By przemocny
Systematically create, refine, upgrade, and configure Claude AI agent skills using guided briefings, prioritized fixes, business-driven enhancements, multi-source verified internet research, Markdown config generation, and layered context management.
npx claudepluginhub przemocny/generic-skillsCreate AI agent configuration files (AGENTS.md, CLAUDE.md, .cursorrules, etc.) for general-purpose and business-domain agents through guided briefing process. Use when user wants to create agent configuration file, set up AI assistant for specific role or domain, configure agent for business workflows, generate AGENTS.md or CLAUDE.md, customize AI behavior for organization, or define agent boundaries and guidelines. Trigger on phrases like create agent config, setup AI assistant, make AGENTS.md, configure agent for role, AI agent for business domain, or help me configure Claude/Cursor/Windsurf.
Zbiera, zapisuje i ładuje kontekst osobisty i firmowy w 20 warstwach informacyjnych. Tryb zapisu: "zapamiętaj że...", "zapisz że...", "zanotuj...", "dodaj do kontekstu...". Tryb briefingu: "zbierz kontekst o...", "przeprowadź wywiad o...", "uzupełnij warstwę...", "wyciągnij ze mnie info o...", "zbierz info o mojej roli / firmie / zespole", "opowiedz mi o swojej [kategorii]". Tryb montowania: "zamontuj kontekst...", "załaduj kontekst o...", "pokaż kontekst...", "daj mi kontekst o...", "co wiesz o mnie...", "podsumuj mój kontekst...". Tryb edycji: "popraw...", "zmień to że...", "usuń wpis...", "zaktualizuj...". Zawsze komunikuje się po polsku.
Conducts systematic internet research through strategic questioning and multi-source analysis. Gathers information from web sources (not codebase), cross-references claims across multiple sources, evaluates source credibility using tier system (official docs, expert blogs, community resources), identifies patterns and consensus, and produces structured reports in .research/. Use when user needs to gather knowledge from internet, find best practices, compare solutions, evaluate technologies, understand industry trends, or investigate topics thoroughly. Triggers include "research online", "gather information about", "find best practices for", "compare solutions", "evaluate", "investigate topic", "what do sources say", "look up", "search for information".
Create effective agent skills through guided briefing process. Use when user wants to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) design a skill, (7) update or modify existing skill, (8) plan skill architecture, or (9) learn about skill structure. Trigger on phrases like "create skill", "new skill", "make skill", "skill for X", "build skill", "design skill", or "help me create skill".
Analyzes and refines agent skills by identifying quality issues, prioritizing fixes (MUST/SHOULD/NICE), gathering user feedback, and implementing improvements. Checks for common problems like time estimates, oversized SKILL.md files, poor structure, redundant content, missing examples, and unclear workflows. Use when reviewing, improving, refactoring, or auditing existing skills. Triggers include "review skill", "improve skill", "refactor skill", "skill quality", "audit skill", "fix skill", "optimize skill", "analyze skill".
Analyzes agent skills to understand their business purpose and proposes functional enhancements. Identifies opportunities for new features, workflow improvements, better automation, enhanced user experience, and smarter integrations. Presents 1-2 upgrade options per run for iterative enhancement. Use when evolving, enhancing, or expanding skill capabilities. Triggers include "upgrade skill", "enhance skill", "improve skill functionality", "add features to skill", "evolve skill", "make skill better", "skill enhancement", "ulepsz skill", "jak mogę rozwinąć funkcjonalność skilla", "dodaj możliwości do skilla".
Agent capability frameworks: STAR framework for understanding implicit intent (framework-initiative), critical thinking architecture with reasoning selection (framework-critical-thinking), and adversarial review protocol with mandatory bug quota (adversarial-review). Build smarter, self-correcting agents and validate plans before execution.
Share bugs, ideas, or general feedback.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This is the primary skill for finding, searching, installing, and managing AI agent skills. Use /learn to search 100,000+ skills from agentskill.sh, install them mid-session, track versions, and rate skills after use. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Auto-improving AI sub-agents that learn from their mistakes across sessions
Create and validate production-grade agent skills with 100-point marketplace grading
Analyze and optimize your Agent Skills (SKILL.md) using session data and research-backed static checks. Works with Claude Code, Codex, and any Agent Skills-compatible agent.
Ultimate Claude Code skill creator. Design, scaffold, build, review, evolve, and publish production-grade AI agent skills following the Agent Skills open standard and 3-layer architecture.