mochammadshenna/go-adk-q/retro

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Engineering retrospective for go-adk-q. Review what shipped, what broke, what slowed us down, and what to do differently next time.

Install

npx vskill@latest install mochammadshenna/go-adk-q/retro

SKILL.md

Retro

Run after a sprint, milestone, or significant feature. Keep it short. The goal is actionable output, not a therapy session.

Format (timebox: 20 minutes)

What shipped

List everything merged or completed since the last retro. Be specific: feature names, bug fixes, refactors.

Example:

- Glamour markdown rendering (replaces hand-rolled renderer)
- Slash command autocomplete menu
- Theme change now invalidates renderer cache
- /skills TUI command
- 6 new skill files: qa, test-driven, health, writing-plan, retro, brainstorming
What worked well

Patterns, tools, or decisions that made work faster or higher quality. Keep for next time.

Example:

- Writing failing tests before implementing (caught the renderer cache bug immediately)
- Small atomic commits — easy to revert individual changes
- Reading existing code before touching anything
What was painful

Friction, mistakes, or time sinks. Be honest.

Example:

- Edit tool appended instead of replacing — need to use Write for full-file rewrites
- Forgot to run go build after edits twice — costs 30 seconds each time
- Provider key management during testing is manual and error-prone
What to change

One action per pain point. Concrete, not vague.

Example:

- Pain: Edit tool duplicate content → Action: use Write for whole-file rewrites
- Pain: Build not run after edits → Action: always run go build before marking done
- Pain: Manual provider testing → Action: add make smoke-test target
Metrics snapshot

Run these and record the numbers:

bash
go test -count=1 ./... 2>&1 | tail -5 # test count and status
go test -cover ./cmd/tui/ 2>&1 | grep coverage # coverage %
git log --oneline -10 # recent commits
wc -l cmd/tui/chat.go # file size (watch for growth)
ls skills/ | wc -l # skill count
One thing to try next sprint

Pick one experiment. Small enough to evaluate in one week.

Example: "Add a Makefile target make qa that runs build + vet + test + staticcheck in sequence."

Output

Write the retro as a dated entry in docs/RETRO.md (create if it doesn't exist). Append — never overwrite previous retros.

Format:

markdown
## Retro — YYYY-MM-DD
### Shipped
...
### Worked well
...
### Painful
...
### Changes
...
### Metrics
Tests: N passing | Coverage: X% | Skills: N | chat.go: N lines
### Next experiment
...

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
1
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/mochammadshenna/go-adk-q/retro/badge)](https://verified-skill.com/skills/mochammadshenna/go-adk-q/retro)

Something wrong with this skill or its page? Tell us.