Agent skill · Data & Analytics

retro

Brutally honest engineering retrospective. Analyzes git history for what actually happened — not what people think happened. Gives blunt, specific, data-backed feedback per contributor. No vibes, only data.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill retro-blakeox-llm-skills --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 3 KB
Bundled scripts: none
Path: skills/analysis/retro-blakeox-llm-skills/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

Read `../_house-style/house-style.md` before starting. ## Anchor phrases - Git is the source of truth. Not memory. Not standups. Not Slack. - More commits does not mean more output. More LOC does not mean more value. - "Great job everyone" is not feedback. It's the absence of feedback. - Specific praise builds trust. Vague praise builds nothing. ## Domain-specific examples **Contributor feedback — wrong way:** "Alice had a productive week with lots of commits. She's doing great work on the payment system. Keep it up!" **Contributor feedback — right way:** "**Alice** — 12 commits, +1.8k LOC, 8% test ratio, 3 PRs. All PRs under 200 LOC — disciplined. Shipped the Stripe webhook handler (`app/services/webhooks/stripe.rb`) with retry logic and idempotency keys — this is the kind of infrastructure that prevents 2am pages. **Growth opportunity:** test ratio at 8% on payment code is a liability. The webhook handler has no test for the duplicate-event path, which is the most common Stripe failure mode. Add integration tests for duplicate and out-of-order events before the next payment feature goes in." **Team observation — wrong way:** "Overall a productive week. We should try to write more

What's inside
Steps it walks through
  1. Anchor phrases
  2. Domain-specific examples
  3. Data collection
  4. Output format
  5. Period summary
  6. Biggest wins
  7. Biggest problems
  8. Per-contributor breakdown
  9. Hotspots
  10. Risks
  11. Three things to change
  12. Devil's advocate
  13. What I didn't check
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the retro skill do?

Brutally honest engineering retrospective. Analyzes git history for what actually happened — not what people think happened. Gives blunt, specific, data-backed feedback per contributor. No vibes, only data.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill retro-blakeox-llm-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going