Loading...
Loading...
Found 22 Skills
Chinese Resume-Driven Interview Prediction and Deep Grilling Skill: Reads the user's resume and target job position, extracts experience Claims that need verification, predicts high-probability interview questions, and identifies knowledge gaps that are listed on the resume but cannot be clearly explained through layered questioning; activated when the user inputs "/interview", requests interview prediction, mock interviews, resume grilling, stress interviews, or checks resume mastery.
Create a hedera-harness recipe — PRD, recipe file, validators, and optional stages — by grilling an idea into a runnable feature spec. Use when the user wants to turn a Hedera feature idea into harness inputs.
Triggers when a user asks to prototype a decision, compare visible or behavioral options in throwaway pages, keep prototyping through a consultant, grilling, or wayfinder session, or says /prototyping. It builds one loopback session that grows step by step and also handles a one-off "prototype this" request. Not for durable standalone HTML artifacts, polished product demos, browser QA, or integrating selected prototype code into an application.
Take a prepared task and run it to 'ready for human review' on your own: code, self-review loop, self-fixes, verification, commits by the team convention, and an honest handover report. Use when the developer hands over a task whose analysis and grilling are already done — trigger on «реализуй задачу», «запускай в работу», «пили», «делай задачу», «бери таску», implement the task, run this task, even when the skill is never named and even right after a grill session ends. NOT for a small change the developer is watching — that is quick-edit. Does not analyse or grill the task, does not estimate it, and does not create the merge request.
Researches internal or external ecosystem evidence for a design decision and returns decision-oriented patterns with sources. Use during design, grilling, retrospectives, architecture work, or implementation planning when the user asks to research a topic, compare external systems, inspect prior sessions, analyze patterns, or gather evidence before deciding.
Reads and writes ClickUp tasks through the clickup CLI: prepares a task for grilling (card, comments, linked tasks, statement in the developer's own words, list of unknowns), creates tasks and bug reports to the team's own convention, puts estimates and comments on tasks. Use whenever the user gives a ClickUp task id or app.clickup.com/t/ URL, or says «прочитай задачу», «что в таске», «подготовь к грилю», «заведи таску», «багрепорт», «поставь оценку», «напиши коммент в таску», read the task, create a task, bug report, estimate the task, comment on the task — even when ClickUp is never named and even when the request looks like a one-liner.
Ask me questions within this workspace regarding the workflow requirements I want to build.
A rigorous interrogation session for refining plans or designs, with documentation (ADR and glossary) generated during the process.
Interview me about the workflow specifications I want to build in this workspace.
A relentless interview to sharpen a plan or design.