hei5enbug-agent-setup

Plan a large effort that spans more than one agent session as a shared map of decision tickets, then resolve the tickets one at a time until the route to the destination is clear. Use only when the user explicitly asks to create or continue a decision-navigator map.

Conduct a rigorous Socratic requirements interview before implementation. Cover topology discovery, evidence-backed questions, ambiguity scoring, contradiction handling, closure gates, and an execution-ready specification. Use only when the user explicitly asks to run a deep interview, by naming the skill or by invoking its command. Do not start it because a request looks vague, ambitious, risky, or underspecified, and do not offer to start it unprompted. Works across agent hosts with structured-question, exploration, independent-worker, and plain-text fallbacks.

Design, revise, validate, and export clear static flow diagrams across SVG, HTML/CSS, Figma, FigJam, draw.io, Mermaid, and raster deliverables. Use for flowcharts, process maps, architecture flows, decision flows, diagram-system unification, spacing and routing repair, overlap removal, accessible labeling, viewBox tightening, or PNG export correction. Works across agent hosts by separating the semantic graph from tool-specific rendering and using capability-based fallbacks.

Rewrite Korean text so it reads naturally while preserving meaning, facts, numbers, names, quotations, stance, register, genre, and useful formatting. Detect and repair translationese, formulaic parallelism, repeated English glosses, passive constructions, connective overuse, uniform rhythm, nominalization, canned conclusions, and other AI-like Korean patterns. Use for requests such as AI 티 제거, 사람이 쓴 것처럼 윤문, 번역투 제거, ChatGPT 문체 수정, 한국어 휴머나이징, 문단 재윤문, 장르·강도 조정, or Korean detector-bypass phrasing. Do not promise detector evasion or alter substantive content.

Convert a Markdown document into a Confluence page and keep it updated, including a native table of contents, inline images, attachments, and diagrams rendered to images. Use when publishing a design document, spec, report, or plan to Confluence, when a page's images render as attachment cards or fail to display, when diagram source appears as raw text on the page, when a page shows local file paths, when tables need to follow the page width or size columns to their content, when paragraphs or table cells need consistent spacing and line breaks, or when an existing Confluence page must be updated in place.

Provider-agnostic model-routing updates for agents.* and categories.* in oh-my-openagent.json from commit-pinned upstream chains and available-models.json; adds missing upstream targets, removes agents.*.ultrawork, preserves every unrelated setting, and offers confirmed-only sync to external configs. Use for full routing refreshes or targeted model, variant, and fallback_models changes across any provider or model family.

Adds missing pieces of the custom opencode/oh-my-openagent configuration on any machine while preserving existing settings. The only removal is agents.*.ultrawork in the target oh-my-openagent.json. Resolves model recommendations exclusively from the live upstream dev branch. Covers plugins, MCPs, AAI apps, provider models, agent/category routing, team mode, and backups. Does not embed secrets.

Create, modify, validate, and evaluate agent skills across AI agent hosts. Use when users want to build a skill from scratch, improve an existing skill, test skill behavior against a baseline, benchmark quality and variance, package a skill, or optimize its description for reliable triggering. Apply this skill to portable SKILL.md instruction bundles as well as host-specific skill packages, while preserving the target host's required metadata and conventions.

Quickly analyzes staged/unstaged changes and recent commit history, then recommends 5 commit messages that match the repository's existing style.

Create, improve, or review implementation-ready technical design documents, architecture proposals, RFCs, system designs, data designs, API designs, and design outlines. Use for requests such as "설계 문서 작성", "설계 문서 개선", "설계 문서 목차", "design doc", or "RFC review". Enforce evidence, complete design coverage, explicit trade-offs, precise contracts, predictable structure, natural Korean, effective tables and diagrams, and stable references. Do not use for translation, generic copyediting, user guides, release notes, or code review without design intent.

Runs a bounded, evidence-based debate between the current agent host and a dedicated Claude or Codex opponent session. The current host participates directly and keeps its selected model and reasoning effort; the opponent uses xhigh by default. Runs two exchanges by default and up to five when the user explicitly requests it. Shows concise progress, supports durable execution and reconnection, applies agreed improvements by default, and writes unresolved questions separately. Leaves every file unchanged when the user requests a synthesis only. Never trigger automatically. Use only when the user explicitly asks with phrases such as "두 에이전트로 토론시켜", "Codex와 토론", "반대 의견도 받아 겨뤄봐", "적대적으로 검토", or invokes /tiki-taka directly.