skill

Run iterative agent evaluation and improvement loops (judge, improve, scenarios, playbooks) via pi-autocontext or autoctx CLI. Use when improving repeatable agent workflows (review rubrics, skill quality, scenario-based feedback), checking run status, or accumulating knowledge—not for one-off code edits or repo pattern drift (use continuity) or single PR review (use zereight-review).

Pi-native evaluate→improve→persist harness. Provides a systematic loop for generating candidates, judging them against rubrics, and accumulating knowledge as playbooks. Use for iterative output improvement, not for one-off edits (use continuity) or single PR review (use zereight-review).

Audit agent skills — token cost, duplicates, outdated plugin versions, unused skills, and overly long descriptions. Use when trimming skill prompt budget, finding duplicate or unused skills, auditing plugin versions, or deciding which skills to remove.

Diagnose why a skill is missing from Pi /skill or Cursor lists. Use when a skill exists on disk but does not appear, Pi shows only project or extension skills, or after adding a repo skill under .agents/skills/.

Comprehensive code review skill for practical PR feedback. Use for feature, bugfix, and refactor reviews. Prioritizes correctness, edge cases, logic invariants, fallback-chain safety, async state transitions, architecture analysis, OWASP security, and clear actionable feedback.

Skill map and inventory workflow. Use for scanning installed skills, skill overview, 스킬 목록, skill map.

Inspects Cursor agent transcript history, analyzes repeated assistant mistakes, and turns durable learnings into corrective skills or context updates. Use when the user asks to review previous Cursor chats, learn from a failed interaction, run /session-lessons, or stop the model repeating a mistake.

Comprehensive code review skill for practical PR feedback. Use for feature, bugfix, and refactor reviews. Prioritizes correctness, edge cases, logic invariants, fallback-chain safety, async state transitions, architecture analysis, OWASP security, and clear actionable feedback.

Create and maintain BankX deep link request tickets from PRDs, specs, notification requirements, or screen requests. Use when the user asks to request BankX deeplinks, create MAR Jira tickets, extract deeplink needs from PRDs/docx files, follow the "How to request deep link" Confluence workflow, or update deep link request issues on bankx.atlassian.net.

Use this skill when a task needs MCP tools, internal app connectors, or "use mcp" behavior. Search and inspect mcporter servers/tools first, then call the right MCP tool through mcporter before using browser, REST, raw CLI, or other fallback paths.

Guide for using roborev continuous background code review. Use when the user asks about roborev install paths, git hooks, daemon status, review results, TUI, show/list/log commands, agent/model configuration, Codex/Claude/Pi agent settings, post-commit behavior, auto-fix, refine, or troubleshooting roborev review jobs.

Prepare evidence-backed competency and growth profiles for 1on1, self-review, performance review, promotion prep, or stage calibration. Use when the user wants STAR examples, competency category mapping, Stage 2-3 evidence, manager talking points, weak-evidence checks, or questions to ask in a growth/performance conversation.

Explicit-only opencode delegation skill for research drafts, source discovery, timeline/IOC drafts, file/text edits, code exploration, first-pass triage, and review-assist candidate discovery. Codex must verify primary evidence before final conclusions.

Cost-aware Chorus review workflow for explicit review requests only. Use only when the user explicitly invokes `$chorus-review`, says `chorus-review`, or asks to review with Chorus. Routes review work through a Claude-optional, Codex xhigh, Gemini review profile; preserves normal Codex low reasoning outside review; checks Claude health before use; avoids spending Claude/Codex quota unless this skill was explicitly requested.

Content card and visual export workflow. Use for PNG cards, infographics, comic cards, whiteboard visuals, 카드로 만들어줘, 이미지로 정리, 정보그래픽, 만화 카드, 화이트보드.

Investment analysis workflow. Use for startup, token, stock, product, market, 투자 분석, 사업성 검토, 프로젝트 분석.

Concept learning and explanation workflow. Use for concept breakdown, learning, 개념 설명, 쉽게 이해, 공부 도와줘.

Paper workflow combining reading and card creation. Use for paper summary plus visual card, 논문 읽고 카드, paper to card.

Paper lineage and related work tracing workflow. Use for citation trail, prior work, follow-up research, 논문 계보, 관련 연구.

Paper reader and idea extraction workflow. Use for research papers, arXiv links, PDFs, 논문 분석, 논문 읽기, paper review.

Plain language rewriting workflow. Use for simplify, explain like I am smart but new, 쉽게 풀어줘, 번역투 제거, 쉬운 설명.

Presentation slide/card generator. Use for outline to slides, keynote cards, 발표 자료, 슬라이드 초안, slogan deck.

Skill sync helper. Use for syncing local ljg skills, skill publishing, 스킬 동기화, skill push.

Q&A extraction workflow. Use for turning articles, books, papers into question-answer chains, 질문 뽑기, Q&A 정리.

Core driver analysis workflow. Use for finding first principles, independent factors, 핵심 요인, 구조 분석, first principles.

Reading companion workflow. Use for books, essays, articles, close reading, 같이 읽기, 독해, text walkthrough.

Relationship analysis workflow. Use for interpersonal patterns, conflict, conversation, 관계 고민, 대화 분석.

Structured roundtable discussion workflow. Use for multi-perspective debate, panel discussion, 관점 토론, 라운드테이블.

Deep thinking workflow. Use for root-cause thinking, why analysis, 본질 분석, 깊게 생각, drill down.

Travel research workflow. Use for city research, museums, architecture, itinerary context, 여행 리서치, 도시 공부.

Word study plus infographic workflow. Use for word analysis and visual card, 단어 분석 카드, vocabulary card.

English word deep-dive workflow. Use for vocabulary, etymology, nuance, 영어 단어, 단어 분석, word study.

Writing workflow for developing an idea into an essay. Use for essay draft, argument writing, 글쓰기, 초안, 생각 정리.

Create clean ASCII diagrams for code comments and documentation. Use when the user wants box-and-arrow diagrams, flow charts, tables, trees, or other ASCII art that can be pasted into source-code comments, README files, design notes, or issue/PR explanations.

Read or verify Atlassian Jira and Confluence items through mcporter. Use for bankx.atlassian.net links, Jira issue keys, Confluence pages, Jira ticket validation, JQL/CQL searches, or when another Jira MCP wrapper fails.

Use this skill for Bitbucket Cloud work when the user wants REST/API access through injected environment variables and explicitly does not want Bitbucket MCP, mcporter Bitbucket, or connector-backed Bitbucket tools.

Stress-test a strategy until confidence is evidence-backed. Use when the user asks whether a plan is 100% reliable, wants loopholes found, or asks to iterate fixes until the strategy is factually solid.

Addy agent-skills pack entrypoint. Use when you want to find or use Addy Osmani's agent-skills workflows, including addy-test-driven-development, addy-code-review-and-quality, addy-security-and-hardening, addy-source-driven-development, and related addy-* skills.

Situational learning coach that helps the user recognize a concrete situation, understand the key concept, practice with targeted exercises, receive feedback, and adapt future explanations to the user's learning style. Use when the user wants to learn from a specific scenario, mistake, code review, workflow, decision, incident, concept, or repeated pattern; when they ask for practice questions, quizzes, coaching, tutoring, drills, feedback, or step-by-step learning; or when the agent should turn an observed situation into a teachable moment.

Gateway skill for React Native development. Routes tasks to the right specialist skill — basics, animations, state, navigation, native modules, testing, deployment, or Storybook. Use when starting any React Native development task.