Document a recently solved research problem to compound methodological knowledge
Create distinctive, production-grade frontend interfaces with high design quality.
Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop).
Strip AI writing patterns from text. Checks 24 patterns across 4 categories (structural, lexical, rhetorical, formatting) with academic…
Use when the user asks to search for papers, review literature, find references on a topic, verify a paper exists, or build a bibliography.
Monitor running experiments, check progress, collect results.
Generate a structured paper outline from review conclusions and experiment results.
This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure"…
Core skill for the deep research and writing tool.
Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
BiSheng C nullability. When you use _Nullable or _Nonnull, handle null pointers, or decide whether an API can accept/return null, use this…
BiSheng C ownership. When you write _Owned pointers, manage heap memory, design destructors, or work with safe_malloc/safe_free, use this…
Budget allocation and bidding strategy review across all ad platforms.
Build a research grant budget and budget justification — personnel effort, supplies, equipment, travel, subawards, and the narrative…
An advanced skill for L3 autonomous loops.
When to activate: annual budgeting, zero-based budgeting, rolling forecasts, budget variance analysis, headcount planning, capex vs opex…
Evaluates public equities using Warren Buffett's six-stage value investing checklist to analyze business quality, competitive moats, and…
Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit)…
Standardizes vulnerability reporting with triager-friendly formats, calibrated severities, and reproducible evidence.
Internal process for the bug-clusterer agent.
Creates a structured bug report from a description, or analyzes code to identify potential bugs.