Skip to content
Skills Library
Programming · Building & coding

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.

Licence
MIT
Last repository change
13.11.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.

Licence

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. 1. Pin down the request
  2. 2. Scope lock — write it down
  3. 3. Read
  4. 4. Plan
  5. 5. Loop per step
  6. 6. Scope check
  7. 7. Prove
Original SKILL.md headings · 39 lines, 332 words
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

RepositoryScoreLicence
This page · AndreasTopuh/agent-workflow-kit100MIT
ericrisco/rsc-harness100MIT
yonatangross/orchestkit100MIT
sentimony/agentic-workflow100MIT
moberghr/mtk-agent-toolkit100MIT
michielvandermeer/skills100MIT
rossumai/claude-marketplace100MIT
userKael/rastro100MIT
yonatangross/orchestkit100MIT

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…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.