mochammadshenna/go-adk-q/writing-plan

Trust tier 3
  • community
Source check pending

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

Structure a clear implementation plan before touching code. Covers goal, constraints, steps, risks, and verification criteria.

Install

npx vskill@latest install mochammadshenna/go-adk-q/writing-plan

SKILL.md

Writing a Plan

Use before any non-trivial change. A plan written in 10 minutes prevents an hour of backtracking.

When to use this skill

  • New feature spanning more than one file
  • Refactor that changes interfaces or package boundaries
  • Bug whose root cause is not yet confirmed
  • Any work that will take longer than 30 minutes to implement

Plan structure

1. Goal (one sentence)

What does "done" look like? Be concrete. Bad: "Improve the TUI." Good: "Add a /skills slash command that reads ./skills/ and lists each skill's name and description as a system message."

2. Context
  • What files are affected?
  • What existing patterns does this work build on?
  • Any constraints (API compatibility, performance, no new dependencies)?
3. Steps (ordered)

Number each step. Each step should be small enough to verify independently.

Example:

1. Add /skills to allSlashCmds in cmd/tui/slash.go
2. Implement listSkillsSummary() — reads ./skills/, parses YAML front matter
3. Handle /skills case in the enter key switch in chat.go
4. Add /skills to the help overlay bindings
5. Write a test: TestListSkillsSummary_NonEmpty
6. go build ./... && go test ./...
4. Risks and unknowns
  • What could go wrong?
  • What do you need to verify before starting?
  • Any parts you're uncertain about?
5. Verification

How will you know it works?

  • Which tests will pass?
  • What manual behaviour confirms it?
  • What does failure look like?

Rules

  • Do not start coding until steps 1-4 are written.
  • If you discover a risk during implementation that changes the plan, update the plan first.
  • Each step must be completable and verifiable on its own — no "and also" steps.
  • If a step depends on an earlier one, say so explicitly.

For this codebase specifically

Before planning any TUI change:

  1. Read the affected function in cmd/tui/chat.go or cmd/tui/slash.go
  2. Run go test ./cmd/tui/ -count=1 to confirm green baseline
  3. Check cmd/tui/mdtest_test.go for existing test patterns to follow

Before planning any provider change:

  1. Read model/oaibridge/bridge.go — all providers go through this
  2. Check cmd/tui/main.go:buildRunner() for the failover wiring

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
8

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/writing-plan/badge)](https://verified-skill.com/skills/mochammadshenna/go-adk-q/writing-plan)

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