatic patterns for the detected stack. For framework-specific details, use context7 MCP or web search — don't guess.
## Principle
Five design principles that produce modular, testable, and resilient systems. While originally framed for object-oriented design, the underlying ideas apply to any paradigm — functions, modules, services, or components.
## Why This Matters in Production
SOLID code is change-friendly code. Production systems change constantly — new features, bug fixes, integrations, scaling. Systems designed with SOLID principles absorb change locally rather than requiring cascading modifications. This means fewer regressions, faster feature delivery, and smaller blast radius when things go wrong.
View the complete source on GitHubyagni
When your agent uses it
When writing or reviewing code to prevent over-engineering and speculative features. Use when the user says "is this over-engineered," "do we need this," "should I add," "future-proof," or "just in case." For simplicity concerns, see kiss. For abstraction design, see solid.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,040 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before Applying
- Principle
- Why This Matters in Production
- Rules
- Anti-Patterns
- Examples
- Boundaries
- Code Review Checklist
- Related Skills
Files
SKILL.mdcore4,966 bytesSKILL.mdcore4,966 bytes
Read SKILL.md
# YAGNI — You Aren't Gonna Need It
## Before Applying
If `.agents/stack-context.md` exists, read it first. Apply this principle using idiomatic patterns for the detected stack. For framework-specific details, use context7 MCP or web search — don't guess.
## Principle
Do not build for hypothetical future requirements. Build what is needed now, and refactor when actual requirements emerge.
## Why This Matters in Production
Speculative code is the #1 source of accidental complexity. Every abstraction, configuration option, or extension point you add "just in case" has a real cost: it must be understood, tested, maintained, and debugged. Unused code paths are the most dangerous — they rot silently, give false confidence in test coverage, and create surface area for bugs.
View the complete source on GitHubSkills included
- boy-scout-rule
- convention-over-configuration
- detect-stack
- dry
- kiss
- law-of-demeter
- separation-of-concerns
- solid
- yagni
Repository facts
- License
- MIT
- Created
- Feb 28, 2026
- Last pushed
- Feb 28, 2026
- Forks
- 4
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 6 notes
skills/convention-over-configuration/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dry/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dry/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dry/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dry/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/yagni/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 6 network referencesin 1 file: .claude-plugin/marketplace.json:3
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 6 signals by file
.claude-plugin/marketplace.json
- Network accessline 3
"owner": { "name": "Jordan Coin Jackson", "url": "https://github.com/JordanCoin" - Network accessline 4
"name": "Jordan Coin Jackson", "url": "https://github.com/JordanCoin" }, - Network accessline 5
"url": "https://github.com/JordanCoin" - Network accessline 8
"description": "Coding principles for AI agents — KISS, DRY, SOLID, YAGNI, separation of concerns, law of demeter, and more", "version": "1.0.0", "repository": "https://github.com/JordanCoin/codingskills" - Network accessline 9
"version": "1.0.0", "repository": "https://github.com/JordanCoin/codingskills" }, - Network accessline 10
"repository": "https://github.com/JordanCoin/codingskills"
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/boy-scout-rule/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/boy-scout-rule/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/boy-scout-rule/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/boy-scout-rule/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.