AugmentClaude

Release Retrospective Runner

Guide product leads through a structured retrospective after major or minor releases.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/agf-running-release-retro-pcliangx/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Use when product-lead is about to run a release retrospective after a successful MAJOR or MINOR release push (PATCH skipped). Provides applicability gate, pre-conditions, 7-step execution sequence, anti-patterns, and the verification gate before commit. Pairs with template docs/reviews/retro-_TEMPLATE.md and slash /agf-release-retro.

What this skill does

This skill guides product leads through a structured retrospective after MAJOR or MINOR releases. It enforces a seven-step execution sequence with pre-condition checks, role-based self-reports, cost tracking, action-item inheritance limits, and a verification gate before committing the final retrospective document to the repository.

What it does

  • Version gating: Accepts only MAJOR (vX.0.0) and MINOR (vX.Y.0) releases; PATCH releases are rejected at the applicability gate.
  • Pre-condition validation: Confirms the version exists in CHANGELOG.md, as a git tag, and as a GitHub release before proceeding.
  • Template instantiation and pre-fill: Copies docs/reviews/retro-_TEMPLATE.md to docs/reviews/retro-vX.Y.Z-YYYY-MM-DD.md with version, date, and CHANGELOG link.
  • Self-report dispatch: Sends parallel prompts to code-reviewers, QA engineers, development roles, and tech-leads (if an ADR was included) to collect highlights, pain points, and action-item candidates.
  • Cost and token tracking: Requires the user to provide four /usage token counts (input, output, cache creation, cache read) and cost category from cost-budget.md; the retrospective cannot be marked complete without these figures.
  • Action-item inheritance enforcement: Tracks how many times each action item has carried over from the previous retro; items inherited twice must either be hardened (hooks, lints, required template fields) or explicitly dropped, preventing a third inheritance.
  • Cycle-time trend analysis: After three or more retrospectives, calculates feature cycle time from start date to release tag date and flags upward trends as process or scope issues.

How to use it

Trigger this skill by typing /agf-release-retro vX.Y.Z after pushing a MAJOR or MINOR release and creating its GitHub release. Provide the version tag in vX.Y.Z format. During execution, you will be asked to supply the real /usage token counts from your Claude session. The skill produces a final markdown file ready to commit to docs/reviews/ and optionally routes the retrospective to the content writer for internal documentation.

Related skills