Explorar skills

Main orchestrator for email outreach campaigns. Use this skill when the user wants to send bulk emails, manage email campaigns, or do cold outreach using Google Sheets as recipient source. Routes to campaign-executor for actual sending.

Review an existing Ansible role and produce a structured severity report grouped by CRITICAL, WARNING, and INFO. Triggered by /review-role. Checks directory structure completeness, task FQCN, tag coverage, no_log on secret tasks, defaults vs vars usage, meta/main.yml validity, and handler correctness. NEVER modifies files.

Pipeline and task-graph orchestration. Sequential stages with dependency edges — linear chain or arbitrary DAG.

Deprecated name; the skill formerly here is now opinionated-research:interactive-research. Retained as a context-level notice because Claude Code now ships a built-in deep-research workflow that runs one-shot, non-interactive fan-out research (no conversation after the report). interactive-research instead runs a persistent agent team you can keep questioning once the report lands. Guidance for Cl

Analyzes code for smells and structural issues, proposes a safe refactoring plan, and executes it with test verification. Use when code is hard to read, maintain, or extend.

Review patterns for tidymodels workflows, including leakage, resampling, tuning, metrics, and reproducibility.

Esta skill é usada para acionar, testar ou executar manualmente os scripts de busca de emprego, incluindo e-mails diários ou remotos. Ela é ativada por frases como "executar trabalhos diários" ou "testar a busca remota".

Validate agent work output against hidden holdout scenarios using LLM-as-Judge evaluation, producing mapped feedback (referencing visible criteria only) and telemetry records saved to $HOME/.ai-first-kit/. Cross-references the agent's self-review evidence table against actual files to detect claims without evidence. Use when the user says 'validate holdouts', 'test gates against holdouts', 'run ho

Use when designing SAP solution landscapes, defining integration architecture, making BTP vs on-premise decisions, creating extensibility strategies, or producing solution architecture documents for any SAP implementation.

Passive ethical review: manipulation, accessibility, privacy, sustainability in user-facing features.

Generates Claude Code plugin agent .md files: writes YAML frontmatter (name, model, color, tools, hooks, disallowedTools), crafts system prompts, and creates triggering example blocks with context and commentary. Validates agent structure against naming, length, and format constraints. Use when the user asks to create an agent, add an agent, write a subagent, configure agent frontmatter, design ag

Taiwan and US stock technical analysis scanner with portfolio tracking. Use when the user wants to (1) scan Taiwan or US stocks for buy signals ("掃描股票", "scan"), (2) track selected stocks in a watchlist, (3) monitor positions for sell signals ("追蹤"), or (4) manage their stock watchlist (add/remove positions). Scans top 150 Taiwan stocks by market cap OR user-specified US stocks using 8 technical s