← All creators

mrcha033

User

MrCha Skills — portable Agent Skills for ChatGPT, Codex, and compatible agents

8 indexed · 0 Featured · 0 stars · avg score 62
Prolific

Categories

Indexed Skills (8)

AI & Automation Listed

advisor-review

Run a fixed GPT-5.6 Sol advisor-style review in the current task when the user invokes $advisor-review, says Advisor Review or @Advisor-Review, explicitly asks for an advisor/second opinion/adversarial review, or task instructions explicitly require independent review. Uses source-anchored evidence, bounded artifacts, and an adopt/reject/defer decision gate; do not substitute tool discovery, another task, or same-agent reflection.

0 Updated today
mrcha033
AI & Automation Listed

quant-stock-technical

Calculate reproducible, numbers-only stock technical analysis and deterministic KOSPI, KOSDAQ, NYSE, and NASDAQ target-universe screening from completed daily adjusted OHLCV and benchmark data. Use when the user wants an as-of-date market/ticker report, short-, medium-, and long-horizon opinions, a quantitative risk counterpoint, entry/stop/take-profit levels, a 0-100 technical-strength score, or a frozen four-exchange screening artifact for a separate execution system. Do not use news, fundamentals, analyst views, narrative judgment, intraday execution, or live-order claims.

0 Updated today
mrcha033
AI & Automation Listed

stock-scenario-story

Research and perform a vivid, numbers-free, evidence-grounded stock story only after a complete quant-stock-technical JSON result has passed the bundled handoff validator. Use when the user wants a flamboyant showman-style qualitative tale about a company's products, characters, competition, customers, catalysts, culture, policy pressures, dreams, and dangers as pure entertainment. Never run standalone, reveal or restate upstream numbers, reconstruct missing quant inputs, or present the performance as a forecast or personalized investment advice.

0 Updated today
mrcha033
AI & Automation Listed

agent-finish-line

Drive an implementation, experiment, migration, release, or debugging task to a bounded terminal outcome. Use when agent work keeps expanding, repeating tests, adding optional improvements, or stopping at an intermediate artifact instead of shipping the requested deliverable or naming one concrete blocker.

0 Updated today
mrcha033
AI & Automation Listed

yonsei-central-student-governance-counsel

Build source-grounded arguments for Yonsei University's Sinchon and International Campus undergraduate central student governance, including the General Student Council's student assembly, student referendum, expanded steering committee, central steering committee, legislation and audit bodies, plus the General Student Club Union's representatives meeting, steering committee, and central bodies. Reject other universities, Future Campus, and graduate governance, and require body-specific rules before advising on college, department, special, branch, or college-club-union bodies. Adaptively trace official publication paths with deterministic public access and Insane Search fallback. Use when a user supplies an agenda, dispute, desired position, motion, amendment, procedural objection, quorum question, sanction, finance, election, or registration issue and wants current rules turned into a meeting-ready argument with counterarguments, exact citations, and explicit uncertainty.

0 Updated today
mrcha033
AI & Automation Listed

quant-stock-polling-trader

Plan, validate, poll, and reconcile deterministic Korean and U.S. stock orders through broker adapters after a frozen quant-stock-technical screen. Use when the user wants a first-hour entry window, Toss Securities or Korea Investment & Securities API integration, paper/shadow/live promotion gates, cross-broker exposure snapshots, position sizing, order-state recovery, or fail-closed automated trading. Never infer missing risk, account, fee, FX, calendar, fractional-share, or broker semantics.

0 Updated today
mrcha033
AI & Automation Listed

katok-reply-reuse

Find and reuse the user's own past KakaoTalk replies for a new incoming message, with provenance and only explicit placeholder substitution. Use when the user asks what to reply, wants their real KakaoTalk tone, dislikes AI-sounding rewrites, or wants a past response to a similar situation retrieved from a macOS KakaoTalk archive.

0 Updated today
mrcha033
AI & Automation Listed

learnus-course-copilot

Use the user's authenticated browser session to inspect Yonsei LearnUs courses, collect authorized course materials, identify assignments and deadlines, and produce study-ready structured output. Use for LearnUs course pages, lecture resources, VOD links, assignment tracking, or downloads when credential-based scripts fail or SSO state must remain in the browser.

0 Updated today
mrcha033

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.