GET /v1/agent/search?capability=web_search
SKILL.md v2 also accepted as compatibility input.
Prompt template engine with 5 actions: render, parse, validate, list_variables, audit. Zero external dependencies. Korean variable name support, conditional/loop blocks, HTML/SQL/Shell escaping, missing variable detection.
Text chunking toolkit with 5 actions: chunk, detect_boundaries, count_tokens, merge_chunks, audit_chunk_quality. Zero external dependencies. 6 strategies including Korean sentence boundary detection, token-aware chunking, overlap management.
AI tool-call validator with 5 actions: validate_input, validate_output, dry_run, sanitize, audit_schema. Zero external dependencies. JSON Schema Draft 7 self-implemented. Detects path traversal, prompt injection, and type mismatches with auto-fix hints.
LLM API cost estimator with 5 actions: estimate, compare_models, project_budget, simulate_cache, audit_pricing_freshness. Zero external dependencies. Covers Claude/GPT-4o/Gemini pricing, Korean token heuristics, cache hit/miss simulation.
Readability scoring for English and Korean text. 5 actions: score, compare, suggest_improvements, audit, segment. Zero external dependencies. Flesch-Kincaid + Korean heuristics.
Conventional Commits v1.0 linter with 5 actions: lint, parse, suggest_fix, audit, generate_template. Zero external dependencies, breaking-change detection, 50/72 rule, Korean support.
HTML to Markdown converter with 5 actions: convert, sanitize, extract_text, extract_links, audit. Zero external dependencies, GFM tables/strikethrough/task lists, script/style removal.
Validates business model feasibility with financial projections and Go/No-Go scoring.
Converts user behavior data into actionable insights with friction analysis and experiment design.
Models marketing channel attribution with multiple methodologies and budget optimization.
Cohort analysis with LTV prediction, churn modeling, and retention strategy recommendations.
Creates brand positioning maps, identifies white space opportunities, and generates messaging frameworks.
Analyzes financial statements with 20+ ratios, anomaly detection, and industry benchmarking.
Analyzes budget vs actual variances with root cause decomposition and scenario simulation.
AI risk classification, governance policy generation, and NYC LL 144 bias audit for US employment AI systems
Plan SEO blog structure, generate meta tags and JSON-LD schema markup, audit existing content for SEO issues, and design CTA strategy by funnel stage.
Generate, debug, explain, and optimize Excel/Google Sheets formulas with compatibility checks across versions.
Draft, adjust tone, check for passive-aggressive language, optimize subject lines, and suggest replies for US business emails.
Extractive text summarization toolkit: TextRank, frequency & position heuristics, Korean-first, zero external dependencies. Actions: extract, score_sentences, detect_topics, compare_summaries, audit.
Data visualization code generator: auto-detects data shape, recommends chart type, generates matplotlib/plotly/D3 code, applies colorblind-safe Okabe-Ito palette. Zero external deps. Actions: recommend, generate_code, palette, audit, examples.