Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

New Feature

ASecurity

Clear the scratch directory and start a fresh feature context. Load when starting a new feature or resetting pipeline state.

16 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentspythonbashgit

Security Analysis

A93/100
highPerforms destructive filesystem operations

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add woditschka/agentic-coding-reference --skill new-feature --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of New Feature?

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

Security grade badge for New Feature
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/woditschka-new-feature/badge)](https://www.skillsdirectory.com/skills/woditschka-new-feature)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: new-feature
description: >-
  Clear the scratch directory and start a fresh feature context.
  Load when starting a new feature or resetting pipeline state.
compatibility:
  - claude-code
  - github-copilot
  - opencode
metadata:
  version: "1.0"
  author: team
---

# New Feature

Clear the `.scratch/` directory and start a fresh feature context.

## Instructions

1. Guard the removal: when `.scratch/handoff.jsonl` exists, run `python3 scripts/handoff.py route` first — `no-active-slice` clears it; any other decision surfaces to the user before anything is wiped. A `blocked` `human-consultation` is a paused elicitation awaiting the human's answer, never stale state.
2. Remove the entire `.scratch/` directory.
3. Recreate `.scratch/tmp/`. The `handoff.jsonl` file is created on first append by the product-requirements-expert; do not pre-create it.
4. Report what was cleared and confirm the directory is ready.
5. When the request needs discussion, load the `intake` skill: the discussion runs in this session under the product expert's contract and exits by recording an `intake-decision` — the owner's request and decisions, quoted verbatim. `route` then dispatches `product-requirements-expert` on the record (`intake-ready`). When no reply can arrive, skip the discussion and seed the `intake-decision` from the request as stated (`source: "task-prompt"`). Never seed while a `consultation-request` targeting `human` is pending — that pause resolves only through the human's reply. Invoke the `pipeline-coordinator` only for intake that neither the `intake` skill nor the `next` triage covers.

## Execution

```bash
rm -rf .scratch && mkdir -p .scratch/tmp
```

Attribution

woditschkawoditschka
View sourceMore from woditschka →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →