本文へ移動
cccskills
無料GitHub で公開

retro-synthesizer

Synthesize sprint retrospective notes into categorized action items and patterns. Use this skill when: - You have sprint retro notes (raw text, meeting transcript, or structured notes) to process - You need to identify recurring patterns across multiple retros - You want categorized action items with owners and deadlines from retro discussions

インストール方法を見る

含まれるファイル(1)

  • SKILL.md2.8 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Retro Synthesizer

Process sprint retrospective notes into structured action items, recurring patterns, and process improvement recommendations.

Workflow

  1. Accept input — User pastes retro notes or provides file path
  2. Categorize items into: What went well, What didn't go well, Action items
  3. Tag categories: Process, Technical, Team, External
  4. Identify patterns — If previous retro outputs exist, compare for recurring themes
  5. Generate recommendations
  6. Output — Print to conversation

Categories

CategoryCovers
ProcessSprint planning, estimation, ceremonies, communication, standups
TechnicalCode quality, tech debt, tooling, CI/CD, testing, deployments
TeamCollaboration, knowledge sharing, workload balance, onboarding
ExternalDependencies, stakeholder communication, blockers from outside

Output Format

# Retro Summary — Sprint {N} ({Date})

## What Went Well
| Category | Item | Impact |
|----------|------|--------|
| Process | {description} | {why it mattered} |

## What Didn't Go Well
| Category | Item | Root Cause | Frequency |
|----------|------|-----------|-----------|
| Technical | {description} | {why it happened} | First time / Recurring |

## Action Items
| # | Action | Owner | Deadline | Category | Priority |
|---|--------|-------|----------|----------|----------|
| 1 | {specific action} | {name} | {date} | {category} | High/Med/Low |

## Recurring Patterns
{Items that appeared in 2+ retros — flag for systemic fix}

## Process Improvement Recommendations
1. {Specific recommendation with rationale}
2. {Specific recommendation with rationale}

Rules

  • Every action item MUST have an owner (name, not "team") and deadline
  • Flag items recurring across 2+ retros as "Recurring" — these need systemic fixes
  • Recommendations must be specific and actionable ("Add PR size limit of 400 lines" not "Improve code review")
  • If no previous retros available, skip "Recurring Patterns" section

Anti-Patterns

  • Don't assign action items to "the team" — assign to a person
  • Don't write vague recommendations — be specific enough to act on
  • Don't ignore "went well" items — they validate what's working

Quality Checklist

  • Every action item has an owner and deadline
  • Categories applied to all items
  • Recurring patterns identified (if history available)
  • Recommendations are specific and actionable

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Generate A/B copy variants grounded in Eugene Schwartz's awareness and market-sophistication stages and John Caples' tested-headline discipline. Every variant declares its angle, the awareness stage it targets, and a falsifiable hypothesis, and the skill recommends which pair to test first and what delta counts as signal. Use when the user says "A/B test this", "write variants", "give me options", "test different angles", "copy variants", "ab copy", "test this headline", "multiple versions", "which version is better", or wants to test copy before publishing. For reviewing copy that already exists, see copy-review. For sample size and stopping rules, see growth-experiment. For diagnosing a page rather than its words, see page-cro. For full paid ad sets by platform, see ad-campaign-writer.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Build a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Write paid ad copy for LinkedIn, Google, Meta, and YouTube. Produces multiple variants per platform, each targeting a different Eugene Schwartz awareness level and Cialdini persuasion principle. Use when the user asks for ad copy, ad variants, "write LinkedIn ads", Google ads, Meta ads, paid social copy, ad headlines, or wants creative for a paid campaign. Reads brand voice, ICP, and positioning from knowledge/. For organic social posts, see linkedin-post or social-calendar. For the landing page the ad points at, see landing-page-writer. For testing variants, see ab-copy-writer.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Design clean and consistent APIs. Use when the user says "design an API", "API design review", "design these endpoints", "REST API for X", "GraphQL schema", "API contract", "how should this endpoint work", "review my API design", or wants to create or improve an API interface - even if they don't explicitly say "API design".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

qa-aman のスキルをすべて見る

このスキルの問題を報告する