Agent skill

Vibe Sunsang Retro

by fivetaku in fivetaku/gptaku-plugins-codex

Conversation-log converter — transforms Codex session JSONL logs into Markdown (with per-session metrics and an activity-sorted index) and provides an analysis guide.

MITAuto-check passed

Install Vibe Sunsang Retro

skills CLI
$ npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-retro -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install fivetaku/gptaku-plugins-codex vibe-sunsang-retro --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/fivetaku/gptaku-plugins-codex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/vibe-sunsang-codex/skills/vibe-sunsang-retro .claude/skills/vibe-sunsang-retro && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vibe-sunsang-retro
GitHub stars
128
Token cost
~1.1k tokens
SKILL.md length
509 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
MIT

At a glance

Conversation-log converter — transforms Codex session JSONL logs into Markdown (with per-session metrics and an activity-sorted index) and provides an analysis guide.

  • Works in 4 steps: 워크스페이스 자동 치유 (dead-end 방지) → 변환 스크립트 실행 → 인덱스 확인 → …
  • SKILL.md covers 데이터 경로, 실행: 대화 로그 변환, 회고 프레임 and Output, plus 1 more section
  • Calls python3 and python

What it does

Vibe Sunsang Retro is an agent skill from fivetaku/gptaku-plugins-codex. Conversation-log converter — transforms Codex session JSONL logs into Markdown (with per-session metrics and an activity-sorted index) and provides an analysis guide. Korean triggers: "변환", "대화 변환", "로그 변환", "회고", "이번 주 대화". English triggers: "retro", "convert conversations", "log conversion".

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Python. The repository describes itself as: Codex-native GPTaku plugin marketplace. The licence is MIT.

Example prompts

  • “convert conversations”
  • “log conversion”
  • “/vibe-sunsang-retro”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. 워크스페이스 자동 치유 (dead-end 방지)
  2. 변환 스크립트 실행
  3. 인덱스 확인
  4. 분석 템플릿 제안

What it can do on your machine

Read from SKILL.md and the folder at commit d3b47fc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vibe Sunsang Retro loads about 1.1k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 509 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from fivetaku/gptaku-plugins-codex at commit d3b47fc, republished under its MIT licence (© fivetaku). 509 words, ~1,104 tokens.

Download SKILL.mdSave it as .claude/skills/vibe-sunsang-retro/SKILL.md (or your agent's skills folder).
name
vibe-sunsang-retro
description
Conversation-log converter — transforms Codex session JSONL logs into Markdown (with per-session metrics and an activity-sorted index) and provides an analysis guide. Korean triggers: "변환", "대화 변환", "로그 변환", "회고", "이번 주 대화". English triggers: "retro", "convert conversations", "log conversion".

vibe-sunsang-retro (Codex)

Codex 세션 로그를 읽기 좋은 Markdown으로 변환하고 분석 가이드를 제공한다.

Codex는 skill-first다 (별도 커맨드 파일 없음). 객관식은 Codex CLI에 카드 UI가 없으므로 $PLUGIN_ROOT/shared/questioning-policy.md §A 번호 블록으로 채팅에서 묻는다.

데이터 경로

  • 원본: ~/.codex/sessions/**/*.jsonl ($CODEX_HOME/sessions가 있으면 그쪽. 다른 위치는 --sessions-dir)
  • 변환 결과: ~/vibe-sunsang/conversations/{프로젝트명}/
  • 인덱스: ~/vibe-sunsang/conversations/INDEX.md
  • 설정: ~/vibe-sunsang/config/
  • 리포트 저장: ~/vibe-sunsang/exports/
  • 변환 스크립트: $PLUGIN_ROOT/scripts/convert_sessions.py

프로젝트 = 세션의 작업 디렉토리(cwd). 표시 이름은 폴더명에서 자동 생성되고 config/project_names.json(cwd → 이름)으로 바꿀 수 있다. 같은 폴더명이 다른 경로에 있으면 부모 폴더명이 접두로 붙는다.

실행: 대화 로그 변환

인자: $ARGUMENTS

Step 0: 워크스페이스 자동 치유 (dead-end 방지)

파일 존재만 확인하고 튕기지 않는다. 다음을 실행해 워크스페이스를 스스로 준비한다:

bash
python3 "$PLUGIN_ROOT/scripts/ensure_workspace.py" 2>/dev/null || python "$PLUGIN_ROOT/scripts/ensure_workspace.py"

출력 마지막 줄 STATUS <fresh|v2|v1_migrated> CONFIG <present|absent>로 분기한다:

  • v1_migrated → "이전 버전 데이터를 새 구조로 옮겼어요." 한 줄만 안내하고 계속 진행한다.
  • CONFIG absent (fresh) → 아직 초기 설정 전이다. "처음이시네요 — 바로 준비할게요!" 안내 후 vibe-sunsang-onboard로 넘긴다 (자동 이름/기본 유형 lazy 온보딩 가능). 여기서 종료하지 말 것.
  • 그 외(v2, CONFIG present) → 그대로 다음 단계.
Step 1: 변환 스크립트 실행

인자를 분석하여 적절한 옵션으로 실행합니다:

인자동작
(없음)증분 변환 (새 세션·이어진 세션만)
"전체", "force", "다시"--force 전체 재변환
"상세", "verbose"--verbose 도구 결과 전문 포함
프로젝트명--project <이름> 해당 프로젝트만 (INDEX.md 표시 이름 또는 cwd 경로)

프로젝트명이 지정된 경우: ~/vibe-sunsang/conversations/INDEX.md에서 프로젝트 목록을 읽어 일치하는 프로젝트를 찾습니다. 정확히 일치하는 프로젝트가 없으면 shared/questioning-policy.md §A 번호 블록으로 묻는다:

text
질문: 어떤 프로젝트의 대화를 변환할까요?
1. {프로젝트명1} — {세션 수}개 세션 (가장 활발, 추천)
2. {프로젝트명2} — {세션 수}개 세션
3. 문장으로 직접 알려주세요
(모르면 1번으로 진행하겠습니다)

선택지는 INDEX.md에서 읽은 프로젝트 목록으로 동적 생성한다. 세션 수가 많은 순으로 정렬한다.

bash
# 기본: 증분 변환
python3 "$PLUGIN_ROOT/scripts/convert_sessions.py" --names-file "$HOME/vibe-sunsang/config/project_names.json" --output-dir "$HOME/vibe-sunsang/conversations" 2>/dev/null || python "$PLUGIN_ROOT/scripts/convert_sessions.py" --names-file "$HOME/vibe-sunsang/config/project_names.json" --output-dir "$HOME/vibe-sunsang/conversations"

# --force: 인자에 "전체", "force", "다시" 포함 시 위 명령에 --force 추가
# --verbose: 인자에 "상세", "verbose" 포함 시 추가
# --project <이름>: 인자에 프로젝트명 포함 시 추가
에러 처리

변환 스크립트 실행 중 문제가 발생하면 비개발자가 이해할 수 있게 안내합니다:

상황사용자에게 보여줄 메시지
Python 없음"Python이 설치되어 있지 않아요. 터미널에서 python3 --version을 실행해서 확인해주세요."
세션 폴더 없음"Codex 대화 기록을 찾을 수 없어요. Codex로 작업한 적이 있는지, ~/.codex/sessions/가 있는지 확인해주세요. 다른 위치면 --sessions-dir <경로>로 지정할 수 있어요."
권한 오류"파일에 접근할 수 없어요. ~/.codex/sessions/ 폴더의 권한을 확인해주세요."
변환 0건"새로 변환할 대화가 없어요. 이미 최신 상태입니다!"
Show full SKILL.md (216 more words)Show less
Step 2: 인덱스 확인

변환 완료 후 인덱스를 읽어 현황을 보여줍니다:

~/vibe-sunsang/conversations/INDEX.md를 읽습니다 (프로젝트별 세션 수·기간·최근 활동 컬럼, 최근 활동 순 정렬).

변환 결과를 요약합니다:

  • 총 프로젝트 수
  • 총 세션 수
  • 최근 변환된 세션
Step 3: 분석 템플릿 제안

변환이 완료되면 다음 분석 옵션을 제안합니다:

사용 가능한 분석:

  1. 프로젝트 패턴 분석

    "[프로젝트명] 세션들을 분석해줘. 주요 작업 유형, 반복 에러, 도구 활용 패턴을 정리해줘."

  2. 성장 트래커 → "성장 리포트 만들어줘" (vibe-sunsang-growth)

    성장 리포트를 생성합니다. (v2: 6축 기술 차원 분석 + 레이더 차트 포함)

  3. 멘토링 세션 → "멘토링해줘" (vibe-sunsang-mentor)

    AI 활용 능력을 코칭 받습니다. (v2: 6축 중심 맞춤 분석)

  4. 버그/실수 패턴

    "모든 프로젝트에서 내가 겪은 실수 패턴을 찾아줘."

  5. 멀티에이전트 리뷰

    "서브에이전트를 spawn한 세션을 분석해서 코디네이션 효율을 평가해줘." (frontmatter has_orchestration: true)

  6. 비용 분석

    "프로젝트별 토큰 사용량과 모델 분포를 정리해줘."

  7. 6축 분석

    "최근 세션을 6축(DECOMP/VERIFY/ORCH/FAIL/CTX/META) 기준으로 분석해줘."

회고 프레임

회고를 진행할 때 다음 프레임을 쓴다:

  • 사용자가 무엇을 잘 요청했는가?
  • 요청에 맥락이나 수용 기준(acceptance criteria)이 빠진 곳은 어디였는가?
  • 에이전트는 불확실성에 어떻게 반응했는가?
  • 테스트·인용·스크린샷·검증이 적절한 순간에 쓰였는가?
  • 다음에 연습할 행동 하나는 무엇인가?

Output

  • 기본은 간결한 한국어.
  • 사용자가 산출물을 원하면 ~/vibe-sunsang/exports/에 저장한다.

Guardrails

  • 원본 JSONL 로그를 직접 수정하지 않는다 (읽기 전용).
  • 변환된 로그에 보이지 않는 예시를 지어내지 않는다.
  • 변환 중 분석이 완료됐다고 말하지 않는다. 변환은 데이터 준비일 뿐이다.
  • Codex CLI에는 객관식 카드 UI가 없다 → shared/questioning-policy.md §A 번호 블록을 쓴다.

© fivetaku, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/vibe-sunsang-codex/skills/vibe-sunsang-retro of fivetaku/gptaku-plugins-codex.

Open the folder on GitHubat commit d3b47fc

Compare with similar skills

Vibe Sunsang Retro next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vibe Sunsang Retro compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vibe Sunsang Retro this skillfivetaku/gptaku-plugins-codex128—~1.1kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
PDF Processinganthropics/skills180k47 repos~2kAutomated safety check: PassProprietary
NotebookLM Research AssistantPleasePrompto/notebooklm-skill7.8k14 repos~2.4kAutomated safety check: NotesMIT
Manim Video Productionbrowser-use/video-use29k6 repos~3kAutomated safety check: PassMIT
PPT Masterhugohe3/ppt-master59k1 repos~2.5kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • PDF Processing

    anthropics/skills

    Official

    Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.

    180k GitHub starsUsed in 47 repos~2k tokens
    Documents & OfficeAuto-check passed
  • NotebookLM Research Assistant

    PleasePrompto/notebooklm-skill

    Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.

    7.8k GitHub starsUsed in 14 repos~2.4k tokens
    Knowledge ManagementAuto-check: notes
  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    29k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed
  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    59k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed
  • Scikit Learn

    zLanqing/codex-claude-academic-skills

    Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.

    4.7k GitHub starsUsed in 16 repos~3.9k tokens
    Data & AnalyticsAuto-check passed

More from fivetaku/gptaku-plugins-codex

All 25 skills in this repo
  • Pumasi Image

    fivetaku/gptaku-plugins-codex

    Image-generation companion skill for the pumasi plugin family.

    128 GitHub stars~3.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Insane Research Pipeline

    fivetaku/gptaku-plugins-codex

    Runs a multi-agent deep research workflow in seven phases, from scoping questions to a final report with source triangulation, state tracking and quality ratings.

    128 GitHub stars~7.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Skillers Suda

    fivetaku/gptaku-plugins-codex

    This skill should be used when the user asks to "스킬 만들어줘", "에이전트 만들어줘", "커맨드 만들어줘", "스킬러들의 수다", "수다", "Codex 스킬 만들어줘", "이 스킬 분석해줘", "이 스킬 개선해줘", "skill builder", "make a skill", "create a skill"…

    128 GitHub stars~6k tokensUpdated 1 mo ago
    Auto-check passed
  • Dd

    fivetaku/gptaku-plugins-codex

    A skill your agent uses when the user runs /dd or /ㅇㅇ (Hangul IME alias — typing "dd" in Korean IME produces "ㅇㅇ") to act on the current OS clipboard (text or image) without pasting it into chat.

    128 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed
  • Insane Search

    fivetaku/gptaku-plugins-codex

    Adaptive access for blocked websites — tries every method until one works.

    128 GitHub stars~5.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Docs Guide

    fivetaku/gptaku-plugins-codex

    Fetch and explain official documentation for any library, framework, API, or service using an llms.txt-first strategy — triggers on "How do I…", "What is…", "How does X work", "Best practice for…"…

    128 GitHub stars~3.5k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Vibe Sunsang Retro

What does Vibe Sunsang Retro do?

Conversation-log converter — transforms Codex session JSONL logs into Markdown (with per-session metrics and an activity-sorted index) and provides an analysis guide. Vibe Sunsang Retro is an agent skill from fivetaku/gptaku-plugins-codex. Conversation-log converter — transforms Codex session JSONL logs into Markdown (with per-session metrics and an activity-sorted index) and provides an analysis guide.

How do I install Vibe Sunsang Retro in Claude Code?

Run `npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-retro -a claude-code`. Or copy the skill folder (plugins/vibe-sunsang-codex/skills/vibe-sunsang-retro in fivetaku/gptaku-plugins-codex) into .claude/skills/vibe-sunsang-retro in your project. Claude Code loads it when a task matches its description.

How do I install Vibe Sunsang Retro in Codex?

Run `npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-retro -a codex`. Or copy the skill folder (plugins/vibe-sunsang-codex/skills/vibe-sunsang-retro in fivetaku/gptaku-plugins-codex) into .agents/skills/vibe-sunsang-retro in your project. Codex loads it when a task matches its description.

Can I use Vibe Sunsang Retro in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-retro -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vibe-sunsang-retro, .gemini/skills/vibe-sunsang-retro, .github/skills/vibe-sunsang-retro and .opencode/skills/vibe-sunsang-retro in your project.

What does Vibe Sunsang Retro need to run?

Going by SKILL.md and its folder, Vibe Sunsang Retro needs the command-line tools its instructions call (python3 and python). Our summary lists: Python 3.

Does Vibe Sunsang Retro access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vibe Sunsang Retro safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vibe Sunsang Retro use?

Vibe Sunsang Retro is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vibe Sunsang Retro use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vibe Sunsang Retro?

Skills that share tags, products or a category with Vibe Sunsang Retro: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vibe Sunsang Retro?

fivetaku (a GitHub user) maintains it in fivetaku/gptaku-plugins-codex, which has 128 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on September 8, 2026.

Source: fivetaku/gptaku-plugins-codex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.