account-research
Research a company or person and get actionable sales intel. Works standalone with web search, supercharged when you connect enrichment tools or your CRM.…
Lightweight design smell review for modules and APIs—coupling, cohesion, naming, boundaries, and unnecessary complexity. Use before large refactors or when code feels hard to change. Complements gstack/review (diff-focused).
$ npx -y skills add charlieviettq/awesome-agent-skill --skill design-smell-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/design-smell-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Lightweight design smell review for modules and APIs—coupling, cohesion, naming, boundaries, and unnecessary complexity. Use before large refactors or when code feels hard to change. Complements gstack/review (diff-focused).
name: design-smell-review description: "Lightweight design smell review for modules and APIs—coupling, cohesion, naming, boundaries, and unnecessary complexity. Use before large refactors or when code feels hard to change. Complements gstack/review (diff-focused)." allowed-tools: Read, Glob, Grep
Review **structure and boundaries**, not line-by-line style. Pair with PR diff review for changes; use this for module-level health.
| Smell | Signal | Direction | |-------|--------|-----------| | God module | Many unrelated responsibilities | Split by domain | | Shotgun surgery | One change touches many files | Consolidate logic | | Feature envy | Module A mostly uses B's data | Move behavior | | Leaky abstraction | Impl details escape API | Narrow public surface | | Config soup | Magic strings everywhere | Named constants / schema | | Boolean flags | `if is_x` branches everywhere | Polymorphism or strategy |
1. Map **entry points** and **dependencies** (imports, public API). 2. List **responsibilities** per module; flag >1 unrelated core job. 3. Check **testability** — can core logic run without I/O? 4. Propose **smallest** structural improvement (not full rewrite). 5. Record decision in ADR if trade-off is significant.
## Summary [1-2 sentences] ## Smells (priority order) 1. [Smell] — evidence — suggested fix (effort: S/M/L) ## Recommended next step [One concrete change to try first]
Before deleting or collapsing code, ask **why it exists**:
Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).
Research a company or person and get actionable sales intel. Works standalone with web search, supercharged when you connect enrichment tools or your CRM.…
Evaluate LLM agents and tool-using workflows—task success, tool accuracy, latency/cost, safety, and regression suites. Use when shipping agent features,…
Design agent tools and CLI surfaces—schemas, naming, errors, idempotency, and discoverability for LLM callers. Use when defining tools for agents, SDKs, or…
\"Implement and select ad bidding strategies from manual CPC to automated target-CPA and target-ROAS. Use this skill when the user needs to choose a bidding…
\"Optimize advertising budget allocation across campaigns using marginal returns analysis. Use this skill when the user needs to distribute budget across…
\"Build CTR prediction models for estimating ad click-through rates from features. Use this skill when the user needs to predict click probability, build an ad…