可能是最深度的 AI 投研报告 Skill：九章个股深研 + 九章财报深度分析，脚本化 DCF/EPV 与可复算估值

Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>, ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays whenever the question is whether a procedure is fit for its intended purpose. Triggers include "method validation", "analytical method validation", "AMV", "validation protocol", "acceptance criteria", "linearity", "reportable range", "accuracy and precision", "repeatability", "intermediate precision", "recovery", "LOD", "LOQ", "detection limit", "quantitation limit", "specificity", "robustness", "method transfer", "method comparison", "Deming", "Passing-Bablok", "Bland-Altman", "equivalence testing", "OOS investigation", "ICH Q2", "Q2(R2)", "Q14", "USP 1225", "ICH M10", "incurred sample reanalysis", "ISR", "CLSI EP", and any request to show that an assay works.

Multi-platform prediction market trading bot: trades weather temperature markets on Kalshi (KXHIGH series) and Polymarket using 31-member GFS ensemble forecasts + BTC 5-min microstructure signals. Kelly criterion sizing, signal calibration, React dashboard. (Highest profits $1.8k)

Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.

A public open sourced tool. Log4J scanner that detects vulnerable Log4J versions (CVE-2021-44228, CVE-2021-45046, etc) on your file-system within any application. It is able to even find Log4J instances that are hidden several layers deep. Works on Linux, Windows, and Mac, and everywhere else Java runs, too! TAG_OS_TOOL, OWNER_KELLY, DC_PUBLIC

Conduct phone-based accessibility intake interviews for users who cannot complete web-based accessibility audit forms (screen reader fatigue, motor impairment, low vision, cognitive load), and produce a structured result mapped to VPAT 2.4 / Section 508 conformance reporting fields.

Microbenchmarking for Modern C++

Autonomous skill-prompt optimization — Karpathy-style mutate/score/keep loop on SKILL.md. Triggers "autoresearch", "optimize skill", "tune", "evolve" a skill, "prompt optimization".

Build PFC 5.0 asphalt-mixture specimens with explicit aggregate objects, a declared homogenized-mastic or fine-particle abstraction, residual air voids, measured gradation conversion, contact-pair assignment, compaction, equilibrium, and mass-volume closure; use before Marshall, rutting, creep, or strength tests.

Conduct SPARK methodology analysis for new project inception. Use at the beginning of a new project, when evaluating significant features, before bootstrap-project to validate viability, or when pivoting an existing project.

Create a sprint plan for a new development cycle. Use when starting a new sprint, after completing wrapup-sprint, or when initializing Sprint 1 for a new project.