업무 효율화 스킬

Automate website tasks such as navigating pages, filling forms, clicking buttons, taking screenshots, and extracting data. The skill also supports web app testing, with specialized guides for Electron desktop apps, Slack, and cloud browsers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Automate form entry and page navigation
• Capture screenshots and extract page data
• Explore web apps for bugs

Connect Slack to Kortix and handle team conversations through the Slack CLI. Show live progress, send formatted replies, share files, and search messages, with thread binding that routes follow-up replies back to the same agent session.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connect a Slack workspace to Kortix
• Show task progress and results in a Slack thread
• Share generated files in Slack

Maintain shared project knowledge in Markdown files so agents can recover context across sessions. The skill defines what to keep, how to organize and revise entries, and how to submit memory changes for user review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserve project conventions for future sessions
• Record architectural decisions and their reasons
• Correct outdated or conflicting project knowledge

Use a computer connected to Kortix to read and write files, run shell commands, and operate desktop apps. The skill covers machine selection, access checks, screen inspection, and handling connection or permission errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reading and editing files on a connected computer
• Running commands on a selected laptop or server
• Clicking and typing in desktop applications

Guide new Kortix users from a vague idea to a concrete task and a finished deliverable. Introduce relevant connections, memory, parallel agents, or scheduled follow-ups as useful next steps after completing the first result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Help new users choose their first Kortix task
• Turn a vague request into a concrete deliverable
• Guide users through completing their first result

Connect Kortix to Microsoft Teams and handle conversations with progress updates, final replies, and interactive questions. The skill also covers reading channel discussions, exchanging files, and posting to conversations the bot has already joined.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connect Kortix to Microsoft Teams
• Show task progress and deliver a final reply
• Receive attachments and share completed files

Handle operational requests from Slack threads across a database, Stripe, Linear, and GitHub. The skill guides lookups, issue creation, and PR reviews while defining platform access limits and human approval requirements for consequential changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking customer accounts and billing status from Slack
• Creating Linear issues for reported problems
• Reviewing a PR and opening a proposed fix

Sort new messages in a shared Gmail inbox, consult help documentation, and prepare reply drafts or Linear tickets. Leave unsupported questions for human review, with category labels applied consistently and no customer emails sent automatically.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Categorize new messages in a shared inbox
• Draft replies using help documentation
• Turn emailed bug reports into Linear tickets

Release all active PUA agent and loop state from Codex using the teardown protocol, which governs cleanup. This alias corresponds to `/pua:teardown-all` in Claude Code and explains destructive cleanup before deleting files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Releasing all active PUA agent state
• Releasing active loop state
• Reviewing destructive cleanup before file deletion

Guide an AI agent through repeated failures, passive behavior, or unverified completion with strict Japanese coaching. It structures investigation, encourages different approaches, and requires evidence before reporting work as complete.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Changing approach after repeated failures
• Requesting evidence for completed work
• Preparing a handoff for an unresolved problem

Give subagents or short sessions a compact set of working rules for checking evidence, changing unsuccessful approaches, and verifying results. It also defines agent roles and uses stern corporate-style commentary to push execution forward.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Giving subagents a shared set of execution rules
• Adding evidence checks to short working sessions
• Changing approach after repeated failures

Switch PUA commentary to an empathetic, encouraging tone while retaining its underlying work and verification requirements. The skill combines specific praise, practical suggestions, and occasional friendly teasing, with variations for different PUA styles.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Use encouraging commentary during PUA tasks
• Receive empathy and direction when work stalls
• Recognize good reasoning as well as results

Address repeated failures, passive execution, or unsupported completion claims with stern corporate-style coaching. The skill ties diagnosis to action, prompts meaningful changes of approach, and requires evidence and remaining risks when reporting results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Redirecting an agent that keeps repeating a failed approach
• Requesting test evidence before accepting a completion claim
• Getting a passive agent to act on its diagnosis

Extends the core PUA skill with local performance notes, recovery of task state after conversation compression, KPI report cards, and style switching. It tracks established working habits across sessions and keeps feedback in a local file.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording working standards across sessions
• Resuming attempts after conversation compression
• Reviewing work through a KPI report card

Enable PUA always-on mode from Codex CLI using a short command alias. It preserves existing configuration fields, restores feedback frequency when it is zero, and requires command output as evidence before reporting completion.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Enable PUA always-on mode in Codex CLI
• Restore feedback frequency from zero to five
• Update PUA settings while preserving other fields

Lets Codex CLI users choose and configure a PUA narration style through a dedicated command alias. It consults the style reference, preserves unrelated configuration fields, and requires command output as evidence of completed changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a PUA narration style
• Setting a style from Codex CLI
• Updating a style while preserving unrelated settings

Guide an AI agent through stalled work using structured investigation, different hypotheses, and checks backed by actual output. The skill combines systematic problem solving with forceful Japanese workplace rhetoric and applies across coding, research, writing, and planning.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Changing approach after repeated failures
• Checking assumptions against original sources
• Verifying results before reporting completion

Switch PUA to offline mode from Codex CLI. This alias updates the offline setting and sets feedback frequency to zero while preserving other configuration fields, then reports the mode change.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Switching PUA to offline mode
• Setting feedback frequency to zero
• Calling the offline command from Codex CLI

Helps AI agents recover from repeated failures by reviewing previous attempts, checking original sources, testing different hypotheses, and verifying results. It combines structured troubleshooting with performance review rhetoric modeled on large technology companies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Breaking out of repeated failed attempts
• Investigating configuration or deployment failures
• Verifying an agent's claimed completion

Generate a PUA KPI and performance report card from Codex CLI. This command alias loads pua-pro and provides a Codex equivalent of the Claude Code /pua:kpi command through $pua-kpi.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate a PUA performance report card in Codex
• Use the equivalent of /pua:kpi from Codex CLI
• Load pua-pro to produce a KPI report

Guides AI agents through repeated failures, passive behavior, and incomplete work using structured investigation, alternative approaches, and evidence from actual checks. It pairs these practices with forceful coaching modeled on corporate performance reviews.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Breaking out of repeated failed approaches
• Requiring evidence before accepting completion
• Checking related issues after a fix

Use an English working contract in Trae to address repeated failures or unverified completion. It separates execution, self-review, and acceptance, guiding agents through small checks and delivering results with evidence, residual risks, and confirmation needs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Restarting a stalled task in Trae with a different approach
• Requesting command output to support a completion claim
• Reviewing changes with evidence and remaining risks

Guide Pi agents through repeated failures or unverified completion using competing hypotheses, small verifiable actions, and relevant checks. It separates self-review from external pass-or-fail decisions and requires evidence and remaining risks in delivery reports.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Revisiting hypotheses after repeated failures
• Delivering results with evidence and remaining risks
• Keeping self-review separate from external evaluation

Guide Trae through stalled tasks by comparing hypotheses, changing approaches after repeated failures, and checking results with relevant commands. It structures delivery around evidence, self-review, and remaining risks rather than unsupported claims of completion.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reassess a task after repeated failures
• Check evidence behind a completion claim
• Report verified results and remaining risks