Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Implement

ASecurity

Full TDD implementation of a feature with review cycles

2 stars
0 votes
0 copies
1 views
Added 9/29/2026
code-quality

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add abnegate/claudes --skill implement --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Implement?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Implement
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/abnegate-implement/badge)](https://www.skillsdirectory.com/skills/abnegate-implement)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: implement
description: Full TDD implementation of a feature with review cycles
argument-hint: <feature description>
---

# Implement Feature (TDD)

Complete end-to-end implementation of a feature using Test-Driven Development with code review cycles.

**YOU MUST NOT STOP UNTIL THE ENTIRE PLAN IS IMPLEMENTED. NO TODOS. NO PARTIAL WORK.**

## Arguments

- `$ARGUMENTS` - Feature, fix, or chore description

## Phase 0: Clarify Requirements

Ask questions until you have COMPLETE understanding:

- What exactly should this feature do?
- What are the edge cases and acceptance criteria?
- Are there existing patterns to follow?
- Are there any constraints or requirements?

Use `AskUserQuestion` to gather any missing information. Do NOT proceed with ambiguity.

## Phase 1: Orchestrate

Invoke the **consolidation** skill, which loads the full orchestration cycle into your context. You become the conductor and dispatch each stage:

```
Skill(skill="skills:consolidation", args="## Task\n[full feature description from $ARGUMENTS]\n\n## Acceptance criteria\n[from Phase 0]\n\n## Constraints\n- TDD: write failing tests before implementation for every subtask\n- Every subtask must include its own tests\n- Follow project conventions\n\n## Working directory\n[cwd]")
```

The cycle handles:
1. **Planner** — decomposes the feature into subtasks, maps files and dependencies
2. **Verifier** — validates the plan for correctness and efficiency
3. **Parallel architects** — execute subtasks in worktrees (each doing TDD red-green-refactor)
4. **Consolidator** — merges all branches, resolves overlaps, wires integration points
5. **Reviewer** — reviews the merged output, fixes are applied
6. **Verifier** — confirms all acceptance criteria are met, tests pass, lint clean

The skill runs in *your* context: you conduct it (the consolidation skill decides whether to delegate workstreams to `conductor` subagents).

## Phase 2: Commit

After the cycle completes, delegate to `skills:commit` (or `skills:commit-all` if multiple logical groups).

## Completion Criteria

The cycle's final verifier confirms these before it ends, but double-check:

1. ALL tests pass
2. Code is reviewed (reviewer) and issues addressed
3. No TODOs or placeholders in code
4. Feature works end-to-end
5. Lint and build pass

## Hard Rules

1. **NO STOPPING MID-FEATURE** — complete the entire task
2. **NO SKIPPING TESTS** — TDD is mandatory (communicated via skill args)
3. **NO PLACEHOLDERS** — implement fully or don't start
4. **ASK QUESTIONS EARLY** — don't guess requirements (Phase 0)
5. **NO "PRE-EXISTING" EXCUSES** — if any test fails, fix it. Always complete with passing tests.

Attribution

abnegateabnegate
View sourceSee grades on GitHubMore from abnegate →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman Review

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

1100021 votes

Caveman Commit

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

1100021 votes

Verification Loop

一个全面的 Claude Code 会话验证系统。

2456590 votes

Springboot Verification

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

2456590 votes

Django Verification

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

2456590 votes
View all in code-quality →