mochammadshenna/go-adk-q/executing-plans
- community
Checking that the SKILL.md file is still in the repository.
Discipline for executing a written plan. Stay on the plan, track progress, surface blockers early, and avoid scope creep.
Install
npx vskill@latest install mochammadshenna/go-adk-q/executing-plansSKILL.md
Executing Plans
Use this skill when you have a written plan (from writing-plan) and are ready to implement. The plan is the contract — follow it.
Pre-execution checklist
Before writing the first line:
If any check fails, fix it before starting. Do not implement on a dirty baseline — you won't be able to tell what you broke.
Execution discipline
One step at a time
Complete step N fully before starting step N+1. Partial implementations compound into confusion.
Verify each step
Every step in the plan has a verification. Run it. Do not move on until it passes.
Build after every change
Takes 2 seconds. Catches type errors before they compound across multiple files.
Commit atomically
Each completed step is one commit:
Atomic commits mean any step can be reverted without affecting others.
When you hit a blocker
A blocker is anything that prevents completing the current step as planned.
Do not:
- Skip the step and continue
- Silently change the approach
Do:
- Stop
- Name the blocker in one sentence
- Check if the plan needs updating
- If yes, update the plan, then continue
- If the blocker reveals the plan is wrong, run brainstorming before continuing
Scope creep detection
During implementation you will notice things you could also fix or improve. Log them — do not implement them.
Maintain a running list:
Add these to the next plan after this one finishes.
For go-adk-q specifically
Execution order for TUI changes
- Update data structures (add fields to
chatModel,styledSet, etc.) - Update
newChatModelinitializer - Add new functions/methods
- Wire into
Update()(key handling) - Wire into
View()(rendering) - Add/update tests
go build ./... && go test ./...
Execution order for provider changes
- Create
model/<name>/<name>.gowithConfig,ConfigFromEnv(),NewModel() - Add to failover chain in
cmd/tui/main.go:buildRunner() - Add to
main.go:buildRunner()(CLI path) - Add to
applyProviderSelected()substring match go build ./...
Never do this
- Edit a file without reading it first
- Run
go testand ignore a FAIL - Add an import without checking if it's already imported
- Rename a function without searching for all call sites:
grep -rn "funcName" .
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
- SKILL.md in the repositoryCheckingskills/workflow/executing-plans/SKILL.md
Popularity
- 7-day trend score
- 0
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
[](https://verified-skill.com/skills/mochammadshenna/go-adk-q/executing-plans)