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.…
Create and maintain Architecture Decision Records (ADRs) for significant technical choices—frameworks, data stores, API shapes, ML platform decisions. Use when documenting a decision, onboarding, or superseding a prior approach.
$ npx -y skills add charlieviettq/awesome-agent-skill --skill architecture-decision-records --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/architecture-decision-recordsContext preview
The summary Claude sees to decide when to auto-load this skill.
Create and maintain Architecture Decision Records (ADRs) for significant technical choices—frameworks, data stores, API shapes, ML platform decisions. Use when documenting a decision, onboarding, or superseding a prior approach.
name: architecture-decision-records description: "Create and maintain Architecture Decision Records (ADRs) for significant technical choices—frameworks, data stores, API shapes, ML platform decisions. Use when documenting a decision, onboarding, or superseding a prior approach." allowed-tools: Read, Glob, Grep
| Write ADR | Skip ADR | |-----------|----------| | New framework or major dependency | Minor version bump | | Database or storage choice | Bug fix | | API or integration pattern | Config-only change | | Security or auth architecture | Routine maintenance |
`Proposed` -> `Accepted` -> `Deprecated` -> `Superseded`
Do not rewrite accepted ADRs; add a new ADR that supersedes the old one.
1. **Context** — problem and constraints 2. **Decision** — what was chosen (one clear statement) 3. **Consequences** — positive, negative, risks and mitigations 4. **Status** and date
# ADR-NNNN: Title **Status:** Accepted | **Date:** YYYY-MM-DD ## Context [Why we needed to decide] ## Decision [What we decided] ## Consequences **Positive:** ... **Negative:** ... **Risks:** ... **Mitigation:** ...
See [reference.md](reference.md) for extended templates (standard, Y-statement, deprecation).
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…