Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By smileynet
Real-world concepts from programming, education, and design — packaged as AI commands
npx claudepluginhub smileynet/sams-genai-spells --plugin spellFind what you don't know you don't know — surface hidden assumptions, failure modes, and missing perspectives
Research and produce a structured best-practices and antipatterns document
Map all possible causes of a problem using fishbone (Ishikawa) categorical decomposition
Explore and map how a codebase or subsystem works
Systematic root cause analysis — trace symptoms to their actual cause before attempting fixes
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Codex CLIにセカンドオピニオンを求めるスキル。「codexと相談して」「codexに聞いて」で発動する。
Documentation quality, generation, and improvement using Diataxis principles. Pairs with beagle-core for full workflow.
添加關於實作選擇和程式碼庫模式的教育性見解(模擬已棄用的解釋性輸出風格)
Documentation and authoring workflow router: audit docs vs code drift, sync docs after changes, optimize prompts and SKILL.md files, validate GLFM and Markdown formatting, summarize files/URLs/images with fidelity enforcement. Use when: docs are out of date, CLAUDE.md needs improving, SKILL.md needs optimizing, checking if documentation matches code, summarizing files or URLs.
Standalone utilities for codebase exploration, web research, git operations, and code maintenance
AI-powered Socratic learning mode - Transform Claude into a patient coding mentor that guides you through problem-solving without giving direct answers
Simple workflow orchestration for Claude Code sessions - mise, prep, cook, serve, tidy, plate, run
Game design spice for Line Cook — MLP scoping, core loop frameworks, economy design, difficulty curves, content planning, mechanics palette, playtesting, scenario walkthroughs, anti-patterns, architecture auditing, with interactive commands, code review agent, and implementation guidance
Code quality spice for Line Cook — decision frameworks, antipattern detection, refactoring patterns, tradeoff analysis, YAGNI guidance, dead code pruning, and plan auditing
Real-world concepts from programming, education, and design — packaged as AI commands.
These aren't prompt engineering techniques I invented. They're established concepts from real fields — idiomatic code (programming), the Socratic method (education), Diataxis + progressive disclosure (documentation theory), task graphs (operations research), systematic debugging (reliability engineering), program comprehension (software engineering). I just got tired of re-explaining them every session and made commands to use them.
Modifier -- you invoke it once, and it changes the whole session:
> /spell:idiomatic Python 3.12
IDIOMATIC MODE: PYTHON 3.12
══════════════════════════════════════════════════════════════
Version: 3.12
Source: https://docs.python.org/3.12/
SESSION CONSTRAINTS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
USE (canonical patterns):
• pathlib.Path over os.path — modern path handling
• match/case for structural pattern matching — added in 3.10
• f-strings over .format() — cleaner, faster
• type hints with built-in generics (list[int] not List[int]) — PEP 585
AVOID (deprecated or non-idiomatic):
• os.path.join() → Use pathlib.Path / operator instead
• typing.List, typing.Dict → Use built-in list[], dict[] generics
• implicit string concatenation → Use f-strings or explicit +
These constraints are active for the rest of this session.
Workflow -- does research and gives you something concrete:
> /spell:bpap Git commit messages
BEST PRACTICES & ANTIPATTERNS: GIT COMMIT MESSAGES
══════════════════════════════════════════════════════════════
Source: Built-in knowledge + https://cbea.ms/git-commit/
DO ✓
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
1. Use imperative mood in subject line — "Add feature" not "Added feature"
2. Keep subject to 50 characters — forces concise summary
3. Separate subject from body with blank line — tools depend on this
4. Wrap body at 72 characters — readable in terminal and git log
DON'T ✗
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
1. Don't end subject with period — it's a title, not a sentence
2. Don't use "fix bug" or "update code" — say what and why
3. Don't put everything in the subject — use the body for detail
ANTIPATTERNS ⚠
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
1. THE KITCHEN SINK — Unrelated changes lumped into one commit
Why it's tempting: You're "almost done" and don't want to split work
Consequences: Impossible to revert one change without losing others
Instead: One logical change per commit, use interactive staging
Modifiers change how the AI behaves for the rest of the session. You invoke one, then keep working. The constraints stick.
| Spell | What it does |
|---|---|
| idiomatic | AI keeps hallucinating APIs that don't exist? Sets session constraints based on real docs and canonical patterns, not guesswork. |
| socratic | Want to actually learn, not just get an answer? Flips the AI into question-mode so you reason through problems yourself. |
Workflows do research and produce actual output. They'll ask you questions first, then go do the work.