본문으로 건너뛰기
cccskills
무료GitHub에 공개

pmstudio-changelog

Create or update a structured change log for a product or platform. Use when someone asks to "create a change log", "log this change", "what changed", "update the change log", "release notes", or "changelog". Reads project memory (CLAUDE.local.md Recent Changes) and meeting notes to build chronological change records. Supports init (backfill from memory), update (append new entries), and release (summarize for a version).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md4.5 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Change Log — Running Product Change Record

Purpose

Maintains a chronological, append-only record of all meaningful changes to a product. Unlike CLAUDE.local.md (which is AI context), the change log is a stakeholder-facing document suitable for sharing with leadership, auditors, and team members.

Process

Step 1: Determine Mode

  • /change-log init — Create new change log, backfill from CLAUDE.local.md
  • /change-log update — Find changes since last entry, propose new entries
  • /change-log release {version} — Create release summary from accumulated entries
  • /change-log (no args) — Same as update

Step 2: Read Context

Always read:

  • CLAUDE.local.md — Recent Changes section (primary source of truth for what changed)
  • Existing change log file (if update or release mode)

For init mode, also read:

  • Meeting-Notes/ directory listing — to identify decision-bearing meetings
  • PRD/ — version history sections
  • .sync-watch.json — project name

For update mode:

  • Find the date of the last change log entry
  • Read any Meeting-Notes/ files dated after that
  • Read CLAUDE.local.md Recent Changes entries dated after that

Step 3: Extract Changes

For each source, extract structured change data:

- Date: YYYY-MM-DD
- Summary: one-line description
- Type: Feature | Enhancement | Bug Fix | Configuration | Process | Security | Documentation
- Impact: High | Medium | Low
- Components: which modules/layers/documents were affected
- Author: who made or requested the change
- Approved By: who approved (if known from meeting notes)
- Details: bullet list of specific changes
- Rationale: why the change was made
- Downstream: what else was updated as a result

Impact classification:

  • High — Changes product behavior, affects users, or modifies architecture
  • Medium — Updates documentation, adds stakeholders, changes processes
  • Low — Minor fixes, formatting, internal-only changes

Step 4: Propose Entries (update/init)

Present proposed entries to user before writing:

## Proposed Change Log Entries

### [2026-03-17] PRD v0.9 — User Journey Sections
**Type:** Enhancement | **Impact:** High
**Components:** ProductB PRD, ProductB PRD Presentation
- Added Current User Journey (6-step timeline)
- Added Future User Journey (3-layer cascading)
- Renumbered all sections (19 total)

Accept? [Y/n] or modify?

Step 5: Write

File location: Data/Change-Log-{ProjectName}.md

File structure:

# Change Log — {Product Name}

> Running record of all changes. Newest entries first.
> Generated and maintained via `/change-log` skill.

Last updated: {date}
Total entries: {count}

---

## [YYYY-MM-DD] v{X.Y} — {Summary}

**Type:** {type} | **Impact:** {impact}
**Components:** {affected components}
**Author:** {name} | **Approved By:** {name or "—"}

### Changes
- {specific change 1}
- {specific change 2}

### Rationale
- {why this change was made}

### Downstream Effects
- {what else was updated}

---

## [YYYY-MM-DD] ...

For release mode:

Collect all entries since the last release entry (or all entries if first release). Produce a summary:

## Release: v{version} — {date}

### Summary
{2-3 sentence overview of what this release includes}

### Changes Included
| Date | Type | Summary | Impact |
|------|------|---------|--------|
| ... | ... | ... | ... |

### Highlights
- {Most important change}
- {Second most important}

### Known Issues
- {Any caveats}

Critical Rules

  1. Append-only. Never modify existing entries. Only add new ones at the top.
  2. Propose before writing. Always show the user what entries will be added.
  3. Don't duplicate. Check existing entries before proposing. If a change is already logged, skip it.
  4. Real content only. Don't log trivial changes (typo fixes, formatting) unless the user specifically asks.
  5. Dates from sources. Use the date from CLAUDE.local.md or meeting notes, not today's date, for the change date. Today's date is for entries about changes made today.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting up agent training, instrumenting agents with tracing, configuring LightningStore, implementing reward functions, or optimizing prompts with RL/APO algorithms.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

coco-research/coco7602026년 10월 19일 업데이트

Post-run self-evaluation system that scores agent output on correctness, clarity, actionability, and conciseness. Use after /team runs, skill executions, or when explicitly asked to evaluate output quality.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

coco-research/coco7602026년 10월 19일 업데이트

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

coco-research/coco7602026년 10월 19일 업데이트

Use when building AI features into a product: LLM integration, RAG pipelines, guardrails, streaming, AI UX, prompt engineering, or AI cost control. Treats prompts as code and validates every model output.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

coco-research/coco7602026년 10월 19일 업데이트

Your AI research and engineering brain trust. 59 named personas across 8 cells covering frontier labs, applied product, model architecture, reasoning/RL/agents, alignment and interpretability, theory and science of DL, multimodal and…

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

coco-research/coco7602026년 10월 19일 업데이트

Use when designing a new REST or GraphQL API, reviewing an API spec before implementation, setting team API standards, or migrating REST to GraphQL. Covers resources, HTTP semantics, pagination, error handling, and pitfalls.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

coco-research/coco7602026년 10월 19일 업데이트

coco-research의 스킬 모두 보기

이 스킬의 문제 신고