개발 스킬

Build structured 3-scenario financial models (Base / Bull / Bear) for business planning or investment decisions. Sensitize revenue and cost drivers across scenarios, produce P&L summaries, cash flow bridges, and executive narratives. Aligns with FP&A 2.0 and CIMA Management Accounting standards. Use when leadership needs to understand the financial impact range of a decision. Do not use for statutory financial reporting or audit-ready financials.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build and maintain a rolling financial forecast using a 12–18 month horizon. Lock actuals, reforecast remaining periods, extend the planning window, and generate a waterfall bridge showing prior-to-new variance. Use monthly or quarterly when the organization follows a continuous planning cadence instead of annual budgets.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Draft concise follow-up messages, nudges, reminders, and recap emails from open decisions, stale requests, or recent meetings. Use when the work is repetitive business writing with known context. Do not use for sensitive legal language, high-stakes negotiation, or board-level communication without review.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Record and track organizational decisions using the RAPID framework. Captures decision context, options analysis, RAPID roles, risk assessment, and communication plan. Use when making cross-functional decisions, documenting governance choices, or building an auditable decision trail.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Prepare customer or executive business reviews with outcome tracking, adoption health, ROI narrative, risks, commitments, and next-quarter plan using customer success and CX frameworks. Use when teams need QBRs, success plans, churn-risk conversations, or executive account reviews. Do not use for generic slide beautification or cold outreach prospecting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Map the end-to-end customer journey across awareness, consideration, purchase, onboarding, adoption, retention, and advocacy stages. Identify touchpoints, pain points, emotions, and Moments of Truth per stage. Use when designing or improving customer experience. Do not use for internal employee process mapping — use process-mapper instead.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build change management plans using ADKAR and Kotter's 8-Step framework. Covers stakeholder readiness, communication plans, training schedules, resistance management, and adoption metrics. Use when rolling out new systems, reorganizations, or process changes that affect people.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build competitive intelligence briefs following the CI cycle — Plan, Collect, Analyze, Disseminate. Profile competitors, create feature comparison matrices, analyze pricing, build positioning maps, and identify win/loss patterns. Use when preparing for product launches, sales enablement, or strategic reviews.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Delegate coding tasks to Codex AI for implementation, analysis, and alternative solutions. Use when you need a second AI perspective, want to explore different approaches, or need specialized Codex capabilities for complex coding tasks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guide for creating VS Code extensions and plugins from scratch through Marketplace publication. Use when developing a VS Code extension/plugin, adding commands or keybindings, building TreeView or Webview UI, publishing to Marketplace, or troubleshooting activation and packaging issues.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design, run, and review fair performance, token, and cost comparisons across GitHub Copilot CLI, Codex CLI, and direct model APIs. Use for AI CLI benchmark, Copilot vs Codex, prompt-cache diagnosis, cache read/write analysis, fresh-process latency measurement, token-cost comparison, or when a benchmark must separate provider caching from local CLI caches.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate ASCII-art text banners for terminals, READMEs, and CLI startup messages. Use when a user asks for an ASCII banner, text art, バナー, アスキーアート, or a decorative header for a script/README.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guide for simplifying and refining code after coding sessions. Use when cleaning up complex code, reviewing PRs for readability, or applying consistent refactoring patterns. Triggers on simplify code, refactor, clean up, code review, コード整理, リファクタ, 複雑さ削減, コードレビュー.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Govern Asphalt-Codex-Skills-5 as a PFC 5.0-only asphalt-mixture package, enforcing version purity, external fistPkg boundaries, portable assets, validation, and release hygiene.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Optimize oversized agent instruction files using progressive disclosure. Handles CLAUDE.md (Claude Code), AGENTS.md (OpenAI Codex / GitHub Copilot agents), and copilot-instructions.md (GitHub Copilot). Auto-detects all three formats in your repo, analyzes content tiers, creates sub-documents using each format's native mechanism, and rewrites the main file with zero information loss. Triggers: optimize CLAUDE.md, AGENTS.md too long, reduce copilot-instructions.md, agent instructions file too large, shrink context file, apply progressive disclosure, instructions file bloated

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Unwraps hard-wrapped markdown files so that each sentence ends with a newline instead of mid-sentence line breaks. Joins continuation lines within a paragraph into single lines, then re-breaks at sentence boundaries (period, question mark, exclamation point). Preserves blank lines, headings, fenced code blocks, block quotes, and list items. Use when asked to unwrap text, fix line breaks, reflow sentences, or clean up hard-wrapped markdown or .qmd files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Translates LaTeX documents (.tex) to Typst (.typ), focusing on article-class documents. Use when asked to convert, port, migrate, or translate LaTeX to Typst. Covers document structure, text formatting, page layout, math equations and symbols, figures, tables, TikZ-to-CeTZ diagrams, bibliography, cross-references, footnotes, and code blocks. Includes comprehensive symbol mapping tables.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Developer personality portrait generator. Supports subcommands: (1) 'generate my portrait' / 'analyze my personality' — full analysis; (2) 'update my portrait' — incremental update since last analysis; (3) 'install persona from <url>' — install community persona from GitHub; (4) 'list personas' / '我安装了哪些人格' — show installed; (5) 'remove persona <id>' — uninstall; (6) 'think like <name>' / '像<name>一样思考' — activate a persona. Also triggers on 'vibe-portrait', 'what kind of developer am I'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

"Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OpenAI Codex CLI wrapper — three modes. (gstack).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Systematic debugging with root cause investigation. (gstack).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

"Apply social capital theory (Putnam, Coleman, Bourdieu, Burt) to analyze how network structures and trust generate value or impose constraints. Use this skill when the user needs to evaluate bridging vs bonding capital, identify structural holes or network closure benefits, assess community or organizational trust dynamics, or when they ask 'how does our network create value', 'are we too insular', or 'where are the structural holes we can exploit'.".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Triage and address GitHub PR review comments systematically—classify, respond, fix or defer with rationale. Use when a PR has review feedback, requested changes, or unresolved threads.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.