implement
/implement
Use when adding a feature, changing behaviour, refactoring, or changing UI / design to a new requirement (Indonesian: buat, tambah, ubah, ganti, jadikan, perbaiki design, rapikan). Pins down measurable goals, locks scope, then works in small verified steps.
- Author
- AndreasTopuh ↗
- Repository
- agent-workflow-kit ↗
- Licence
- MIT
- Last repository change
- 13.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use when adding a feature, changing behaviour, refactoring, or changing UI / design to a new requirement (Indonesian: buat, tambah, ubah, ganti, jadikan, perbaiki design, rapikan). Pins down measurable goals, locks scope, then works in small verified steps.
Original author description
Use when adding a feature, changing behaviour, refactoring, or changing UI / design to a new requirement (Indonesian: buat, tambah, ubah, ganti, jadikan, perbaiki design, rapikan). Pins down measurable goals, locks scope, then works in small verified steps.
How it works
- 1. Pin down the request
- 2. Scope lock — write it down
- 3. Read
- 4. Plan
- 5. Loop per step
- 6. Scope check
- 7. Prove
SKILL.md preview
---
name: implement
description: >-
Use when adding a feature, changing behaviour, refactoring, or changing UI / design to a
new requirement (Indonesian: buat, tambah, ubah, ganti, jadikan, perbaiki design, rapikan).
Pins down measurable goals, locks scope, then works in small verified steps.
---
# Implement a change
## 1. Pin down the request
- Restate it in 1 sentence. Two readings with different results → ask ONE short question with options.
- Vague wish ("lebih rapi", "smooth", "seperti ChatGPT", "cepat dan berhasil") → write 2–4 MEASURABLE checks.
Examples: "no layout shift > 2 px", "select sits top-right at 375 px and 1440 px",
"first token < 1 s", "0 console errors", "all 12 existing tests still pass".
- The user referenced an example (screenshot, website, another screen) → look at it first.
## 2. Scope lock — write it down
- WILL change: <files / behaviour>
- WILL NOT change: <neighbouring features that must survive, e.g. quick answers,
existing props, the payload sent to the API/AI, stored data format>
## 3. Read
- Read every file you will edit (the relevant parts).
- `grep` every symbol you will touch: callers, tests, types, configs.
- Find an existing similar implementation in this codebase and copy its pattern.
- Check real APIs in `node_modules` types or official docs. Never guess props, flags or config keys.
## 4. Plan
- 3+ steps → task list (your tool's todo/task tool). Each step small and checkable on its own.
- For each step note HOW you will check it (which test / command / screen).
## 5. Loop per step
edit → narrowest typecheck / lint / test → READ the output → fix or continue.
- An error you caused → fix it now, before the next step.
- Never: weaken tests, `@ts-ignore`, `as any`, empty catch, `|| true` to get green.
## 6. Scope check
- `git diff --stat` then `git diff`. Every hunk must map to the request.
Revert anything else (reformatting, renames, removed features).
- Check every "WILL NOT change" item still works.
## 7. Prove
- Visible change → skill `prove-in-browser`.
- New logic → a test for it that fails without the change.
- Then skill `verify-done`, then the report block from AGENTS.md §9.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · AndreasTopuh/agent-workflow-kit | 100 | MIT |
| ericrisco/rsc-harness | 100 | MIT |
| yonatangross/orchestkit | 100 | MIT |
| sentimony/agentic-workflow | 100 | MIT |
| moberghr/mtk-agent-toolkit | 100 | MIT |
| michielvandermeer/skills | 100 | MIT |
| rossumai/claude-marketplace | 100 | MIT |
| userKael/rastro | 100 | MIT |
| yonatangross/orchestkit | 100 | MIT |
Database snapshot: 13.11.2026 · package version 80c1909b2196 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100refactoring-specialist
Plans and performs behaviour-preserving refactoring in small, test-protected steps, starting with characterisation tests for untested code. Use when improving structure without changing behaviour. - 100refactoring-specialist
Plans and performs behaviour-preserving refactoring in small, test-protected steps, starting with characterisation tests for untested code. Use when improving structure without changing behaviour. - 100refactoring-workflow
Improve the structure of existing code without changing its behaviour, in small verified steps under a green test suite. Use when the user asks to refactor, clean up, restructure or simplify code, wants to reduce duplication or coupling, is preparing a codebase for a feature it… - 100test-first
Use when implementing a feature, fixing a bug, refactoring, or changing behaviour in any codebase, before writing the production code that does it. - 100refactor
Plans and performs a behaviour-preserving refactor in small steps with the test suite green before, during and after. Use when code is hard to change, duplicated, too large, or when a tech-debt item is scheduled. - 100pstack-feature
pstack feature playbook: turn a requirement into a shipped change. Restate it, survey the subsystem, compare two designs, write a throughput checkpoint, build in small verified units, verify on the real surface. Use for /pstack-feature, or when asked to analyse and implement a…