Skip to content
Skills Library
Programming · Planning

implement

/implement

Use when a design exists and it's time to break it into tasks and execute with subagent dispatch and review

Repository
org-gtd.el ↗
Licence
GPL-3.0
Last repository change
06.08.2026

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 06.08.2026, without references to retired models or APIs.

Licence

GPL-3.0, otwarta.

What it does and when to use it

Use when a design exists and it's time to break it into tasks and execute with subagent dispatch and review

Original author description

Use when a design exists and it's time to break it into tasks and execute with subagent dispatch and review

How it works

  1. Overview
  2. When to Use
  3. The Process
  4. Common Mistakes
Original SKILL.md headings · 97 lines, 475 words
SKILL.md preview
---
name: implement
description: Use when a design exists and it's time to break it into tasks and execute with subagent dispatch and review
---

# /implement — Plan + Execute

## Overview

**Break a design into bite-sized TDD tasks, execute each with a fresh subagent, review every task before moving on.**

**Core principle:** Small tasks + fresh subagents + two-stage review = high quality.

## When to Use

- Design exists (from `/architect` or provided by user)
- Ready to write code
- Work can be broken into independent TDD steps

## The Process

### 1. Find Design

Look for the most recent `*-design.md` in `docs/plans/`. If none found or multiple exist, ask the user which to use. If no design exists, suggest `/architect` first.

### 2. Break Into Tasks

Each task must be:
- **One TDD cycle**: one test + its implementation
- **2-5 minutes** of focused work
- **Self-contained**: all context provided inline

Template per task:
```markdown
### Task N: [Title]

**Goal**: [one sentence]
**Test**: [describe the test to write first]
**Implementation**: [describe the code to make it pass]
**Files**: [which files to create/modify]
**Acceptance Criteria**: [specific, testable]
```

### 3. Save the Plan

```
docs/plans/YYYY-MM-DD-<name>-plan.md
```

### 4. Execute Each Task

Record base SHA: `git rev-parse HEAD`

For each task, in order:

#### a. Dispatch Implementer

Use `Task` tool with `subagent_type: "tdd"`. In the prompt, include **inline**:
- Full task text (don't reference plan files — subagent can't read them)
- Relevant code snippets (read and paste the actual file content)
- Patterns to follow (paste examples from existing code)
- Acceptance criteria

**Context goes inline.** The subagent receives everything it needs in the prompt.

#### b. Spec Review

When implementer completes, dispatch `spec-reviewer` via `Task` tool with `subagent_type: "superpowers:code-reviewer"`. Include:
- The task's acceptance criteria (copy inline)
- List of changed files

If FAIL: resume implementer to fix, then re-review.

#### c. Quality Review

Dispatch `quality-reviewer` via `Task` tool with `subagent_type: "superpowers:code-reviewer"`. Include:
- Base SHA and current HEAD
- Feature context

If critical issues: resume implementer to fix, then re-review.

#### d. Move On

Only proceed to next task when both reviews pass.

### 5. After All Tasks

> Implementation complete. Use `/qa` for adversarial testing, or `/refactor` for a quality pass.

## Common Mistakes

| Mistake | Fix |
|---------|-----|
| Tasks too large (whole features) | One TDD cycle per task. If it takes >10 min, split it. |
| Expecting subagent to read plan files | Provide ALL context inline in the dispatch prompt. |
| Skipping review for "simple" tasks | Every task gets spec review + quality review. No exceptions. |
| Phase-based grouping instead of task list | Flat numbered list. Dependencies noted, not phase boundaries. |
| No plan file saved | Always save to `docs/plans/YYYY-MM-DD-<name>-plan.md`. |
| Moving on despite failed review | Fix first. Never proceed with review failures. |
| Not referencing next step | End with: "use `/qa` or `/refactor` when ready" |

Versions

RepositoryScoreLicence
This page · Trevoke/org-gtd.el100GPL-3.0
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 a1acc30b5c9f (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

  • 100subagent-dev
    Execute implementation plans using fresh subagents per task with two-stage review. Auto-triggered for plans with multiple independent tasks. Also available as /subagent-dev.
  • 82implement-spec
    Execute an approved spec's tasks.md test-first, one task per commit, with review subagents. Use when the user asks to implement or continue a spec.
  • 100subagent-driven-development
    Use when executing implementation plans with independent tasks in the current session
  • 100execute
    Dispatch and execute implementation plans with TDD and checkpoints. Use when plan is ready. Parallel by default for independent tasks.
  • 95f
    Use when forcing an implementation with Claude subagent implement + self-review. Shortcut for /implement --force --self-review --self-implement.
  • 100v1-implement-unit
    Use when explicitly implementing one planned ticket through independent review and a mergeable PR. Triggers on "implement this ticket end to end" or "/v1-implement-unit".

Feedback and reports

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