AI Agent Workflow Collection

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms.

Presentation creation, editing, and analysis.

Aphorism management. USE WHEN aphorism, quote, saying. SkillSearch('aphorisms') for docs.

Social media scraping, business data, e-commerce via Apify actors. USE WHEN Twitter, Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon scraping.

Extended thinking mode. USE WHEN be creative, deep thinking, deep thinking, extended reasoning. SkillSearch('becreative') for docs.

Analyze text content using both traditional NLP and LLM-enhanced methods.

Generate TypeScript CLIs. USE WHEN create CLI, build CLI, command-line tool. SkillSearch('createcli') for docs.

MANDATORY skill creation framework for ALL skill creation requests. USE WHEN user wants to create, validate, update, or canonicalize a skill, OR user mentions skill creation, skill development, new skill, build skill, OR user references skill compliance, skill structure, or skill architecture.

Agent evaluation framework based on Anthropic's best practices. USE WHEN eval, evaluate, test agent, benchmark, verify behavior, regression test, capability test. Includes three grader types (code-based, model-based, human), transcript capture, pass@k/pass^k metrics, and ALGORITHM integration.

Intelligent prompt pattern system with 240+ specialized patterns for content analysis, extraction, and transformation.

Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start an investigation" or wants to: trace code paths or data flow ("trace from X to Y", "what touches X", "follow the wiring"), document system architecture comprehensively ("document how the system works", "archeology"), investigate bugs ("figure out why X happens"), explore technical feasibility ("can we do X?"), or explore design options ("explore the API", "gather context", "design alternatives"). Creates dated folder with README. NOT for simple code questions or single-file searches.

Extract system improvements from content AND monitor external sources (Anthropic ecosystem, YouTube).

Ethical people-finding. USE WHEN find person, locate, reconnect, people search, skip trace. SkillSearch('privateinvestigator') for docs.

Prompt injection testing. USE WHEN prompt injection, jailbreak, LLM security, AI security assessment, pentest AI application, test chatbot vulnerabilities.

Security reconnaissance. USE WHEN recon, reconnaissance, bug bounty, attack surface. SkillSearch('recon') for docs.

Spawn a one-shot red-team subagent to challenge a milestone result. Calibrated to return "nothing substantive" when the work is sound — does not invent issues to seem thorough. Use at goal-locked, major-result, or pre-write-up milestones, or whenever you want a deliberate adversarial check on something specific.

Security news aggregation from tldrsec, no.security, and other sources. USE WHEN security news, security updates, what's new in security, breaches, security research, sec updates. SkillSearch('secupdates') for docs.

Voice server management. USE WHEN voice server, TTS server, voice notification, prosody.

Web security assessment. USE WHEN web assessment, pentest, security testing, vulnerability scan. SkillSearch('webassessment') for docs.

아이디어 탐색부터 Epic 생성까지 원스톱 워크플로우. Use when (1) 러프한 아이디어가 있을 때, (2) 새 기능/프로젝트 구상 시, (3) "뭔가 만들고 싶어", (4) 가설 수립 및 검증 필요 시.