Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Updates the apple-fm README to reflect its current feature set for a major release. Reviews and revises demo modes, with screenshots captured by the user.
Authors ModSec rules, APF/CSF/iptables/nftables firewall blocks, and LMD/ClamAV signature submissions for confirmed attack patterns. Validates with apachectl preflight, FP-corpus checks, and CDN-safelist awareness. Use when the case requires generating a defensive rule, signature, or block to prevent recurrence.
Turns research, notes, proposals, meeting summaries, or educational material into shareable HTML presentations. Supports readable article and navigable slide modes, synchronized ElevenLabs voiceover, scroll-reveal animations, GPT Image 2 illustrations, and configurable detail levels.
Supports pricing research, tier structures, packaging, and monetization decisions. Covers freemium models, free trials, price increases, value metrics, willingness to pay, and Van Westendorp analysis.
complete multi-language current architecture package. Primary owner: MD/JSON/HTML/PDF/draw.io/Mermaid package. Do not use for: lightweight TS/JS dependency map. Use when this role is selected by the Agent-Vorcl-Flow router.
Создать полный code-grounded архитектурный пакет текущего репозитория: сначала ARCHITECTURE.md, затем JSON, HTML, draw.io, Mermaid и PDF. Use для первого анализа; существующий пакет обновляет /principal-architect:update.
Обновить существующий code-grounded архитектурный пакет после изменений кода: полный rescan, evidence diff и атомарная перегенерация всех форматов.
Цель роли principal-architect: session-first план, реализация в разрешённом scope и независимая проверка; Task Master только по явному выбору.
Создавать и обновлять production-grade архитектурный пакет текущего репозитория строго по исходному коду, конфигурации, схемам БД, manifests, CI/CD и IaC: сначала ARCHITECTURE.md с file:line evidence, затем JSON, self-contained HTML, PDF, draw.io и копируемые Mermaid L0-L4. Use when нужно нарисовать реальную архитектуру существующего проекта, провести code-aware architecture review, показать data/…
Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name